Prospective application of an expert system for the medical history of joint pain

Summary An expert system with 60 questions about medical history was developed for 32 rheumatologic diseases: 358 outpatients with joint complaints have been examined. The final diagnosis (result of symptoms, signs, and findings) was compared with the computer diagnoses and with the independently assumed diagnoses of the physician. The only source of information available to the physician was the medical history. Misinterpretation of the computer diagnoses occurred in 25.6% of cases compared with 21.5% of the physician. The final clinical diagnosis remained uncertain in 32.6% of cases. The error frequency of the expert system was influenced by the underlying disease, the certainty of the assumed diagnosis by the physician, the user experience in rheumatology, the number of questions asked, and the time of application before or after the doctor-patient contact. Of the errors 44% were produced because of information deficits of the computer using standardized questions. The information of the physician in the diagnostic process is quite different to that of the computer.Abbreviations XPS expert system - DIP distal interphalangeal joints - ARA American Rheumatology Association - OA osteoarthritis - Osteoarthritis g.j. osteoarthritis of greater joints     

The role of basic science knowledge and clinical knowledge in diagnostic reasoning: a structural equation modeling approach.

PURPOSE: To examine four theories on the role of basic science knowledge and clinical knowledge in diagnostic reasoning. METHOD: In 2000-01, the authors tested the basic science and clinical knowledge and diagnostic performances of 59 family physicians and 184 second- to sixth-year medical students at Maastricht University, The Netherlands. Structural equation modeling was used to analyze the data. Four theoretical models were tested. In the first model only basic science knowledge is involved in diagnostic reasoning; in the second model only clinical knowledge is related to diagnostic reasoning; in the third model, clinical knowledge is related to diagnostic reasoning, but basic science knowledge is integrated in clinical knowledge; and in the fourth model, both basic science knowledge and clinical knowledge independently influence diagnostic reasoning. RESULTS: Forty-four (75%) of the family physicians and 184 (100%) of the students responded. The results indicated that the third model, which is based on the knowledge encapsulation theory, provided the best fit to the data, whereas the models that had directly related basic science knowledge with diagnostic performance did not fit the data adequately. CONCLUSION: The results generally supported the third model by Schmidt and Boshuizen of knowledge encapsulation theory suggesting that basic science knowledge is activated in expert diagnostic reasoning through its relation with clinical knowledge.     

Desiderata for product labeling of medical expert systems

The proliferation and increasing complexity of medical expert systems raise ethical and legal concerns about the ability of practitioners to protect their patients from defective or misused software. Appropriate product labeling of expert systems can help clinical users to understand software indications and limitations. Mechanisms of action and knowledge representation schema should be explained in layperson's terminology. User qualifications and resources available for acquiring the skills necessary to understand and critique the system output should be listed. The processes used for building and maintaining the system's knowledge base are key determinants of the product's quality, and should be carefully documented. To meet these desiderata, a printed label is insufficient. The authors suggest a new, more active, model of product labeling for medical expert systems that involves embedding `knowledge of the knowledge base', creating user-specific data, and sharing global information using the Internet.     

Does a decision aid help physicians to detect chronic obstructive pulmonary disease?

Background

Numerous decision aids have been developed recently, but the value they add above that of the initial clinical assessment is not well known.

Aim

To quantify whethera formal decision aid for chronic obstructive pulmonary disease (COPD) adds diagnostic information, above the physician''s clinical assessment.

Design and setting

Subanalysis of a diagnostic study in Dutch primary care.

Method

Sixty-five primary care physicians included 357 patients who attended for persistent cough and were not known to have COPD. The physicians estimated the probability of COPD after short history taking and physical examination. After this, the presence or absence of COPD was determined using results of extensive diagnostic work-up. The extent to which an 8-item decision aid for COPD, which included only symptoms and signs, added diagnostic value above the physician''s estimation was quantified by the increase of the area under the receiver operating characteristic curve (ROC area), and the improvement in diagnostic risk classification across two classes: ‘low probability of COPD’ (<20%) and ‘possible COPD’ (≥20%).

Results

One hundred and four patients (29%) had COPD. Adding the decision aid to the clinical assessment increased the ROC area from 0.75 (95% confidence interval [CI] = 0.70 to 0.81) to 0.84 (95% CI = 0.80 to 0.89) (P<0.005), and improved the diagnostic risk classification of the patients, such that 35 fewer patients needed spirometry testing and eight fewer COPD cases were missed.

Conclusion

A short decision aid for COPD added diagnostic value to the physician''s clinical assessment.     

