Machine learning for clinical decision support in infectious diseases: a narrative review of current applications.

BACKGROUND: Machine learning (ML) is a growing field in medicine. This narrative review describes the current body of literature on ML for clinical decision support in infectious diseases (ID). OBJECTIVES: We aim to inform clinicians about the use of ML for diagnosis, classification, outcome prediction and antimicrobial management in ID. SOURCES: References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, ACM Digital Library, arXiV and IEEE Xplore Digital Library up to July 2019. CONTENT: We found 60 unique ML-clinical decision support systems (ML-CDSS) aiming to assist ID clinicians. Overall, 37 (62%) focused on bacterial infections, 10 (17%) on viral infections, nine (15%) on tuberculosis and four (7%) on any kind of infection. Among them, 20 (33%) addressed the diagnosis of infection, 18 (30%) the prediction, early detection or stratification of sepsis, 13 (22%) the prediction of treatment response, four (7%) the prediction of antibiotic resistance, three (5%) the choice of antibiotic regimen and two (3%) the choice of a combination antiretroviral therapy. The ML-CDSS were developed for intensive care units (n = 24, 40%), ID consultation (n = 15, 25%), medical or surgical wards (n = 13, 20%), emergency department (n = 4, 7%), primary care (n = 3, 5%) and antimicrobial stewardship (n = 1, 2%). Fifty-three ML-CDSS (88%) were developed using data from high-income countries and seven (12%) with data from low- and middle-income countries (LMIC). The evaluation of ML-CDSS was limited to measures of performance (e.g. sensitivity, specificity) for 57 ML-CDSS (95%) and included data in clinical practice for three (5%). IMPLICATIONS: Considering comprehensive patient data from socioeconomically diverse healthcare settings, including primary care and LMICs, may improve the ability of ML-CDSS to suggest decisions adapted to various clinical contexts. Currents gaps identified in the evaluation of ML-CDSS must also be addressed in order to know the potential impact of such tools for clinicians and patients.

Partnering With Your Health System to Select and Implement Clinical Decision Support for Imaging.

Recent legislation mandates the documentation of appropriateness criteria consultation when ordering advanced imaging for Medicare patients to remain eligible for reimbursement. Implementation of imaging clinical decision support (CDS) is a solution adopted by many systems to automate compliance with the new requirements. This article is intended to help radiologists who are employed by, contracted with, or otherwise affiliated with systems planning to implement CDS in the near future and ensure that they are able to understand and contribute to the process wherever possible. It includes an in-depth discussion of the legislation, evidence for and against the efficacy of imaging CDS, considerations for selecting a CDS vendor, tips for configuring CDS in a fashion consistent with departmental goals, and pointers for implementation and change management.

Quality of drug information for healthcare professionals: the ARCA acronym / Calidad de la información sobre medicamentos para profesionales de la salud: el acrónimo ARCA

No disponible

Clinical Decision Support Systems and Medical Imaging.

Clinical decision support systems (CDSS) can help clinicians make correct and timely decisions about patient care, reduce errors, comply with standard treatment and medication guidelines, reduce costs, and ultimately improve the quality of healthcare. An overview of various models is provided. This tool can apply to six areas of healthcare, all of which have a significant impact on improving care and provider performance: diagnosis, disease progress management, care and treatment, drug prescribing, evaluation, and prevention. Beginning in January 2017, referring physicians must use appropriateness criteria when ordering advanced imaging for Medicare patients. CDSS will be a critical part of this process. In the medical imaging chain, from ordered study to communicating results, such systems can help achieve best practices.

Biomarkers in the ontology for general medical science.

A great deal of recent work has been devoted to the topic of biomarkers as aids to diagnosis, prognosis and treatment evaluation. Basing our work on the Ontology for General Medical Science (OGMS) and on the specifications provided by the Institute of Medicine (IOM), we propose definitions for biomarkers of various types. These definitions provide a formal representation of what biomarkers are in a way that allows us to remove certain ambiguities and inconsistencies in the documentation provided by the IOM.

Decision time for clinical decision support systems.

Clinical decision support systems are interactive software systems designed to help clinicians with decision-making tasks, such as determining a diagnosis or recommending a treatment for a patient. Clinical decision support systems are a widely researched topic in the computer science community, but their inner workings are less well understood by, and known to, clinicians. This article provides a brief explanation of clinical decision support systems and some examples of real-world systems. It also describes some of the challenges to implementing these systems in clinical environments and posits some reasons for the limited adoption of decision-support systems in practice. It aims to engage clinicians in the development of decision support systems that can meaningfully help with their decision-making tasks and to open a discussion about the future of automated clinical decision support as a part of healthcare delivery.

Creating a web-based incident analysis and communication system.

