Limits and Variability in Drug Databases: Lessons Learnt from Drug Comparisons.

Several drug databases exist, but sometimes differ in their content. Here, we propose a taxonomy of the variability we observed, and we present a tool for investigating the variability through the visual comparison of the properties of a given drug as represented in several sources or databases.

Modular Knowledge-Based Decision Support System Dedicated to a Cooperative Decision to Prevent Cardiovascular Diseases.

Despite the success of artificial intelligence solutions in the recent years, physicians are still reticent to use integrated functionalities to support their decision. Methods used to create these functionalities can be divided into two groups, each being associated to different questions. Data-based methods are seen as black boxes for which it is impossible to understand how the decision is taken; knowledge-based methods need to rely on formalized knowledge sources on the basis of evidence, which can be discussed and criticized by physicians for their use in real life. This paper presents a new modular decision support system for the prevention of cardiovascular diseases, based on knowledge and on cooperative decision between the patient and the physician. The decision support system is based on two layers: (i) the first layer is a knowledge-based module which generates automatically patient profile, and prevention strategies associated to the profile; (ii) the second layer is a dynamic collaborative graphic user interface which displayed information about the risks of treatment adherence failure, personalized motivation and follow-up strategies. In the future, we aim at assessing the platform in real life.

Building a Knowledge-Based Tool for Auto-Assessing the Cardiovascular Risk.

The prevention of cardiovascular diseases needs first to quantify the cardiovascular risk. To estimate this risk, French national health authorities provided clinical practice guidelines extending the existing European SCORE, which doesn't include all the cardiovascular risk factors (e.g. diabetes). Hence, French national clinical practice guidelines to quantify the cardiovascular risk is able to deal with more clinical situations than the SCORE. The goal of this paper is to formalize knowledge extracted from these guidelines and implement the rules so that they can be used into an auto-assessing tool of cardiovascular risk. Formalization followed five steps and was conducted under the guidance of medical experts. It resulted into a decision tree fed by eight decision variables. Evaluation of the accuracy of the decision tree showed 80% of agreement with an expert in medical informatics in predicting the cardiovascular risk level for 15 different clinical situations. Discrepancies correspond to the knowledge gaps within Clinical Practice Guidelines. We intend to extend the implementation of the decision tree to a complete tool, for allowing patient to auto-assess their cardiovascular risk. This tool will be integrated into a platform providing recommendations adapted to the calculated level of cardiovascular risk.

Using visual analytics for presenting comparative information on new drugs.

OBJECTIVE: When a new drug is marketed, physicians must decide whether they will consider it for their future practice. However, information about new drugs can be biased or hard to find. In this work, our objective was to study whether visual analytics could be used for comparing drug properties such as contraindications and adverse effects, and whether this visual comparison can help physicians to forge their own well-founded opinions about a new drug. MATERIALS AND METHODS: First, an ontology for comparative drug information was designed, based on the expectations expressed during focus groups comprised of physicians. Second, a prototype of a visual drug comparator website was developed. It implements several visualization methods: rainbow boxes (a new technique for overlapping set visualization), dynamic tables, bar charts and icons. Third, the website was evaluated by 22 GPs for four new drugs. We recorded the general satisfaction, the physician's decision whether to consider the new drug for future prescription, both before and after consulting the website, and their arguments to justify their choice. RESULTS: The prototype website permits the visual comparison of up to 10 drugs, including efficacy, contraindications, interactions, adverse effects, prices, dosage regimens,…All physicians found that the website allowed them to forge a well-founded opinion on the four new drugs. The physicians changed their decision about using a new drug in their future practice in 29 cases (out of 88) after consulting the website. DISCUSSION AND CONCLUSION: Visual analytics is a promising approach for presenting drug information and for comparing drugs. The visual comparison of drug properties allows physicians to forge their opinions on drugs. Since drug properties are available in reference texts, reviewed by public health agencies, it could contribute to the independent of drug information.