Clinical laboratory and expert system]

Computer-based expert systems are designed to incorporate the knowledge of a human expert such that the computer program will solve problems in a manner similar to the human expert. The systems can be applied fruitfully to many phases of the laboratory testing, including order entry, specimen collection, analysis, result verification, and reporting. Interpretive reporting by means of expert systems is useful for influencing physician's use of laboratory and they offer potential help for clinical decision making. Although much of the early work in the clinical laboratory involved stand-alone expert systems, approaches that integrate more closely with laboratory information system or hospital information system are being used. A short review on the technology of expert system with an emphasis on the roles played by clinical laboratory is made. A trial system dealing with thyroid diseases, based on interpretation of hormonal levels (TSH, Total and Free T3, T4), is described.     

The role of biomedical knowledge in clinical reasoning: a lexical decision study.

PURPOSE: To investigate the role of biomedical and diagnostic inferences in clinical reasoning of advanced medical students and experienced family physicians using a lexical decision task. METHOD: In 2002, 15 family physicians and 20 fourth-year medical students at Maastricht University medical school in The Netherlands were instructed to carefully study 60 short clinical texts consisting of signs and symptoms associated with a particular disease. Participants read the texts on a computer screen and responded using a computer keyboard. Each text was followed by a target item (i.e., biomedical item, diagnostic item, or a nonword). Participants had to decide as quickly and accurately as possible whether the presented target item was a word or a nonword. For both groups, mean response time and mean error rate for all levels of item type were analyzed. RESULTS: Findings indicate that both physicians and medical students judged diagnostic target items faster and more accurately than biomedical target items. However, physicians were considerably faster than were students on judging biomedical and diagnostic target items. CONCLUSIONS: These findings are largely in line with knowledge encapsulation in that biomedical knowledge still plays a prominent role in the physician's clinical reasoning.     

MED1: An intelligent computer program for thoracic pain diagnosis

Summary MED1 is a fully implemented, medical expert system providing assistance in the diagnosis of patients complaining of chest pain. Its reasoning strategy combines efficient mechanisms for hypothesis generation and hypothesis evaluation in a model simulalting the basic features of the hypothesize-and-test approach found to be applied by diagnosing physicians. The knowledge acquisition facility of the program is comfortable enough to allow the expert physician to alter the knowledge base without understanding the basic code (LISP) of the program.Abbreviations AI Artificial intelligence - DH Diagnostic hypothesis - HE Hypothesis evaluation - HG Hypothesis generation - MED1 Metaebenen-Diagnosesystem - TI Technical inverstigation - XPS Expert system     

Computer knowledge amongst clinical year medical students in a resource poor setting

Objective

To study the computer knowledge and desires of clinical year medical students at one of the oldest and largest medical schools in Nigeria.

Design

A survey using validated structured questionnaires.

Setting

Medical school of Ahmadu Bello University, Zaria, Nigeria.

Subjects

Two hundred and thirty seven clinical year (4^th, 5^th and 6^th years) medical students.

Outcome measures

Computer knowledge, mode of acquiring computer knowledge, regular access to computer, desire for inclusion of computer training in curriculum.

Results

One hundred twenty (50.6%) students had knowledge of computer technology and it use. Of these, 108 (90%) had no regular access to a computer and none owned a computer; only 32 (26.7%) were sufficiently familiar with computer tools to perform advanced tasks, but 72 (60%) were comfortable with word processing. Seventy two of the 120 students acquired their computer knowledge through self-learning efforts while 45 (37.5%) attended short periods of formal training. Overall, 45.7% of males and 64.5% of females had computer knowledge. The main reason for lack of computer knowledge was lack of time and lack of access to a computer. Eighty percent of all students would like computer education to be included in medical school curriculum.

Conclusion

Knowledge and use of computers amongst clinical year medical students in this setting is low. It is important that computer education be taught to the students to enhance their ability to use electronic information and communicate more effectively using computer resources.     

An examination of the usefulness of repeat testing practices in a large hospital clinical chemistry laboratory

A long-standing practice in clinical laboratories has been to automatically repeat laboratory tests when values trigger automated "repeat rules" in the laboratory information system such as a critical test result. We examined 25,553 repeated laboratory values for 30 common chemistry tests from December 1, 2010, to February 28, 2011, to determine whether this practice is necessary and whether it may be possible to reduce repeat testing to improve efficiency and turnaround time for reporting critical values. An "error" was defined to occur when the difference between the initial and verified values exceeded the College of American Pathologists/Clinical Laboratory Improvement Amendments allowable error limit. The initial values from 2.6% of all repeated tests (668) were errors. Of these 668 errors, only 102 occurred for values within the analytic measurement range. Median delays in reporting critical values owing to repeated testing ranged from 5 (blood gases) to 17 (glucose) minutes.     

