2013年3月27日 星期三

PDFOnline 線上將 PDF 轉 Word、Word 轉 PDF

PDF 和 DOC 是相當常見的兩種文件格式,無論是學生或上班族,一定曾經遇過需要將兩者轉檔的處境,要把 Word 轉為 PDF 比較簡單,直接在 Word 裡將檔案儲存為 PDF 格式即可,若要把 PDF 文件轉成 Word(DOC)格式就比較麻煩了,其實有許多網路服務都提供在線上免費轉檔(PDF 轉檔工具),無需額外下載或安裝任何軟體,把要轉檔的文件上傳即可。

http://www.pdfonline.com/pdf-to-word-converter/

2011年12月17日 星期六

What can natural language processing do for clinical decision support?Ch#6-8

6. Providing evidence: personalized context-sensitive summarization and question answering
6。提供證據:個性化上下文敏感總結和答疑

The need to link evidence to patients’ records was stated in the 1977 assessment of computer-based medical information systems undertaken because of increased concern over the quality and rising costs of medical care [103]. The assessment concluded that the quality and cost concerns could be addressed by medical information systems that will supply physicians with information and incorporate valid ?ndings of medical research [103]. The results of medical research might soon become directly available through querying clinical research databases, however to date, ?ndings of medical research can be primarily found in the literature. Following the 1977 report, medical informatics research focused on understanding physicians’ information needs and enabling physicians’ access to the published results of clinical studies. This research provides a solid foundation for NLP aimed at satisfying physicians’ desiderata. The most desired features include comprehensive specific bottom-line recommendations that anticipate and directly answer clinical questions, rapid access, current information, and evidence-based rationale for recommendations [104].

需要聯繫的證據,病人的病歷中申明1977年開展以計算機為基礎的醫療信息系統的評估,因為日益關注的質量和成本上升的醫療[103]。評估得出的結論是質量和成本問題,可以通過醫療信息系統,將提供資料的醫生和納入有效的醫療研究結果[103]。醫學研究的結果可能很快成為直接可通過查詢臨床研究數據庫,但迄今為止,醫學研究的結果可以主要見於文獻中。繼1977年的報告,醫學信息學研究主要集中在了解醫師的信息需求,使醫生獲得臨床研究結果公佈。這項研究提供了一個堅實的基礎,旨在滿足醫生的必要條件為 NLP。最想要的功能包括全面具體的底線預測和建議,直接回答的臨床問題,快速訪問,當前的信息,和證據為基礎的建議的理由[104]。

6.1. Clinical data and evidence summarization for clinicians

6.1。為臨床的臨床資料和證據匯總

Unlike the comparatively better researched summarization and visualization of structured clinical data [105–108], summarization of clinical narrative is an evolving area of research. Afantenos et al. surveyed the potential of summarization technology in the medical domain [109]. Van Vleck et al. identified information physicians consider relevant to summarizing a patient’s medical history in the medical record. The following categories were identified as necessary to capturing patient’s history: Labs and Tests, Problem and Treatment, History, Findings, Allergies, Meds, Plan, and Identifying Info [110]. Meng et al. approached generation of clinical notes as an extractive summarization problem [111]. In this approach, sentences containing patient information that needs to be repeated are extracted based on their rhetorical categories determined using semantic patterns. This extraction method compares favorably to the baseline extraction method (the position of a sentence in the note) on a test set of 162 sentences in urological clinical notes [111]. Cao et al summarized patients’ discharge summaries into problem lists [70].

不同於相對更好的研究總結和結構性的臨床數據的可視化[105-108],總結臨床敘事研究發展的領域。 Afantenos等。調查匯總的技術在醫療領域的潛力[109]。範 Vleck等。總結在一個病人的病歷,病歷確定的信息,醫生認為有關。要捕捉患者的病史,實驗室和試驗,存在的問題及處理,歷史,結果,過敏,MEDS,計劃,並確定信息[110]被確定為以下類別。 Meng等人。走近臨床筆記一代作為採掘總結問題[111]。在這種方法中,包含病人的信息,需要重複的句子中提取的基礎上確定使用語義模式的修辭類別。這種提取方法相比,毫不遜色在泌尿外科臨床記錄的162句的測試集上的基線提取方法(注意在一個句子中的位置)[111]。問題列出曹等人總結病人出院摘要[70]。

The PERSIVAL project (a prototype system, not currently in use) summarized medical scienti?c publications [112,113]. The summarization module of the PERSIVAL system generated summaries tailored for physicians and patients. Summaries generated for a physician contained information relevant to a specific patient’s record. Each publication was represented using a set of templates. Templates were then clustered into semantically related units in order to generate a summary [112,113].

PERSIVAL項目(一個原型系統,目前尚未使用)總結醫學科學出版物[112113]。總結 PERSIVAL系統模塊產生的摘要,為醫生和患者量身定做。醫生的生成摘要中包含的信息有關的特定病人的記錄。每個發布代表用一組模板。模板,然後將語義相關的單位集中在以生成摘要[112113]。

Based on the semantic abstraction paradigm, Fiszman et al. are developing a summarization system that relies on SemRep for semantic interpretation of the biomedical literature. The system condenses SemRep predications and presents them in graphical format [114]. We hope to see in the future if the above method holds promise for summarization and visual presentation of clinical notes.
基於語義的抽象範式,Fiszman等。正在開發一個總結系統上依賴於生物醫學文獻的語義解釋 SemRep。該系統凝結 SemRep predications和圖形格式[114]。我們希望看到在未來,如果上面的方法保存總結和視覺表現的臨床筆記承諾。

6.2. Clinical data and evidence summarization for patients
6.2。為患者的臨床資料和證據匯總

The online access to personal health and medical records and the overwhelming amount of health-related information available to patients (alternatively called health care consumers and lay users) pose many interesting questions. Hardcastle and Hallet studied which text segments of a patient record require explanation before being released to patients and what types of explanation are appropriate [115]. Elhadad and Sutaria presented an unsupervised method for building a lexicon of semantically equivalent pairs of technical and lay medical terms [116].
    Ahlfeldt et al. surveyed issues related to communicating technical medical terms in everyday language for patients and generating patient-friendly texts [117]. The survey presents research on alleviating the lack of understanding of clinical documents caused by medical terminology. This research includes generation of patient vocabularies and matching those vocabularies and problem lists with standard terminologies; generation of terminological resources, corpora and annotation tool; development of natural consumer  anguage generation systems; and customization of patient education materials [117]. Green presents the design of a discourse generator that plans the content and organization of lay-oriented genetic counseling documents to assist drafting letters that summarize the results for patients [118].

在線訪問個人健康和醫療記錄和健康有關的信息提供給患者(或者稱為醫療保健消費者,奠定用戶)絕大多數量,提出了許多有趣的問題。Hardcastle和Hallet研究病人記錄的文本段需要被釋放之前向患者解釋和什麼類型的解釋是適當的[115]。Elhadad和Sutaria提出了建設一個詞彙語義上等同於對技術的無監督方法和非專業醫學術語[116]。
    Ahlfeldt等人。在日常語言溝通技術的醫療條件,為病人和病人友好的文本[117]有關調查的問題。調查研究提出減輕缺乏引起的臨床醫療術語文件的理解。這項研究包括病人的詞彙和匹配的詞彙和標準術語的問題列出代代用語上的資源,語料庫和註釋工具;自然消費 anguage發電系統的發展;和定制的患者教育材料[117]。綠色呈現一個話語發生器的設計,計劃奠定面向遺傳諮詢文件的內容和組織協助起草的信件,總結患者的結果[118]。

6.3. Clinical question answering
6.3。臨床問題回答

One of the principal purposes of CDS is answering questions[14]. Questions occurring in clinical situations could pertain to "information on particular patients; data on health and sickness within the local population; medical knowledge; local information on doctors available for referral; information on local social in?uences and expectations; and information on scientific, political, legal, social, management, and ethical changes affecting both how medicine is practiced and how doctors interact with individual patients” [119]. Some questions do not need NLP and can be answered directly by a known resource. For example, the NLM Go Local service19 (which connects users to health services in their local communities and directs users of the Go Local sites to MedlinePlus health information) was established to answer logistics questions by providing access to local information. Questions about particular patients are currently answered by manually browsing or searching the EHR. Answering these questions can be facilitated by summarization (which requires NLP if information is extracted from free-text fields) and visualization tools [105–108]. Facilitating access to medical knowledge by providing answers to clinical questions is an area of active NLP research [120]. The goal of clinical question answering systems is to satisfy medical knowledge questions providing answers in the form of short action items supported by strong evidence.