Abstractive Summarization of Drug Dosage Regimens for Supporting Drug Comparison.

Complicated dosage regimens often reduce adherence to drug treatments. The ease-of-administration must thus be taken into account when prescribing. Given one drug, there exists often several dosage regimens. Hence, comparison to similar drugs is difficult. Simplifying and summarizing them appears to be a required task for supporting General Practitioners to find the drug with the simplest regimen for the patient. We propose a summarization in two steps: first prunes out all low-importance information, and second proceed to fusion of remaining information. Rules for pruning and fusion strategies were designed by an expert in drug models. Evaluation was conducted on a dataset of 169 drugs. The agreement rate was 27.2%. We demonstrate that applying rules leads to a result that is correct by a computational point of view, but the result is often meaningless for the GP. We conclude with recommendations for further work.

Patient-physician agreement on tobacco and alcohol consumption: a multilevel analysis of GPs' characteristics.

BACKGROUND: Data about tobacco and alcohol consumption are essential in many types of studies. These data can be obtained by directly questioning patients or by using the information collected from physicians. Agreement between these two sources varies according to the characteristics of patients but probably also those of physicians. The purpose of this study was to analyze the characteristics of general practitioners (GPs) associated with agreement between them and their patients about the patients' consumption of alcohol and tobacco. METHODS: Data came from an observational survey among GPs who were internship supervisors in the Paris metropolitan area. Fifty-two volunteer GPs completed a self-administered questionnaire about the organization of their practice and their training. For each GP, a random sample of 70 patients, aged 40 to 74 years, answered questions about their personal tobacco and alcohol consumption. GPs simultaneously answered similar questions about each patient. We used a mixed logistic model to assess the association between physicians' characteristics and agreement for patients' smoking status and alcohol consumption. RESULTS: Data were collected from both patient and physician for 2599 patients. The agreement between patients and their physicians was 60.4% for smoking status and 48.7% for alcohol consumption. Physicians with continuing medical education in management of smokers and those reporting specific skill in managing hypertension had the best agreement for smoking. Physicians who taught courses at the university medical school and those reporting specific skill in managing alcoholism had the best agreement for alcohol consumption. CONCLUSIONS: Agreement increases with physicians' training and skills in management of patients with tobacco and alcohol problems. It supports the importance of professional training for improving the quality of epidemiologic data in general practice. Researchers who use GPs as a source of information about patients' tobacco and alcohol consumption must assess the physicians' characteristics.

Improving access to clinical practice guidelines with an interactive graphical interface using an iconic language.

BACKGROUND: Clinical practice guidelines are useful for physicians, and guidelines are available on the Internet from various websites such as Vidal Recos. However, these guidelines are long and difficult to read, especially during consultation. Similar difficulties have been encountered with drug summaries of product characteristics. In a previous work, we have proposed an iconic language (called VCM, for Visualization of Concepts in Medicine) for representing patient conditions, treatments and laboratory tests, and we have used these icons to design a user interface that graphically indexes summaries of product characteristics. In the current study, our objective was to design and evaluate an iconic user interface for the consultation of clinical practice guidelines by physicians. METHODS: Focus groups of physicians were set up to identify the difficulties encountered when reading guidelines. Icons were integrated into Vidal Recos, taking human factors into account. The resulting interface includes a graphical summary and an iconic indexation of the guideline. The new interface was evaluated. We compared the response times and the number of errors recorded when physicians answered questions about two clinical scenarios using the interactive iconic interface or a textual interface. Users' perceived usability was evaluated with the System Usability Scale. RESULTS: The main difficulties encountered by physicians when reading guidelines were obtaining an overview and finding recommendations for patients corresponding to "particular cases". We designed a graphical interface for guideline consultation, using icons to identify particular cases and providing a graphical summary of the icons organized by anatomy and etiology. The evaluation showed that physicians gave clinical responses more rapidly with the iconic interface than the textual interface (25.2 seconds versus 45.6, p < 0.05). The physicians appreciated the new interface, and the System Usability Scale score value was 75 (between good and excellent). CONCLUSION: An interactive iconic interface can provide physicians with an overview of clinical practice guidelines, and can decrease the time required to access the content of such guidelines.