Physicians' preferences for asthma guidelines implementation

Purpose

Patient care based on asthma guidelines is cost-effective and leads to improved treatment outcomes. However, ineffective implementation strategies interfere with the use of these recommendations in clinical practice. This study investigated physicians'' preferences for asthma guidelines, including content, supporting evidence, learning strategies, format, and placement in the clinical workplace.

Methods

We obtained information through a questionnaire survey. The questionnaire was distributed to physicians attending continuing medical education courses and sent to other physicians by airmail, e-mail, and facsimile.

Results

A total of 183 physicians responded (male to female ratio, 2.3:1; mean age, 40.4±9.9 years); 89.9% of respondents were internists or pediatricians, and 51.7% were primary care physicians. Physicians preferred information that described asthma medications, classified the disease according to severity and level of control, and provided methods of evaluation/treatment/monitoring and management of acute exacerbation. The most effective strategies for encouraging the use of the guidelines were through continuing medical education and discussions with colleagues. Physicians required supporting evidence in the form of randomized controlled trials and expert consensus. They preferred that the guidelines be presented as algorithms or flow charts/flow diagrams on plastic sheets, pocket cards, or in electronic medical records.

Conclusions

This study identified the items of the asthma guidelines preferred by physicians in Korea. Asthma guidelines with physicians'' preferences would encourage their implementation in clinical practice.     

Development of retrieval system about clinical laboratory handbook "Kensa Koujien"]

Medical knowledge has been increasing and diversifying on a worldwide scale, while specialization of physicians has been extended vigorously. The knowledge has extended beyond the memory of human beings, there by causing the deterioration of service, called "Knowledge crisis". To tackle this problem, the electronic medical textbook(EMT) has been conceived and set up as a medical knowledge base for physician to optimize their specialties and activities in clinical practice. The doctors' diagnostic process is to be mentioned as the solution of backward problem, to speculate problem such as disease by the information observed from symptoms and findings. The EMT is more powerful tool for diagnosis than experiences or textbook that will aid for specifying the name of disease by arranging and combining information. Meanwhile, laboratory information systems are widely introduced. However, there are few systems which allow interpretation of the findings obtained. With this in mind, we have improved the utility of the EMT by enhancing its function with laboratory information follow-up, thesaurus back-up, Japanese language support, and on-line access. It made use of these experiences, we compiled an clinical laboratory handbook "Kensa Koujien", and developed retrieval system.     

Parent satisfaction with the electronic medical record in an academic pediatric rheumatology practice

Background

Patient satisfaction has not been widely studied with respect to implementation of the electronic medical record (EMR). There are few reports of the impact of the EMR in pediatrics.

Objective

The objective of this study was to assess the impact of implementation of an electronic medical record system on families in an academic pediatric rheumatology practice.

Methods

Families were surveyed 1 month pre-EMR implementation and 3 months post-EMR implementation.

Results

Overall, EMR was well received by families. Compared with the paper chart, parents agreed the EMR improved the quality of doctor care (55% or 59/107 vs 26% or 26/99, P < .001). More parents indicated they would prefer their pediatric physicians to use an EMR (68% or 73/107 vs 51% or 50/99, P = .01).

Conclusions

Transitioning an academic pediatric rheumatology practice to an EMR can increase family satisfaction with the office visit.     

Postgraduate training of pathologists]

Specialization of institutions engaged in training of pathologists is a key condition of skilled specialists turn out. Medical colleges should be responsible for training hospital and junior physicians. Institutes for postgraduate medical education must ensure updating of the practicing pathologists knowledge and prepare them for getting special degrees and diplomas including "European Pathologist". The system of continuous training of pathologists should rest on fundamental legal base which should be warranted by the Russian Federation Ministry of Public Health.     

Prevalence and correlates of patient-centred preparatory information provision to computed tomography and magnetic resonance imaging outpatients: A cross-sectional study

Objective

Responsiveness to information preferences is key to high-quality, patient-centred care. This study examined the top ten preparatory information items not delivered in accordance with medical imaging outpatients’ preferences, and patient characteristics associated with reporting a greater number of unmet information preferences.

Improving perceptions of empathy in patients undergoing low-yield computerized tomographic imaging in the emergency department

Objective

We assessed emergency department (ED) patient perceptions of how physicians can improve their language to determine patient preferences for 11 phrases to enhance physician empathy toward the goal of reducing low-value advanced imaging.