CDS的主要目的之一是回答問題 [14]。在臨床情況下發生的問題可能涉及到“特別是病人的信息;在當地居民的健康和疾病的數據;醫療知識,對醫生轉介的本地信息,對當地的社會影響和期望的信息;和信息科學,政治,法律,社會,管理,和道德的變化影響都實行醫藥是如何和醫生如何與個別病人的互動“[119]有些問題並不需要NLP和可直接回答已知的資源,例如,NLM的本地service19(連接用戶在當地社區衛生服務,並指導用戶轉到本地網站 MedlinePlus衛生信息)建立物流問題的答案提供訪問本地信息,關於特別是病人的問題,目前正在通過手動瀏覽或搜索的回答電子病歷回答這些問題總結(需要NLP的信息是從自由文本字段中提取)和可視化工具,可以促進[105-108]促進獲得醫療知識,提供臨床問題的答案是一個活躍的領域NLP的研究[120]。臨床問題回答系統的目標是為了滿足醫學知識的問題提供了有力的證據支持短期行動項目的形式答案

 Jacquemart and Zweigenbaum studied the feasibility of answering students’ questions in the domain of oral pathology using Web resources. Questions involving pathology,procedures, treatments,examinations, indications, diagnosis and anatomy were used to develop eight broad semantic models comprised of 66 different syntactico-semantic patterns representing the questions. The triple-based model ([concept]–(relation)–[concept]) combined with which, why, and does modalities accounted for a vast majority of questions. The formally represented questions were used to query 10 different search engines. Search results were checked manually to find a passage answering the question in a consistent context[121]

Jacquemart和Zweigenbaum回答學生的問題在口腔病理學域使用網絡資源的可行性研究。涉及病理的問題,被用來開發8大66不同syntactico的語義表示問題的模式組成的語義模型的過程,治療,檢查,適應症,診斷和解剖。基於三重模式([概念] - (關係) - [概念])結合,為什麼,不佔絕大多數的問題的方式。正式代表的問題,用於查詢10個不同的搜索引擎。檢查手動搜索結果找到一個通道,在一致的情況下回答問題[121]

The [concept]–(relation)–[concept] triples generated by SemRep can be used to generate conceptual condensates that summarize a set of documents [114], or answer speci?c questions, for example, ?nding the best pharmacotherapy for a given disease[65]. Within the EpoCare project, the same question type is answered by using an SVM to classify MEDLINE abstract sentences as containing an outcome (answer) or not and extracting the high-ranking sentences [122]. The CQA-1.0 system also implements an Evidence Based Medicine (EBM)-inspired approach to outcome extraction [120]. In addition to extracting outcomes from individual MEDLINE abstracts to answer a wide range of questions,the CQA-1.0 system aggregates answers to questions about the best drug therapy into 5–6 drug classes generated based on the individual pharmaceutical treatments extracted from each abstract. Each class is supported by the strongest patient-oriented outcome pertaining to each drug in the class. The EpoCare and CQA-1.0 systems rely on the Patient-Intervention-Comparison-Outcome (PICO) framework developed to help clinicians formulate clinical questions [99]. The MedQA system answers de?nitional questions by integrating information retrieval, extraction, and summarization techniques to automatically generate paragraph-level text [123].

[概念] - (關係) - [概念] SemRep生成的三倍,可以用來產生概念的凝析油,總結一套
文件[114],或回答具體問題,例如,找到一個給定的疾病的最佳藥物[65]。在該 EpoCare項目中,同樣的問題類型是通過使用SVM分類包含的結果(答案)或不提取的高級的句子[122]論文摘要的句子回答。CQA- 1.0系統還實現了循證醫學(EBM)啟發的結果提取方法[120]。除了提取結果個人論文摘要,回答了範圍廣泛的問題,CQA-1.0系統聚集大約為5-6類藥物的最佳藥物治療的問題的答案從每個抽象提取的個人藥物治療的基礎上產生。每個類是最強的病人為本的有關藥物類中的每個結果的支持。 EpoCare和CQA- 1.0系統依靠病人干預比較成果(皮秒)的框架,以幫助臨床醫生制定臨床問題[99]。 MedQA系統集成信息檢索,提取和總結技術,自動生成段級文字[123]定義問題的答案。

7. Clinical NLP: direct applications of NLP in healthcare
   In addition to processing text pertaining to patients and generated by clinicians and researchers, NLP methods have been applied directly to patients’ narratives for diagnostic and prognostic purposes.
   The Linguistic Inquiry and Word Count (LIWC)20 tool was used to explore personality expressed through a person’s linguistic style [124]. The LIWC tool (which calculates the percentage of words in written text that match up to 82 language dimensions) was evaluated in predicting post-bereavement improvements in mental and physical health [125], predicting adjustment to cancer [126], differentiating between the Internet message board entries and homepages of pro-anorexics or recovering anorexics [127], and recognizing suicidal and non-suicidal individuals [128]. Pestian et al. demonstrated that the sequential minimization optimization algorithm can classify completer and simulated suicide notes as well as mental health professionals [129].
   Another potential clinical NLP application is assessment of neurodegenerative impairments. Roark et al. studied automation of NLP methods for diagnosis of mild cognitive impairment (MCI).Automatic psychometric evaluation included syntactic annotation and analysis of spoken language samples elicited during neuropsychological exams of elderly subjects. Evaluation of syntactic complexity of the narrative was based on analysis of dependency structures and deviations from the standard (for English) rightbranching trees in parse trees of subjects’ utterances. Measures derived from automatic parses highly correlated with manually derived measures, indicating that automatically derived measures may be useful for discriminating between healthy and MCI subjects. [130].

7。臨床 NLP:NLP的直接應用在醫療保健
   除了處理有關患者和臨床醫生和研究人員所產生的文本,NLP方法已直接應用於病人的診斷和預後的目的“敘述。   的語言調查和Word計數(LIWC)20工具被用來探索通過人的語言風格表達的個性[124]。 LIWC工具(計算中的單詞匹配多達82個語言尺寸的書面文本的百分比)進行了評估預測後喪親之痛的改進,在精神和身體健康[125],預測調整為癌症[126],區分互聯網留言板條目和網頁的親厭食症或恢復厭食症[127],並認識到自殺及非自殺的人[128]。 Pestian等人。表明,順序最小化的優化算法分類的完備和模擬自殺筆記,以及心理衛生專業人員[129]。
   另一個潛在的臨床應用 NLP應用是神經退行性損傷評估。含有Roark等人。 NLP的方法研究自動化診斷輕度認知功能障礙(MCI)的自動心理評估包括口語樣本的語法註釋和分析引起老年受試者的神經心理學考試期間。的敘事語法的複雜性的評價是基於依賴結構和rightbranching科目“話語的解析樹的樹木(英文)的標準偏差分析。從自動產生的高度相關措施分析與手動派生的措施,表明自動派生的措施,可用於健康和MCI科目之間的歧視。 [130]。

Clinical NLP is also used for medication compliance and drug
abuse monitoring. Butler et al. explored usefulness of content analysis of Internet message board postings for detection of potentially abusable opioid analgesics [131]. In this study, attractiveness for abuse of OxyContin, Vicodin, and Kadian determined automatically (using the total number of posts by product, total number of mentions by product (including synonyms and misspellings), total number of posts containing at least one mention of each product,total number of unique authors, and the number of unique authors of posts referencing any of the 3 target products) was compared to the known attractiveness of the products. The numbers of mentions of the products were signi?cantly different and corresponded to the product attractiveness. Based on this and other metrics, the authors conclude that a systematic approach to post-marketing surveillance of Internet chatter related to pharmaceutical products is feasible [131]. Understanding patient compliance issues could help in clinical decisions. This understanding could be gained through processing of informal textual communications found in the publicly available blog postings and e-mail archives. For example, Malouf et al. analyzed 316,373 posts to 19 Internet discussion groups and other websites from 8731 distinct users and found associations (such as cognitive side effects, risks, and dosage related issues) the epilepsy patients and their caregivers have for different medications [132].

NLP也是臨床用於服藥依從性和藥物濫用監測。巴特勒等人。探討互聯網留言板帖子內容分析的用處檢測潛在的abusable阿片類鎮痛藥[131]。在這項研究中,自動確定 OxyContin,Vicodin,並 Kadian濫用的吸引力(按產品的職位總數,提到了產品的總人數(包括同義詞和拼寫錯誤),至少包含一個提到每個職位總數的產品,獨特的作者總數,和獨特的作者引用的3個目標產品)的職位數相比,產品的已知的吸引力。提到的產品的數量均顯著不同,相當於產品的吸引力。和其他指標的基礎上,作者得出結論,上市後監視互聯網相關的醫藥產品的喋喋不休,系統化的方法是可行的[131]。了解患者的依從性問題,可以幫助臨床決策。這種理解可能會獲得通過公開發布的博客文章和電子郵件檔案中發現的非正式文本通信處理。例如,Malouf等。分析316373職位,以19互聯網討論組和8731不同用戶和協會(如認知的副作用,風險,與劑量相關的問題)的癲癇患者和他們的照顧者的其他網站有不同的藥物[132]。

To the best of our knowledge, the applications described in this section are experimental rather than deployed and regularly used in clinical setting. The dif?culties in translation of clinical NLP research into clinical practice and obstacles in determining the level of practical engagement of NLP systems are discussed in the next section.

據我們所知,在本節中所述的應用程序,而不是部署,並在臨床上經常使用的實驗。在翻譯的NLP的臨床研究到臨床實踐,並在確定 NLP的系統的實際參與程度的障礙,困難是在下一節討論。

 Most of the above presented methods and systems were developed for speci?c users, document types and CDS goals. Future research might indicate if such systems could be easily retargeted for new users and goals and whether the retargeted systems can compete with those designed for speci?c tasks and clinical systems. Evaluation methods for measuring the impact of NLP methods on healthcare in addition to reliable standardized evaluation of NLP systems need to be developed.