Using an iconic language to improve access to electronic medical records in general medicine.

Physicians have difficulties to access and analyse information in a medical record. In a previous work on drug databanks, we have shown that with an iconic language as VCM, an icon-based presentation can help physicians to access medical information. Our objective, herein, is to study whether VCM can be used in an electronic medical record for facilitating physician access in general practice. We identify the data and the functionalities of an electronic medical record that could benefit from VCM icons representing clinical findings, patient history, etc. We also present a preliminary evaluation of this new icon-focused interface. We conclude by discussing the results like the assessment of the user's satisfaction and pointing out the importance of coding data.

A generic system for critiquing physicians' prescriptions: usability, satisfaction and lessons learnt.

Clinical decision support systems have been developed to help physicians to take clinical guidelines into account during consultations. The ASTI critiquing module is one such systems; it provides the physician with automatic criticisms when a drug prescription does not follow the guidelines. It was initially developed for hypertension and type 2 diabetes, but is designed to be generic enough for application to all chronic diseases. We present here the results of usability and satisfaction evaluations for the ASTI critiquing module, obtained with GPs for a newly implemented guideline concerning dyslipaemia, and we discuss the lessons learnt and the difficulties encountered when building a generic DSS for critiquing physicians' prescriptions.

Towards iconic language for patient records, drug monographs, guidelines and medical search engines.

Practicing physicians have limited time for consulting medical knowledge and records. We have previously shown that using icons instead of text to present drug monographs may allow contraindications and adverse effects to be identified more rapidly and more accurately. These findings were based on the use of an iconic language designed for drug knowledge, providing icons for many medical concepts, including diseases, antecedents, drug classes and tests. In this paper, we describe a new project aimed at extending this iconic language, and exploring the possible applications of these icons in medicine. Based on evaluators' comments, focus groups of physicians and opinions of academic, industrial and associative partners, we propose iconic applications related to patient records, for example summarizing patient conditions, searching for specific clinical documents and helping to code structured data. Other applications involve the presentation of clinical practice guidelines and improving the interface of medical search engines. These new applications could use the same iconic language that was designed for drug knowledge, with a few additional items that respect the logic of the language.

How to translate therapeutic recommendations in clinical practice guidelines into rules for critiquing physician prescriptions? Methods and application to five guidelines.

BACKGROUND: Clinical practice guidelines give recommendations about what to do in various medical situations, including therapeutical recommendations for drug prescription. An effective way to computerize these recommendations is to design critiquing decision support systems, i.e. systems that criticize the physician's prescription when it does not conform to the guidelines. These systems are commonly based on a list of "if conditions then criticism" rules. However, writing these rules from the guidelines is not a trivial task. The objective of this article is to propose methods that (1) simplify the implementation of guidelines' therapeutical recommendations in critiquing systems by automatically translating structured therapeutical recommendations into a list of "if conditions then criticize" rules, and (2) can generate an appropriate textual label to explain to the physician why his/her prescription is not recommended. METHODS: We worked on the therapeutic recommendations in five clinical practice guidelines concerning chronic diseases related to the management of cardiovascular risk. We evaluated the system using a test base of more than 2000 cases. RESULTS: Algorithms for automatically translating therapeutical recommendations into "if conditions then criticize" rules are presented. Eight generic recommendations are also proposed; they are guideline-independent, and can be used as default behaviour for handling various situations that are usually implicit in the guidelines, such as decreasing the dose of a poorly tolerated drug. Finally, we provide models and methods for generating a human-readable textual critique. The system was successfully evaluated on the test base. CONCLUSION: We show that it is possible to criticize physicians' prescriptions starting from a structured clinical guideline, and to provide clear explanations. We are now planning a randomized clinical trial to evaluate the impact of the system on practices.