AFP RIA结果分析计算机专家系统（ARA）的开发

为了探索计算机技术在放免结果分析中的应用。用ＶＰ－ＥＸＰＥＲＴ专家系统开发软件开发了ＡＦＰ结果分析专家系统（ＡＲＡ），经临床初步试用，诊断符合率为８２．３％。     

Critical appraisal skills of family physicians in Ontario,Canada

Background

Our primary objective in this study was to measure family physicians' knowledge of the key elements that go into assessing the validity and interpreting the results in three different types of studies: i) a randomized controlled trial (RCT); ii) a study evaluating a diagnostic test; and iii) a systematic review (SR). Our secondary objectives were to determine the relationship between the above skills and age, gender, and type of practice.

Methods

We obtained a random sample of 1000 family physicians in Ontario from the College of Family Physicians of Canada database. These physicians were sent a questionnaire in the mail with follow-up mailings to non-responders at 3 and 8 weeks. The questionnaire was designed to measure knowledge and understanding of the basic concepts of critical appraisal skills. Based on the responses to the questions an Evidence Based Medicine (EBM) Knowledge Score was determined for each physician.

Results

A response rate of 30.2% was achieved. The respondents were younger and more likely to be recent graduates than the population of Ontario Family Physicians as a whole. This was an expected outcome. Just over 50% of respondents were able to answer questions concerning the critical appraisal of methods and the interpretation of results of research articles satisfactorily. The average score on the 12-point EBM Knowledge Scale was 6.4. The younger physicians scored higher than the older physicians, and academic physicians scored higher than community-based physicians. Scores of male and female physicians did not differ.

Conclusions

We have shown that in a population of physicians which is younger than the general population of physicians, about 50% have reasonable knowledge regarding the critical appraisal of the methods and the interpretation of results of a research article. In general, younger physicians were more knowledgeable than were older physicians. EBM principles were felt to be important to the practice of medicine by 95% of respondents.

     

The information needs of people attending for computed tomography (CT): What are they and how can they be met?

Objective

To establish patients’ knowledge of CT, their views of information provided and explore the role of information in imaging.

Methods

A sample of 150 first-time outpatients attending for CT scanning at a Scottish hospital. The study had three phases: a questionnaire survey; structured interviews pre-scan and face-to-face interviews post-scan.

Results

One hundred and twelve questionnaires were returned with 82 deemed usable. Sixty and 53 respondents participated in the pre-scan and post-scan interviews, respectively. Thirty percent of questionnaire respondents and 57.4% of pre-scan interviewees identified accurately the type of scan to be received. Scores on the knowledge test improved by the time of the pre-scan interview. During all stages of the study family members were described as a source of information. Patients reported clinicians as providing few details about the scan, and there was confusion about how results were communicated. Most interviewees thought the leaflet had prepared them for the procedure.

Conclusion

The study revealed a lack of familiarity with CT scanning, diverse informational needs, and the importance of personal contact in information giving.

Practice implications

The study raised wide-ranging issues and highlights the key role of information in the provision of diagnostic health services.     

Prodromal schizophrenia in primary care: a randomised sensitisation study

Background

GPs are often the first point of contact for patients with prodromal schizophrenia. Early intervention, and therefore early detection, of schizophrenia is pivotal for the further disease course. However, recent studies have revealed that, due to its low prevalence in general practice and its insidious features, prodromal schizophrenia often remains unnoticed.

Aim

To test whether a repeated sensitisation method using clinical vignettes can improve diagnostic knowledge of GPs.

Design of study

Postal survey using anonymous questionnaires.Repeated sensitisation model using clinical vignettes.

Setting

GPs in three distinct regions in Switzerland covering a general population of 1.43 million.

Method

The study was conducted between September 2008 and October 2009. Questionnaires were sent to 1138 GPs at baseline, and at 6 and 12?months. After randomisation, 591 GPs were sensitised at 1, 3, and 5?months, while no sensitisation was carried out in the remaining 547 GPs.

Results

The overall response rate was 66% (750 GPs).Sensitised GPs demonstrated a highly significant increase in diagnostic knowledge at 6 and at 12?months when compared to their own baseline knowledge scores and also to non-sensitised GPs (P<0.001). In particular, awareness of insidious features, such as functional decline and social withdrawal as signs of prodromal schizophrenia, accounted for this effect.

Conclusion

Theoretical knowledge of prodromal schizophrenia among GPs can successfully be increased by repeated sensitisation models using clinical vignettes.