上述提出的方法和系統開發為特定的用戶,文檔類型和CDS目標。未來的研究可能表明,如果這種系統可以很容易地為新用戶和目標重定向和重定向系統是否能與之抗衡的具體任務和臨床系統設計的。除了可靠NLP的系統的標準化評價的測量 NLP的方法對醫療保健的影響的評價方法需要開發。

For several issues very important to the future development of NLP for CDS, there is currently only anecdotal evidence and sparse publications. For example, with few exceptions, we do not know which of the reviewed NLP–CDS systems are actually implemented or deployed, and what makes these systems worthwhile. We might speculate that, for example, MedLEE is successfully integrated with a clinical information system because it was developed and adapted, as needed, for specific users and CDS goals, but the reason for its success could also be its sophisticated NLP. We could better judge which features determine whether NLP–CDS systems are applied outside of the experimental setting if we had more data points. We believe it would be valuable to have a special venue for presenting case studies and analysis of applied NLP systems in the near future.

NLP的CD的未來發展非常重要的幾個問題,是目前唯一的證據和稀疏的出版物。例如,除了少數例外,我們不知道其中的NLP- CDS系統實際上是實施或部署,是什麼讓這些系統值得。我們不妨推測,例如,MedLEE是成功地與臨床信息系統集成,因為它是開發和調整,需要為特定的用戶和CDS的目標,但其成功的原因也可能是其先進的自然語言處理。我們可以更好地判斷哪些功能確定是否NLP- CDS系統應用實驗的設置之外,如果我們有更多的數據點。我們相信這將是有價值的,有一個特殊的案例研究和應用自然語言處理系統的分析,在不久的將來提出場地。

Priorities in NLP development will be determined by the readiness of intended users to adopt NLP. The early successes in NLP and CDS led to high user expectations that were not always met. NLP researchers need to re-gain clinicians’ trust, which is achievable based on better understanding of the NLP strengths and weaknesses by  clinicians, as well as significant progress in biomedical NLP. Reacquainting clinicians with NLP can be facilitated by  NLP training, well-planned NLP experiments, careful and thoughtful evaluation of the results, high-quality implementation of NLP modules, semi-automated and easier methods for adapting NLP for other domains, and evaluations of NLP–CDS adequacy in satisfying user needs.

在NLP發展的優先任務將是確定的目標用戶願意採用自然語言處理。在NLP和CDS的早期成功導致高的用戶並不總是達到預期。NLP的研究人員需要重新獲得醫生的信任,這是可以實現的基礎上更好地了解NLP的長處和弱點,由臨床醫生,以及在生物醫學 NLP的方面取得了重大進展。NLP的訓練,精心策劃的NLP的實驗,細心周到的評價結果,高品質的NLP模塊的實施,半自動化,更容易適應其他域的自然語言處理的方法,和NLP的評價可以促進 Reacquainting臨床與 NLP- CDS在滿足用戶需求的充足。

We believe NLP can contribute to decision support for all groups involved in the clinical process, but the development will probably focus on the areas for which there is higher demand. For example,if researchers are more eager consumers of NLP than clinicians,NLP research into text mining and literature summarization will continue dominating the field.

我們相信NLP可以有助於在臨床過程中涉及的所有群體的決策支持,但發展很可能會集中在哪些領域有更高的要求。例如,如果研究人員正在比醫生更渴望NLP的消費者,自然語言處理到文本挖掘和總結文學的研究將繼續稱霸該領域。

The NLP CDS tasks are so numerous and complex that this area of research will succeed in making practical impact only as a result of coordinated community-wide effort.
NLP的CDS的任務是如此紛繁複雜的,這一領域的研究將成功只能作為協調社會各界的努力的結果,實際影響。

2011年12月15日 星期四

What can natural language processing do for clinical decision support?Ch#5

The early vision of medical NLP was implemented in the Linguistic String Project (LSP) system that developed the basic components and the formal representation of clinical narrative, and implemented the transformation of the free-text clinical documents into a formal representation [66]. The LSP system evolved into the Medical Language Processor (MLP) that includes the English healthcare syntactic lexicon and medically tagged lexicon, the MLP parser, parsing with English medical grammar, selection with medical co-occurrence patterns, English transformation, syntactic regularization, mapping into medical information format structures, and a set of XML tools for browsing and display.

    MedLEE is an NLP system that extracts information from clinical narratives and presents this information in structured form using a controlled vocabulary. MedLEE uses a lexicon to map terms into semantic classes and a semantic grammar to generate formal representation of sentences. It is in use at Columbia University Medical Center, and is one of the few natural language processing systems integrated with clinical information systems. MedLEE has been successfully used to process radiology reports, discharge summaries, sign-out notes, pathology reports, electrocardiogram reports, and echocardiogram reports [10,67–70]. An in-depth overview of the system and a case scenario are provided in [71].

早期醫療 NLP的願景是在語言字符串項目(LSP)系統開發的基本組成部分和臨床敘事的正式代表的實施,並實行自由的文本臨床文件轉化成一個正式的表示[66]。映射到LSP的系統,演變成醫學語言處理器(MLP),其中包括醫療的英語語法詞彙和醫療標籤的詞彙,總綱發展藍圖的解析器,解析英語語法醫療,醫療共生的模式,英國的改造,句法正規化的選擇醫療信息的格式結構,以及一套用於瀏覽和顯示 XML工具。
    MedLEE是一種自然語言處理系統,從臨床敘述中提取的信息和使用受控詞表的結構形式呈現信息。 MedLEE使用一個詞彙映射到語義類和語義語法生成句子的正式代表。它是在哥倫比亞大學醫學中心的使用,是為數不多的自然語言處理系統與臨床信息系統集成。 MedLEE已成功地用於處理放射報告,出院摘要,註銷票據,病理報告,心電圖報告,超聲心動圖報告[10,67-70]。 [71]中提供了一個深入系統的概述和情況。

The Text Analytics architecture developed in collaboration between the Mayo Clinic and IBM is using Unstructured Information Management Architecture (UIMA) to identify clinically relevant entities in clinical notes. The entities are subsequently used for information retrieval and data mining [72]. The ongoing development of this architecture resulted in two specialized pipelines:medKAT/P, which extracts cancer characteristics from pathology reports, and cTAKES, which identifies disorders, drugs, anatomical sites, and procedures in clinical notes. Evaluated on a set of manually annotated colon cancer pathology reports, MedTAS/P achieved F1-scores in the 90% range in extraction of histology, anatomical entities, and primary tumors [73]. A lower score achieved for metastatic tumors was attributed to the small number of instances in the training and test sets [73]. cTAKES and HiTEx, described below,are the first generalized clinical NLP systems to be made publicly available.

梅奧診所和IBM之間的合作開發文本分析的架構是使用非結構化信息管理架構(UIMA)在臨床筆記,以確定臨床相關的實體。這些實體隨後用於信息檢索和數據挖掘[72]。這種架構的持續發展造成了兩個專門的管道:medKAT/ P提取癌症的特點,從病理報告,cTAKES,識別障礙,藥物,解剖部位,並在臨床筆記程序。MedTAS/ P手動註明結腸癌的病理報告進行評估,取得90%的範圍內提取組織學,解剖學的F1 -分數實體和原發腫瘤[73]。轉移性腫瘤所取得的分數較低歸因於少數的實例在訓練和測試集[73]。 cTAKES和Hitex和所述,是廣義臨床 NLP的系統可以公之於眾。

Developed at the National Center for Biomedical Computing,Informatics for Integrating Biology & the Bedside (I2B2), the Health Information Text Extraction (HiTEx) tool based on GATE is a modular system that assembles a different pipeline for extracting specific findings from clinical narrative. For example, a pipeline to extract diagnoses is formed by applying sequentially a section splitter, section filter, sentence splitter, sentence tokenizer, POStagger, noun phrase finder, UMLS concept mapper, and negation finder [74]. A pipeline for extraction of family history from discharge summaries and outpatient clinic notes evaluated on 350 sentences achieved 85% precision and 87% recall in identifying diagnoses; 96% precision and 93% recall differentiating family history from patient history; and 92% precision and recall exactly assigning diagnoses to family members [75].

在國家生物醫學計算中心的開發,信息整合生物學及床頭(I2B2),門極的健康信息的文本提取工具(HiTEx)是一個模塊化系統,組裝不同的管道從臨床敘事中提取的具體結果。例如,管道提取的診斷是由應用順序一個部分分離器,過濾器節,句子分配器,句子標記生成器,POStagger,查找名詞短語,UMLS概念映射器,並否定取景器[74]。一個管道提取家族史出院摘要及門診的350句注意到評估的精確度達到85%和87%,在確定診斷召回,96%的精度,從病史和93%召回差異化的家族史;和92%的準確率和召回完全分配家庭成員的診斷[75]。

The MediClass (a ‘‘Medical Classifier”) system was designed to automatically detect clinical events in any electronic medical record by analyzing the coded and free-text portions of the record.It was assessed in detecting care delivery for smoking cessation;immunization adverse events; and subtypes of diabetic retinopathy. Although the system architecture remained constant for each clinical event detection task, new classification rules and terminology were defined for each task [76]. For example, to detect possible vaccine reactions in the clinical notes, MediClass developers identified the relevant concepts and the linguistic structures used in clinical notes to record and attribute an adverse event to an immunization or vaccine [77]. The identified terms and structures were encoded into rules of a MediClass knowledge module that defines the classification scheme for automatic detection of possible vaccine reactions. The scheme requires detecting an explicit mention of an immunization event and detecting or inferring at least one finding of an adverse event [77]. In 227 of 248 cases (92%), MediClass correctly detected a possible vaccine reaction [77].

該 MediClass(a''Medical分類“)系統的目的是要自動檢測通過分析record.It的編碼和自由文本部分被檢測照顧戒菸交付評估任何電子病歷臨床事件;免疫接種後不良事件;... ...而糖尿病視網膜病變的亞型雖然系統架構仍然是每個臨床事件檢測任務不變,新的分類規則和術語為每個任務定義[76]例如,及時發現可能的臨床筆記疫苗反應,MediClass開發商確定有關的概念和臨床記錄用於記錄和不良事件的屬性到一個或疫苗接種的語言結構 [77]。已確定的條款和結構編碼成一個 MediClass知識模塊規則,定義為自動檢測的分類方案可能的疫苗反應,該計劃要求檢測到的免疫活動,並明確提到檢測或推斷至少有一個不良事件的發現[77],在227248例(92%),MediClass正確偵測到可能的疫苗反應[77]。

5.2. Specialized clinical NLP systems
5.2。專業臨床 NLP系統

The evaluation of the general-purpose architectures in specific tasks and the use of the general-purpose systems as components or foundation of many task- or document-specific systems, make the line between these system types somewhat fuzzy. The differences are most probably not in the end-results but in the initial goals of developing a system to process free text for any task versus solving a specific clinical task. Independent of the starting point and reuse of the general-purpose components, solving a specific task at minimum requires developing a task-specific database and decision rules. Some examples of task-speci?c systems are provided in this section.

評價的具體任務的通用架構和組件或許多基礎任務或文檔特定系統的通用系統的使用,使這些系統類型之間的線有點模糊。差異是最有可能在最終的結果,但在開發一個系統,任何任務與解決一個特定的臨床任務來處理自由文本的初步目標。獨立的出發點和通用組件的重用,至少解決一個特定的任務,需要制定一個特定任務的數據庫和決策規則。本條規定的具體任務系統的一些例子。

5.2.2. Processing radiology reports
   Radiology reports are probably the most studied type of clinical narrative. This extremely important source of clinical data provides information not otherwise available in the coded data and allows performing tasks from coding of the findings and impressions [67,80], to detection of imaging technique suggested for followup or repeated examinations [81], to decision support for nosocomial infections [19], to biosurveillance [82]. The complete description of systems developed for processing of radiology reports is beyond the scope of this review. This section outlines the scope and research directions in processing of radiology reports and omits most of the radiology report studies based on the described above general-purpose systems.

5.2.2。處理放射報告
   放射科報告可能是臨床敘事研究最多的類型。這極其重要的臨床資料來源提供的信息不能編碼數據,並允許執行任務編碼[67,80],建議後續或重複檢查的成像技術檢測的結果和印象[81],決定對院內感染的支持[19],生物監測[82]。放射報告處理開發完整的系統描述,是本次審查的範圍之外。本節概述了在處理放射報告的範圍和研究方向,並省略了大部分的放射報告的研究基礎上,上述通用系統描述。

A family of systems with the initial goal of processing radiology
reports was developed at the LDS Hospital (Intermountain Healthcare). The Special Purpose Radiology Understanding System (SPRUS) extracts and encodes the findings and the radiologists’ interpretations using information from a diagnostic expert system [80]. SPRUS was followed by the Natural language Understanding Systems (NLUS) and Symbolic Text Processor (SymText) systems that combine semantic knowledge stored and applied in the form of a Bayesian Network with syntactic analysis based on a set of
augmented transition network (ATN) grammars [83,84]. SymText was deployed at LDS Hospital for semi-automatic coding of admit diagnoses to ICD-9 codes [85]. SymText was also used to automatically extract interpretations from Ventilation/Perfusion lung scan reports for monitoring diagnostic performance of radiologists [86]. The accuracy of the system in identifying pneumonia-related concepts and inferring the presence or absence of acute bacterial neumonia was evaluated using 292 chest X-ray reports annotated by physicians and lay persons. The 95% recall, 78% precision, and 85% specificity achieved by the system were comparable to that of physicians and better than that of lay persons [19]. SymText evolved to MPLUS (M+), which also uses a semantic model based on Bayesian Networks (BNs), but differs from SymText in the size and modularity of its semantic BNs and in its use of a chart parser [87]. M+ was evaluated for the extraction of American College of Radiology utilization review codes from 600 head CT reports. The system achieved 87% recall, 98% specificity and 85% precision in classifying reports as positive (containing brain conditions) [87].

一個家庭系統與最初的目標處理放射報告是在LDS醫院(山間健康護理)。特殊用途放射了解系統(SPRUS)提取和編碼結果,並在放射科醫生“從診斷專家系統使用的信息的解釋[80]。 SPRUS其次是自然語言理解(NLUS)和符號文字處理器(SymText)系統結合語義知識的形式存儲和應用基於一組與句法分析的貝葉斯網絡擴充轉移網絡(ATN)文法[83,84]。 SymText部署在LDS醫院承認半自動編碼ICD- 9編碼的診斷[85]。 SymText也被用來自動ically提取肺通氣 /灌注掃描的解釋監測的放射診斷性能報告[86]。在確定肺炎相關系統的精度概念和推理急性細菌的存在或缺乏肺炎是評估使用292胸部X光報告註明醫生和非法律專業人士。召回95%,78%的精度,系統所取得的85%,特異性相媲美,醫生和優於非法律專業人士[19]。 SymText到MPLUS(M +),還採用了基於語義模型的演變貝葉斯網絡(BNS)在大小不同,但是從 SymText和其語義 BNS的模塊化,並在其使用圖表分析器[87]。 M +的評估,美國學院的提取放射利用率從600頭顱 CT報告審查代碼。 “系統實現召回87%,特異性98%和85%的精度分類為陽性的報告(含腦條件)[87]。

M+ was also evaluated for classifying chief complaints into syndrome categories [88]. Currently, M+ has been redesigned as Onyx and is being applied to spoken dental exams [89]. These evolving NLP systems provide examples of successful retargeting to coding of other types of clinical reports.

M +的評價分為綜合徵分類[88]行政投訴。目前,M +的已經被重新設計為瑪瑙,並正在發言[89]牙科檢查。這些不斷發展的自然語言處理系統提供的成功重定向到其他類型的臨床報導的編碼的例子。

The REgenstrief data eXtraction tool (REX) coded raw version 2.x Health Level 7 (HL7) messages to a targeted small to medium sized sets of concepts for a particular purpose in a given kind of narrative text [90]. REX was applied to 39,000 chest X-rays performed at Wishard Hospital in a 21-month period to identify findings related to CHF, tuberculosis, pneumonia, suspected malignancy, compression fractions, and several other disorders. REX achieved 100% specificity for all conditions, 94–100% sensitivity,and 95–100% positive predictive value, outperforming human coders in sensitivity [90]. In contrast, mapping six types of radiology reports to a UMLS subset and then selectively recognizing most salient concepts using information retrieval techniques, resulted in 63% recall and 30% precision [91].

REgenstrief數據提取工具(REX)編碼的原始版本2.x的健康水平7(HL7)的消息有針對性的小為特定目的在敘事文本[90]一種中型集的概念。 Rex是應用到39000威舍德醫院在21個月內,以確定瑞士法郎,肺結核,肺炎,疑有惡變,壓縮分數,和其他一些疾病有關的調查結果進行胸部X射線。 REX取得的所有條件,94-100%的敏感性,以及95-100%,陽性預測值100%的特異性,在敏感性方面贏過人類編碼[90]。相比之下,映射六種類型到UMLS子集的放射報告,然後選擇性地認識到使用信息檢索技術的最顯著的概念,導致63%的召回和30%的精度[91]。

5.2.3. Processing emergency department reports
    Topaz targets 55 clinical conditions relevant for detecting pa-
tients with an acute lower respiratory syndrome [92]. Topaz uses three methods for mapping text to the 55 conditions: index UMLS concepts with MetaMap [93]; create compound concepts from UMLS concepts or keywords and section titles (e.g., Section:Neck + UMLS concept for lymphadenopathy = Cervical Lymphadenopathy); and identify measurement-value pairs (e.g.,‘‘temp” + number > 38 degrees Celsius = Fever). Topaz is built on the GATE platform and implements ConText as a GATE module for determining whether indexed conditions are present or absent,experienced by the patient or someone else, and historical, recent,or hypothetical. After integrating potentially multiple mentions of a condition from a report, agreement between Topaz and physicians reading the report was 0.85 using weighted kappa.

5.2.3。處理緊急情況部報告
黃玉目標檢測患者急性下呼吸道綜合徵[92]55有關臨床情況黃玉使用的55個條件映射文本三種方法:指數 UMLS MetaMap概念[93]; UMLS概念關鍵詞節的標題(例如,第:頸部+=頸部淋巴結腫大淋巴結腫大 UMLS概念創建複合概念;並確定測量例如,“溫度+數字>=發燒38攝氏度黃玉是建立在門平台實現確定是否索引條件存在或不存在由患者別人經驗豐富歷史,最近或假想模塊整合存在多種從報告中一個條件提到黃玉醫生閱讀報告之間協議是0.85使用加權卡帕

5.2.4. Processing pathology reports
   Surgical pathology reports are another trove of clinical data for locating information about appropriate human tissue specimens [94] and supporting cancer research. For example, a preprocessor integrated with MedLEE to abstract 13 types of findings related to risks of developing breast cancer achieved a sensitivity of 90.6% and a precision of 91.6% [69].
   In MEDSYNDIKATE, an NLP system for extraction of medical information from pathology reports, the basic sentence-level understanding of the clinical narrative (that takes into consideration grammatical knowledge, conceptual knowledge, and the link between syntactic and conceptual representations) is followed by the text-level analysis that tracks reference relations to eliminate representation errors [95].
   Liu et al. assessed the feasibility of utilizing an existing GATE pipeline for extraction of the Gleason score (a measure of tumor grade), tumor stage, and status of lymph node metastasis from free-text pathology reports [96]. The pipeline was evaluated on committing errors related to the text processing and extraction of values from the report, and errors related to semantic disagreement between the report and the gold standard. Each variable had a different profile of errors. Numerous system errors were observed for Gleason Score extraction that requires fine distinctions and TNM stage extraction requiring multiple discrete decisions.
The authors conclude that the existing system could be used to aid manual annotation or could be extended for automatic annotation [96]. These findings second observations of Schadow and McDonald that general-purpose tools and vocabularies need to be adapted to the specific needs of surgical pathology reports [94]. The Cancer Text Information Extraction System (caTIES) system, built on a GATE framework, uses MetaMap [93] and NegEx [51] to annotate findings, diagnoses, and anatomic locations in pathology reports. caTIES provides researchers with the ability to query, browse and create orders for annotated tissue data and physical material across a network of federated sources using automatically annotated pathology reports.

5.2.4。處理病理報告
   手術病理報告的其他臨床資料的寶庫,為尋找適當的人體組織標本的信息[94]和支持癌症研究。例如,預處理器集成MedLEE抽象13的結果患上乳腺癌的風險,實現了90.6%的敏感性和91.6%的精度[69]。
   MEDSYNDIKATE,病理報告為醫療信息的提取自然語言處理系統,基本句子級的臨床敘事的理解(即需要考慮語法知識,概念性知識,語法和概念的陳述之間的聯繫)其次是文本層次分析跟踪參考的關係,以消除代表性的錯誤 [95]。
   Liu等人。評估利用現有門提取的Gleason評分管道(衡量腫瘤分級),腫瘤分期和狀態從自由文本的病理報告 [96]淋巴結轉移的可行性。該管道進行了評估,提交有關的文字處理和從報告中提取值的錯誤,和錯誤有關的報告和金標準的語義之間的分歧。每個變量有不同的配置文件的錯誤。眾多的系統誤差,觀察 Gleason評分提取需要的細微差別和TNM分期提取,需要多個分立的決定。
作者得出結論:現有的系統可以用於急救手冊註釋,或可自動標註 [96]延長。這些發現需要適應手術病理報告的具體需求,通用工具和詞彙 Schadow和麥當勞的第二個觀察 [94]。癌的文本信息提取系統(caTIES)系統,建立在一個門框架,使用MetaMap [93]和NegEx [51]註釋在病理報告結果,診斷和解剖位置。 caTIES提供註明組織的數據和整個網絡的聯合使用自動註明的病理報告來源的物理材料的訂單查詢,瀏覽和創造能力的研究人員。

5.2.5. Processing a mixture of clinical note types
    The above studies indicate that natural language processing acceptable for clinical decision support is better achieved using tools developed for specific tasks and document types. It is therefore not surprising that processing of a mixture of clinical notes is successful when the task is well-defined and a small knowledge base is developed specifically for the task. For example, Meystre and Haug created a subset of the UMLS Metathesaurus for 80 problems of interest to their longitudinal Electronic Medical Record and evaluated extraction of these problems from 160 randomly selected discharge summaries, radiology reports, pathology reports,progress notes, and other document types [97]. The evaluation demonstrated that using a general purpose entity extraction tool with a custom data  subset, disambiguation, and negation detection achieves 89.2% recall and 75.3% precision [97].

5.2.5。處理臨床注意類型的混合物
    上述研究表明,自然語言處理,可以接受的臨床決策支持,更好地實現使用的具體任務和文件類型的開發工具。因此,也就不足為奇了臨床票據的混合物處理任務時,成功的定義,並專門任務開發一個小的知識基礎。例如,Meystre和豪格創造了UMLS Metathesaurus80關心的問題,其縱向的電子病歷和160隨機選擇出院摘要,放射科報告,病理報告,進度說明,以及其它類型的文檔,這些問題的評估提取的子集[97]。評估表明,使用一個自定義的數據子集,消歧,並否定檢測的一個通用實體提取工具實現召回89.2%和75.3%的精度[97]。

The MediClass system [76] was configured to automatically assess delivery of evidence-based smoking-cessation care [98]. A group of clinicians and tobacco-cessation experts met over several weeks to encode the recommended treatment model using the concepts and the types of phrases that provide evidence for smoking-cessation medications, discussions, referral activities, quitting activities, smoking and readiness-to-quit assessments. The treatment model involves five steps, ‘‘5A’s”: (1) ask about smoking status; (2) advise to quit; (3) assess a patient’s willingness to quit; (4)assist the patient’s quitting efforts; and (5) arrange follow-up. Evaluated on 500 patient records containing structured data in addition to progress notes, patient instructions, medications, referrals, reasons for visit, and other smoking-related data, MediClass performance was judged adequate to replace human coders of the 5A’s of smoking-cessation care [98].

MediClass系統[76]配置為自動評估證據為基礎的戒菸護理[98]交付 A臨床醫生和煙草戒菸專家會見幾個星期的編碼建議的治療模式使用提供戒菸藥物,討論活動戒菸活動吸煙和準備證據的概念和類型短語退出評估五個步驟,治療模式5A(1)詢問有關吸煙狀況;(2)告知退出;(3)評估病人的戒菸意願;(4)協助病人戒菸的努力;(5安排跟進除了進展注意到結構化數據500門診記錄評價病人的指示藥物轉介參觀原因其他與吸煙有關的MediClass性能判斷足夠取代戒菸保健5A人類編碼[ 98]。

The InfoBot system under development at the National Library
of Medicine identifies the elements of a well-formed clinical question [99] in clinical notes. It subsequently invokes a question answering module (the CQA 1.0 system described in Section 6.3)that extracts answers to the question about the best care plan for a given patient with the identified problems from the literature,and delivers documents containing the answers [100]. In a pilot evaluation by 16 NIH Clinical Center nurses, each evaluating 15 patient cases, documents containing answers were found to be relevant and useful in the majority of cases [101]. It remains to be seen if such automated methods of linking evidence to a patient’s record can achieve the accuracy of more controlled delivery  implemented in Infobuttons, decision support tools that deliver information based on the context of the interaction between a clinician and an EHR [102]. Automatic linking of external knowledge bases and patients’ records will be useful if the NLP systems achieve acceptable accuracy in extraction of bottom-line advice and presentation of this information in an easily comprehensible form. Extraction of the bottom-line advice and answers to clinical questions are presented in the next section.

InfoBot系統下發展,在國家圖書館
醫學標識格式良好的臨床問題[99]在臨床筆記中的元素。隨後,它調用一個問題回答模塊(CQA1.0系統在6.3節所述),提取物為從文獻中發現的問題給予病人最好的照顧計劃有關的問題的答案,並提供包含答案的文件[100]。在16 NIH臨床中心護士的試點評估,評估15個門診病例,文件包含答案發現,在大多數情況下[101],相關的和有用的。它仍然有待觀察,如果連接的證據病人的記錄等自動化的方法可以實現的更多控制交付的準確性 Infobuttons,決策支持工具,提供信息的,在一個臨床醫生和一個電子病歷[102之間]互動背景下實施。自動連接外部的知識基礎和病人的病歷,將是有益的,如果NLP系統實現可接受的準確度,在底線的意見和容易理解的形式介紹這一信息的提取。提取的底線的意見和臨床問題的答案在下一節。

2011年6月21日 星期二

轉貼-Prezi - 讓人目瞪口呆的簡報軟體

文章來源:
http://meinews.cc/techknowledge/148-prezi

Tech Knowledge 是梅心聞構思已久的專欄,主要是希望把我們認為好用的科技產品,透過梅心聞的介紹可以讓好用的東西給更多人知道
我們第一周要介紹叫做 Prezi 的簡報軟體。想必大家一定都有上台報告的機會,但是大家應該也都是用微軟的 Power Point 吧?今天我們要介紹的 Prezi,梅心聞認為 Prezi 可說是現有最酷炫也最簡單的簡報軟體喔!如何酷炫呢?我們廢話不多說,請大家自己操作看看嚕!
請大家點選 play 後,再點選 More → FullScreen,之後一直點選下一步( 同play )
酷吧!不過你若許會想,這應該很難吧,應該是要寫程式碼吧?我又不是資工系的,可能不會寫程式碼耶。
梅心聞告訴你!你錯了!Prezi 超簡單,不用你寫程式碼,只要你的滑鼠點一點、拉一拉,就可以完成酷炫的簡報了!我敢說他是個比 Power Point 還簡單的東西。而且,我們還特地寫了教學唷,相信聰明的你一定很快就可以上手的!

Prezi 簡介

Prezi 可說是個雲端的簡報製作網站,讓使用者可以在 Prezi 網站上製作簡報,甚至與許多人一同編輯同一個檔案。
因此使用prezi 必須要有個帳號,一般來說Prezi 免費版本只有 100MB 的容量,但是只要有 ".edu" 的email ( 沒錯!就是你的 oz 信箱 ) ,即可申請一個高達 500MB 的Prezi 帳號喔!
點我申請教育版 500 MB 帳號:http://prezi.com/profile/signup/edu/

Prezi 使用教學

建立完你的帳號後,點選 New Prezi、輸入檔案名稱或敘述,就可以開始編輯了喔!
進入編輯頁面後,在任何地方點兩下,輸入你想輸入的文字,而其中還有文字置左、置中、置右、對齊等選項,如下圖
dbclick
你可以使用滑鼠滾輪來 zoom in / out 來控制視窗的大小。
工具箱在左上方,如果沒看到,只要把滑鼠移到左上方,他就會跑出來了喔!其中分別有:Write, Insert, Frame, Colors & Font, Show 幾個選項,別擔心我們在下面會慢慢介紹它們的功能。
toolbox
點選 " Write " 使用prezi 專屬的「斑馬圈圈」來調整位置、大小、角度。內圈調整位置、中圈調整大小、外圈調整角度。
zebra
點 Insert 的”Load File”(快捷鍵L)上傳加入影片 or 圖片,若要嵌入youtube 影片,只要直接貼上網址就可以了喔!
youtube
點選 Insert 中的 " Shapes "(快捷鍵S) 可畫畫 or 加入箭頭
shape
使用 frame (快捷鍵F) 來決定架構與重點:
讓你的簡報條列分明這可是 Prezi 厲害的地方,他不只讓你的簡報美觀,還讓你可以給觀眾一個縱觀的overview,很清楚的讓觀眾知道你報告的重點和架構!一定要好好利用它!
frame
使用 Path 決定簡報路線,等你編輯完你的簡報內容後,最重要的就是要幫簡報排個路線。 而排定 Path 基本上有兩種方法:
 ● 一種是點選”Add” 然後,從 1 開始,每次都是點下一個所以要呈現的位置,點到最後一個位置。
 ● 另一種方法則是,調整好你所要呈現給觀眾的視窗大小,然後再點選”Capture View”(會出現一個方框表是此為 Capture View),這樣就可以把當下這視窗變成路線的下一個點了喔!
Path
最後見證奇蹟的時刻點選:Show! Full-screen。試試看你的Prezi 吧。播放簡報有兩種方式:
 ● 第一種是如上所說你可以在編輯模式下,直接點選 Show。
 ● 第二種播放方式則是,你可以把此 Prezi 檔下載至你的電腦、甚至隨身碟中帶著走!
download

Prezi 小技巧:

1. 同時選擇多個物件 ( 圖片、文字或影片 ) :按住 Shift 再連續點選物件。
2. 就跟一般的編輯軟體一樣,Prezi 可以
 ● Undo ( 回復上一個動作 ):可以點選右上角的 Undo;或者直接用快捷鍵 Ctrl + Z。
 ● copy ( 複製 )、paste ( 貼上 ):分別直接用快捷鍵 Ctrl + C、Ctrl + V。

Prezi 小缺陷:

(1) 免費教育版,中文支援的問題:
 ● 雖支援中文輸入,但部分中文文字有缺漏。
 ● 中文 colors&font 只有兩種,目前只能點選" Colors & Fonts " →" Original Style "  or " 藍色中文 享受! "。
 ● 不支援中文檔名的上傳檔案。
(2) 影片、圖片支援的問題
 ● 只支援 .FLV 格式,上傳 .SWF 格式亦可,但播放偶而有問題。(上傳 .WMV 格式有時成功有時失敗)。
 ● 下載的播放檔,在播放影片時,其下方的影片控制按鈕消失了。
 ● 圖片 .GIF 格式上傳後,不支援動畫功能,形成單純的圖片。
不過我想這應該還是瑕不掩瑜,你依然可以利用 Prezi 做出令人目瞪口呆的簡報的!

Prezi 官方教學

2011年5月24日 星期二

2011/5/25 Paper閱讀摘錄

Learning gains from using games consoles in primary classrooms: a randomized controlled study
學習增益使用遊戲機在小學教室:一項隨機對照研究

Abstract
It is known that computer games are motivating for children, but there is limited direct evidence of their effects on classroom learning. Following a successful small-scale case study conducted by the authors, the aim of this randomized controlled trial was to further investigate the effects of a commercial off-the-shelf computer game on children’s mental computation skills and on aspects of their self-perceptions. A pre-post design was employed, with 634 primary-school (elementary school) children (10-11 years old) from 32 schools across Scotland. Schools were randomly assigned to experimental or control conditions. In the experimental schools, children used a games console for 20 minutes each day, running a ‘brain training’ game. The controls continued with their normal routine. The treatment period was nine weeks.  Significant pre-post gains were found in both groups over the treatment period for both accuracy and speed of calculations. However, the gains in the games console group were up to twice those of the controls. There were no significant changes in two measures of self-concept for either group, although there was a small but statistically significant gain in attitude to school amongst the experimental group. When scores were analysed by ability, different patterns of scores were apparent. Qualitative data pointed to a range of benefits from the games-console experience. There are many implications which arise from the findings, some of which will be explored at the presentation.

摘要
據了解,電腦遊戲激發兒童,但有有限的直接證據,他們對課堂學習。繼成功的小型案例研究進行了作家,其目的本隨機對照試驗,以進一步探討影響商業現成的,現成的電腦遊戲對兒童的心理運算技能和對問題的自我認知。阿崗前性設計,與 634小學(小學)的兒童(10-11歲)32所學校在蘇格蘭。學校被隨機分配到實驗組或控制的條件。在實驗學校,兒童用的遊戲機,每天20分鐘,運行一個'大腦訓練遊戲的意義。在繼續控制他們的正常程序。治療期為 9週。重大崗前漲幅發現,兩組在治療期間的精確度和速度的計算。然而,收穫的遊戲機組的兩倍那些控件。沒有顯著變化,兩項措施的自我概念,任何一組,雖然有一個小但顯著收益的態度,學校之間在實驗組。當成績進行了分析能力,形態各異的得分明顯。定性數據指出,利益的範圍從遊戲控制台的經驗。其中有許多問題產生的結果,其中一些將探討在頒獎。

1. Background
There is a growing acceptance of the value of ICT in primary schools, with a range of applications now embedded in mainstream practice. In recent years initiatives have included the use of laptops, interactive white boards, hand-held computers and the internet. Additionally, there has long been an interest in the use of games-based applications in the classroom, with a growing interest in the potential of commercial off-the-shelf computer games (COTS) for learning in schools. The arguments for such games are framed in terms of knowledge gains, skill development, motivational aspects and cultural relevance issues (see, for example, Prensky, 2001; Kirriemuir & McFarlane, 2002; Sandford, Ulicsak, Facer & Rudd, 2006). However, as yet, the evidence of their educational value is neither extensive nor robust (Condie & Munro, 2007). In fact, in the current educational literature, much that has been written about the benefits of games and games-based learning appears to focus on the beliefs and attitudes of teachers, pupils and parents (eg McFarlane, Sparrowhawk & Heald, 2002; Facer, 2003; Sandford et al., 2006). There is a notable absence of studies that report output measures in terms of attainment.

1。背景
人們越來越多地接受信息和通信技術的價值在小學,與嵌入式應用範圍目前主流的做法。近年來舉措包括使用筆記本電腦,互動式白板,手提電腦和互聯網。此外,長期以來一直是有興趣的遊戲中使用的應用程序在課堂上,有一個越來越大的興趣,在潛在的商用的現成電腦遊戲(COTS)的學校學習。對於此類遊戲的論據是誣陷在收益方面的知識,技能發展,激勵和文化方面的相關問題(見,例如,Prensky,2001年;柯里繆爾和麥克法蘭,2002;桑福德,Ulicsak,瓦楞機及陸克文,2006)。然而,到目前為止,他們的證據既不是廣泛的教育價值,也不健壯(康迪與蒙羅,2007)。事實上,在當前的教育文獻中,已經寫入多的好處遊戲和遊戲為基礎的學習似乎把重點放在信念和態度的教師,學生及家長(如麥克法蘭,雀鷹和希爾德,2002;瓦楞機, 2003年桑福德等。,2006)。有一個顯著缺乏研究,報表輸出措施條款的實現。

2. Current study
This randomised controlled trial (RCT) followed on from a small-scale case study (Miller & Robertson, in press) which found statistically significant improvements in computation (accuracy and speed of processing) and self-perceptions when children used a COTS programme on a games console (Dr. Kawashima’s brain training) over a ten-week treatment period. The design of the current trial involved identifying schools which were in the lowest quartile in terms of socio-economic status (as measured by entitlement to free school meals) in each of the participating Regional Education Authorities. Once the pool of schools had been identified in each authority, they were randomly assigned to the experimental or control group. Each school in the experimental group was given a set of Nintendo DS lite games consoles for a primary 6 class.

2。目前的研究
這項隨機對照試驗(RCT),其次從一個小規模的案例研究(米勒和羅伯遜在新聞)顯著改善,其中發現在計算(精度和速度,加工)和自我認知,當孩子使用了一個現成方案遊戲控制台(川島博士的大腦訓練)超過十個星期的治療期。設計了目前的審判涉及查明學校在最低四分位數的計算,社會經濟地位(作為衡量學校領取免費餐)在每一個區域教育機構參加。一旦池中的學校已被確定在每一個機關,他們被隨機分配到實驗組或對照組。每所學校在實驗組給予一套任天堂的DS Lite遊戲機的主6級。

2.1. Participants
•32 schools
•4 education authorities
•Complete data set for 634 P6 children

2.1。與會者

•32所學校
•4個教育主管部門
•完整的數據集634小六兒童

2.2. Method
• Randomised controlled trial (stratified random sample)
• There were 2 conditions:
Experimental group, who used the Nintendo half an hour a day, 5 days a week playing Dr. Kawashima’s Brain Training
A control group, where the teachers were asked not to change their normal routine
• A training session was provided for the teachers who were in the Nintendo group
• The treatment period was 9 weeks
• Data collected: pre and post measures of computation (accuracy and speed), various self-measures, (eg mathematics self-concept). In addition, other data were collected: eg children’s previous performance against national standards (5-14 levels); computer use at home.

2.2。方法
•隨機對照試驗(分層隨機抽樣)
•有2個條件:
實驗組,誰使用任天堂每天半小時,每週 5天打川島博士的大腦訓練
對照組,那裡的教師被要求不能改變其正常的例行
•一個培訓課程,為教師提供了誰在任天堂組
•治療時間為9週
•數據收集:前後措施計算(準確度和速度),各種自措施(如數學自我概念)。此外,其他數據的收集,例如:孩子的表現與以前的國家標準(5-14級),電腦在家裡使用。

3. Findings
3.1. quantitative data
3.1.1.1. Accuracy (number correct)
• Statistically significant gains in both groups.
• But the mean gain in the experimental group was approximately 50% greater than that of the control group.
This difference was statistically significant.

3。調查結果
3.1。定量數據
3.1.1.1。精度(號碼是否正確)
•據統計顯著增長,兩組。
•但平均增益實驗組約為50%,超過對照組。
這種差異有統計學意義。

3.1.2. Speed of processing (time taken to complete number test)
• Statistically significant improvement in both groups.
• However, the mean improvement in the experimental group was more than twice that of the control group. This difference was highly statistically significant.

3.1.2。高速加工(需時多久完成數測試)
•顯著改善,兩組。
•然而,平均改善,實驗組兩倍以上的對照組。這種差異是非常顯著。

3.1.3. Self-concept
• No significant change in either maths self-concept or academic self-concept in either group.
3.1.3。自我概念
•沒有任何重大變化數學自我概念或學業自我概念在任一組。

3.1.4. Attitude to school
• Slight – but statistically significant – improvement in attitude towards school in the experimental group, but not in controls

3.1.4。學校的態度
•輕微-但顯著- 改善對學校的態度,在實驗組,但在控制組則否。

3.1.5. Analysis by previously recorded mathematical ability (please note: general trends – more detailed analysis to follow)
• In terms of accuracy, the less able children tended to improve more than the more able children.
• In terms of speed, the middle ability children tended to improve more than the children at the top and bottom of the ability range

3.1.5。通過事先錄製的數學分析能力(請注意:一般趨勢- 更詳細的分析如下)
•在計算準確,越能夠提高孩子往往越能比孩子。
•在計算速度,中間的能力,以改善兒童往往比孩子的頂部和底部能力範圍

3.1.6. Gender:
• There were no significant gender differences.
3.1.6。性別:
•無顯著性別差異。

3.2. qualitative data
In addition to the quantitative data collected, we also noted comments from teachers and children after the treatment period was over. Further qualitative data will be reported in due course, but some interesting findings
included:
• improvements noticed in children’s academic work: tables, basic computation, writing
• truanting and lateness had dramatically improved in some classes (the Nintendos were used at the start of the school day)
• children keen to take responsibility for the management aspects (collection, distribution, charging etc)
• improvements in interpersonal relationships (children taking a supportive interest in the performance of peers)
• children believed that they were ‘smarter’ as a result of using the game

3.2。質性資料
除了量化數據收集,我們也注意到,從教師和學生的意見後,在治療期間已經結束。進一步質性的數據將在適當時候進行報告,但一些有趣的發現
包括:
•改善注意到兒童的學業工作:表,基本計算,寫作
•逃學和遲到了顯著改善,一些類(Nintendos被用於一開始,學校的一天)
•兒童熱衷於承擔責任方面的管理(收集,分配,收費等)
•改善人際關係(兒童權益採取支持的性能同行)
•兒童認為他們是'聰明',結果使用遊戲

4. Conclusion
There are many implications here: for the use of COTS in classrooms, for the raising attainment agenda, for
teaching and learning styles, for further investigation of the domains of learning, for the management of electronic
resources once purchased, for teachers’ belief systems, and a range of other issues. These will be developed in more detail in full journal papers.
To conclude, we wish to emphasise that no sponsorship was involved in this study. Funding was provided by Learning and Teaching Scotland, (a non-departmental public body funded by the Scottish Government) with an additional contribution from one of the participating Regional Education Authorities. The authors neither asked for, nor received, financial or any other form of support from Nintendo or any other commercial organisation.

4。結論
這裡有許多影響:使用現成的課堂,為提高實現的議程,
教學和學習方式,為進一步研究的領域學習,負責管理電子
資源一旦購買,教師信念體系,以及一系列其他問題。這些將制定更詳細全面期刊論文。
最後,我們想強調,沒有贊助商參與了這項研究。經費是由蘇格蘭學習與教學,(非政府部門的公共機構由蘇格蘭政府資助)與一個額外的貢獻,從一個區域教育主管部門參加。筆者既沒有要求,也沒有得到,財務或任何其他形式的支持任天堂或任何其他商業機構。

2011年5月5日 星期四

2011/5/6 Paper閱讀摘錄

5. Conclusions
5.1. Discussion
By using knowledge of how children learn in video games, we have more information to help us determine with which games children may be more likely to engage in learning strategies that encourage the development of critical thinking skills, imagination,and creativity. Further, this knowledge of how children learn in the video game world may lead to developments in designing educational video game products and serious games, and possibly even to modi?cations of learning environments in the classroom. Gee (2003) noted the disparity between the learning environments of video gamers, who are engaged in learning games, with students in traditional school environments, who are given little control over their own learning. He recommends that learning principles from video game design can be used to understand the way children are learning in games, whichmay ultimately lead to modification of classroom instruction to make school learning more relevant to students.

5。結論
5.1。討論
通過使用兒童如何學習的知識在視頻遊戲,我們有更多的信息,以幫助我們確定哪些遊戲與兒童更有可能從事學習策略,鼓勵發展批判性思考能力,想像力和創造力。此外,這個孩子學習知識,如何在視頻遊戲世界中的事態發展可能導致視頻遊戲產品設計教育和嚴肅遊戲,甚至可能要作案?陽離子在課堂上的學習環境。吉(2003)指出,學習環境之間的差距的視頻遊戲,誰是從事學習遊戲,與學生在傳統的學校環境中,誰是給難以控制自己的學習。他建議,學習的原則,從視頻遊戲設計可以用來理解的方式孩子們在遊戲中學習,whichmay最終導致修改學校課堂教學,使學習更貼近學生。

Video games have, in part, been blamed for children’s waning ability to engage in creative play (Cordes & Miler, 2000; Healy,1998). Contrary to that belief, adventure games in particular may encourage boys to try on a new identity and imagine what it would be like to be in the fantasy world created by the game, to make decisions that make sense in that fantasy world. Vygotsky (1978) posited that children come to recognize and appreciate social norms, especially adult roles, by playing. Through play, children have the capacity to pretend and temporarily take on a different identity. Out of all the video game genres explored in this study, it seems that children (and boys in particular) are most likely to engage in this positive form of creative play and imagining when playing adventure games. Action games encourage simple repetition, which may not be as intellectually stimulating as other genres of games, but may encourage patience and perseverance. Important elements of action games that encourage repetition without undue frustration are immediate feedback, rewards for improvement, and lack of punishment for repeated failure (Gee, 2003). It should be noted, however, that the correlational nature of the relationship makes it unclear whether the games of a particular genre encourage children to use certain learning strategies or if children tend to choose games of the genre that requires their preferred learning style to succeed based on game design.

電子遊戲,在某種程度上,被指責為兒童能力逐漸減弱從事創造性遊戲科德斯米勒,2000;希利,1998)。相反,這種信念,冒險遊戲,尤其可鼓勵孩子嘗試一種新的身份和想像它會像幻想世界創造的遊戲,作出決定,在這個有意義的幻想世界維果茨基1978)假定,孩子們認識和欣賞社會規範,尤其是成人的角色通過打通過玩耍,孩子們有能力假裝並暫時採取不同的身份在所有的視頻遊戲類型探討在這項研究中,似乎兒童(特別是男孩)是最有可能從事這種積極的形式,創造性的發揮和想像,當播放的冒險遊戲。鼓勵簡單的重複動作遊戲,它可能不會像其他類型智力刺激的遊戲,可能會鼓勵耐心和毅力。動作遊戲的重要元素,避免不必要的重複,鼓勵挫折及時反饋,獎勵改善,以及缺乏懲罰屢次失敗(哎呀,2003年)。應當指出不過,這自然關係的相關性還不清楚是否一個特定類型的遊戲鼓勵孩子使用一定的學習策略,或者如果孩子往往選擇遊戲類型,需要他們喜歡的學習方式取得成功的基礎在遊戲設計

This study gives preliminary evidence that girls, more often than boys, prefer to learn games through innovative strategies and exploration. When playing adventure games, however, they tend to prefer observing others before playing themselves. This is an interesting paradox between tendencies toward observation and tendencies toward exploration. The difference may be due differences in the game genres. Adventure games take place in fantasy worlds, each with its unique set of rules and customs. Perhaps when placed in such a new and open-ended environment girls would prefer to gain knowledge from watching someone else’ successes and failures before participating themselves. The other types of game play, however – simulation, educational, and action games – tend to be more concrete. The girls in this study were inclined to play simulations such as The Sims and Zoo Tycoon, as well as Webkinz games. The worlds in which these games take place are more similar to the real world, and thus provide a sense of familiarity. This study indicates that in these circumstances, girls prefer to use innovative strategies and to be able to explore the tools and activities available in the game. Further research is needed to see if this translates to learning styles in other contexts besides video games. If so, it would suggest that girls should be given freedom to explore and try new things in educational situations that are familiar to them, and that they may prefer to watch others before participating in new and unfamiliar learning environments.

這項研究提供了初步證據表明,女孩比男孩更經常,更喜歡通過遊戲學習和探索創新戰略。當玩冒險遊戲,但是,他們往往更喜歡觀察別人在玩自己。這是一個有趣的悖論與趨勢走向和趨勢的觀察對探索。這種差別可能是由於不同的遊戲類型。冒險遊戲發生在幻想世界,每個國家都有它獨特的一套規則和習慣。也許,當放置在這樣一個新的和開放式的環境女孩寧願獲得的知識,從看別人的成功與失敗之前參加自己。其他類型的遊戲,但是 - 模擬,教育,和動作遊戲 - 往往更加具體。女孩們在這項研究中傾向於玩模擬,如模擬人生和動物園大亨,以及Webkinz遊戲。世界在發生這些遊戲更接近現實世界,從而提供了一個熟悉感。這項研究表明,在這種情況下,女孩喜歡用創新的戰略,並能夠探索的工具和活動提供在遊戲中。需要進一步研究,看是否能轉化為學習風格在其他情況下,除了視頻遊戲。如果是的話,它會建議,女孩應給予自由探索和嘗試新事物的教育情況是很熟悉他們,他們可能更喜歡看別人之前,參與新的和陌生的學習環境。
In video games children are free to try a number of learning strategies. Knowing the ways children choose to learn when they are engaged in an independent activity such as video games may help guide parents and educators in encouraging different styles of learning in other educational contexts. This study also showed that boys are more likely than girls to use ‘cheats’ to learn game In classroom learning, frequently collaboration and use of outside resources as shortcuts can be considered dishonest, unless the activity is specifically designed with collaboration in mind. It is important to note that such practices are sometimes considered acceptable strategies in the gaming world, and students may not understand the differences between ethics in the gaming world and those of the classroom unless these are directly taught.

在視頻遊戲的孩子們可以自由地嘗試一個數字的學習策略知道了孩子選擇學習方式時,他們正在從事一項獨立的活動,如電子遊戲可能有助於指導家長和教育工作者在鼓勵不同風格的學習其他教育背景。這項研究還表明,男孩比女孩更容易使用'作弊'來學習遊戲課堂學習,經常合作和利用外部資源快捷方式可以被視為不誠實,除非該活動是專門設計的協作精神重要的是要注意,這種做法有時被認為是可以接受的戰略,在遊戲的世界裡,和學生可能不理解之間的差異遊戲世界中的倫理和那些在課堂除非這些都直接授課。

Learning strategies emphasized in the traditional classroom tend to most often include repetition (practice), innovation (thinking of new ways to solve problems), and observation (watching the teacher demonstrate). Role play, or pretending to take on the identity of an expert to learn to think like one, is less often used. This study reveals that boys who play adventure games, one of the more popular game genres, tend to approach learning with this strategy. In addition, girls use this strategy equally as often as boys when learning to play games in general. Besides the seeming preference for this strategy among students, this approach has been lauded among learning theorists, both within and without a technological context, who have advised that taking on a role or identity is one of the most effective ways of learning to think in new ways and learn new subject matter (Gee, 2003; Turkle, 1995; Vygotsky, 1978).Results of this study also reveal that boys and girls both use the repetition strategy to learn games. Educators should note, however, that repetition in game play is a motivating factor because ability and success tend to increase with each attempt. If repetition in classroom learning is not associated with these immediate gains, students may more quickly become frustrated and give up because it is not providing the rewards to which they are accustomed in game play.

學習策略強調在傳統的教室往往通常包括重複(實踐),創新(思維的新方法來解決問題),觀察(老師示範)。角色扮演,或假裝的身份參加專家,學會這樣想的,不經常使用。這項研究表明,男孩誰玩冒險遊戲,其中一個比較流行的遊戲類型,往往這個戰略方針的學習此外,女孩也同樣使用這個戰略和男孩經常玩遊戲學習一般除了這一戰略似乎偏愛學生,這種方法已被稱讚班級學習的理論家,既沒有的技術背景下,誰曾表示接受在角色或身份是一個最有效的途徑學習新的思考學習的方法和新的題材,2003年; Turkle,1995;維果茨基,1978)。這項研究結果也顯示,男孩和女孩都使用了重複學習策略遊戲。教育者應該注意,但是,在遊戲中,重複播放,是一種激勵因素,因為能力和成功往往會增加每一次嘗試如果重複課堂學習不是與這些直接收益,學生可以更迅速地變得沮喪,放棄,因為它不提供獎勵他們所習慣的遊戲。

In exploring children’s motivations for choosing the vide games they play, psychological factors seem to play more of a role than programming factors within the games. Children choose to play games about topics that already interest them and games that are challenging, as well as games that give them freedom to make choices. The ultimate video game experience may also be the ultimate learning experience for children: one that relates to something that interests them, gives them the freedom to make their own choices without too many rules and restrictions, and one that provides a significant challenge. Additionally, the differences between the way girls and boys prefer to approach video games may play a role in other types of learning. While the differences will not hold true for every child, parents and educators may find that they can motivate some boys by allowing them to role play and think like a character to accomplish a goal. They may also find that many girls want the opportunity to explore for themselves in familiar learning environments, and that they may prefer to have some observation time before participating in unfamiliar learning environments. Finally, this study supports the view that children will be attracted to learning environments with content that interests and challenges them. It reveals that fewer children are using video games to avoid thinking but, on the contrary, many are seeking mental challenge and are eager to learn from the games.

在探討兒童的動機選擇他們玩遊戲,心理因素似乎發揮更多的作用遊戲編程因素孩子選擇玩遊戲的話題已經和遊戲,他們感興趣的是挑戰以及遊戲,讓他們自由作出的選擇。最終的視頻遊戲體驗也可能是最終的兒童​​學習經驗:一,涉及到他們感興趣的東西讓他們自由作出自己的選擇沒有太多的規則和限制,並且提供了一個巨大的挑戰此外,不同方式之間的女孩和男孩更喜歡接觸視頻遊戲可能發揮的作用是其他類型的學習。雖然不是真實的差異將每一個兒童,家長和教育工作者可能會發現,他們可以激勵一些男孩,讓他們發揮作用,並認為這樣一個人物來完成一個目標。他們可能還發現,很多女孩希望有機會去探索自己在熟悉的學習環境,他們可能更願意有一些觀察時間才能參與不熟悉的學習環境。最後,本研究支持這一觀點,將吸引孩子們的學習環境內容,他們的利益和挑戰由此可見,兒童較少使用視頻遊戲,以避免思想,但與此相反,許多人尋求心理的挑戰,並渴望學習遊戲。

5.2. Limitations
The most obvious limitation of these analyses is that they are correlational. Cause and effect cannot be determined so we cannot discern, from this research, whether certain types of games are more likely to elicit certain learning strategies in children, or if those children who were already predisposed toward a certain strategy tend to choose particular genres of games. The students who participated in this study were volunteers, so different results may have been obtained if all students participated or if a random sample of students were obtained. Finally, this research included all types of video game play, as defined by the children themselves. It may be beneficial for future research to use a more narrow definition of video game play, as well as more narrow definitions of the types of games played to further analyze habits and strategies used in each genre of game.


5.2。限制
最明顯的限制,這些分析是它們相關性原因及影響數不能確定的,所以我們不能辨別從這項研究中是否某些類型的遊戲,更可能引起一定的學習策略,兒童,或如果這些孩子已經傾向於朝著一定的策略傾向於選擇特定類型的遊戲的學生參與這項研究志願者,不同的結果可能是,如果所有的學生獲得參加隨機抽樣的學生獲得。最後,本研究包括了所有類型的視頻遊戲所界定的兒童本身。也許有利於今後的研究使用較狹窄的定義,視頻遊戲以及更狹義的定義,類型的遊戲的習慣,進一步分析和戰略用於各類型遊戲。