BACKGROUND: Hospitals perform root cause analyses (RCA) and implement action plans for sentinel events (SE) to prevent similar adverse events. Dissemination of RCA action plans between hospitals has been limited by an absence of universal definitions of terms and classification frameworks, which have been recently proposed by the World Health Organization's International Classification for Patient Safety (ICPS). Tools do not exist, however, to assist hospitals in performing SE reviews aligned with the ICPS framework. METHODS: We developed an intranet-based decision support tool that aligns SE reviews with the ICPS framework, and captures SEs and action plans into a searchable database for aggregate reporting. Its structural elements include: 1) encrypted database on a secure server; 2) decision support resources that align SE analyses with the ICPS classification; 3) drop-down lists and help tools to standardize input; 4) standardized individual and aggregate SE reports that vary depending on recipients; 5) real-time access to Web-based RCA resources; 6) fishbone diagramming; and 7) query functions for database searches. RESULTS: Entry of 15 SE reports into the database framework identified gaps in our previous reviews. Safety personnel and health system leadership have expressed positive assessments of the database and approved funding for evaluation of system-wide implementation. DISCUSSION: Expansion of our database to all safety incidents beyond SEs provides a resource for communicating safety opportunities between hospitals. We demonstrate how the ICPS classifications can be migrated into a decision support tool that has potential for standardizing root cause analyses, disseminating action plans, and improving patient safety.

Automatic extraction of relations between medical concepts in clinical texts.

OBJECTIVE: A supervised machine learning approach to discover relations between medical problems, treatments, and tests mentioned in electronic medical records. MATERIALS AND METHODS: A single support vector machine classifier was used to identify relations between concepts and to assign their semantic type. Several resources such as Wikipedia, WordNet, General Inquirer, and a relation similarity metric inform the classifier. RESULTS: The techniques reported in this paper were evaluated in the 2010 i2b2 Challenge and obtained the highest F1 score for the relation extraction task. When gold standard data for concepts and assertions were available, F1 was 73.7, precision was 72.0, and recall was 75.3. F1 is defined as 2*Precision*Recall/(Precision+Recall). Alternatively, when concepts and assertions were discovered automatically, F1 was 48.4, precision was 57.6, and recall was 41.7. DISCUSSION: Although a rich set of features was developed for the classifiers presented in this paper, little knowledge mining was performed from medical ontologies such as those found in UMLS. Future studies should incorporate features extracted from such knowledge sources, which we expect to further improve the results. Moreover, each relation discovery was treated independently. Joint classification of relations may further improve the quality of results. Also, joint learning of the discovery of concepts, assertions, and relations may also improve the results of automatic relation extraction. CONCLUSION: Lexical and contextual features proved to be very important in relation extraction from medical texts. When they are not available to the classifier, the F1 score decreases by 3.7%. In addition, features based on similarity contribute to a decrease of 1.1% when they are not available.

A knowledge discovery and reuse pipeline for information extraction in clinical notes.

OBJECTIVE: Information extraction and classification of clinical data are current challenges in natural language processing. This paper presents a cascaded method to deal with three different extractions and classifications in clinical data: concept annotation, assertion classification and relation classification. MATERIALS AND METHODS: A pipeline system was developed for clinical natural language processing that includes a proofreading process, with gold-standard reflexive validation and correction. The information extraction system is a combination of a machine learning approach and a rule-based approach. The outputs of this system are used for evaluation in all three tiers of the fourth i2b2/VA shared-task and workshop challenge. RESULTS: Overall concept classification attained an F-score of 83.3% against a baseline of 77.0%, the optimal F-score for assertions about the concepts was 92.4% and relation classifier attained 72.6% for relationships between clinical concepts against a baseline of 71.0%. Micro-average results for the challenge test set were 81.79%, 91.90% and 70.18%, respectively. DISCUSSION: The challenge in the multi-task test requires a distribution of time and work load for each individual task so that the overall performance evaluation on all three tasks would be more informative rather than treating each task assessment as independent. The simplicity of the model developed in this work should be contrasted with the very large feature space of other participants in the challenge who only achieved slightly better performance. There is a need to charge a penalty against the complexity of a model as defined in message minimalisation theory when comparing results. CONCLUSION: A complete pipeline system for constructing language processing models that can be used to process multiple practical detection tasks of language structures of clinical records is presented.

A flexible framework for deriving assertions from electronic medical records.

OBJECTIVE: This paper describes natural-language-processing techniques for two tasks: identification of medical concepts in clinical text, and classification of assertions, which indicate the existence, absence, or uncertainty of a medical problem. Because so many resources are available for processing clinical texts, there is interest in developing a framework in which features derived from these resources can be optimally selected for the two tasks of interest. MATERIALS AND METHODS: The authors used two machine-learning (ML) classifiers: support vector machines (SVMs) and conditional random fields (CRFs). Because SVMs and CRFs can operate on a large set of features extracted from both clinical texts and external resources, the authors address the following research question: Which features need to be selected for obtaining optimal results? To this end, the authors devise feature-selection techniques which greatly reduce the amount of manual experimentation and improve performance. RESULTS: The authors evaluated their approaches on the 2010 i2b2/VA challenge data. Concept extraction achieves 79.59 micro F-measure. Assertion classification achieves 93.94 micro F-measure. DISCUSSION: Approaching medical concept extraction and assertion classification through ML-based techniques has the advantage of easily adapting to new data sets and new medical informatics tasks. However, ML-based techniques perform best when optimal features are selected. By devising promising feature-selection techniques, the authors obtain results that outperform the current state of the art. CONCLUSION: This paper presents two ML-based approaches for processing language in the clinical texts evaluated in the 2010 i2b2/VA challenge. By using novel feature-selection methods, the techniques presented in this paper are unique among the i2b2 participants.

Implementation of a taxonomy aiming to support the design of a contextualised clinical decision support system.

Clinical Decision Support Systems (CDSS) are recently implemented in hospital settings to improve the reliability of drug ordering. However, such systems have limited effects due to their tendency to overalert. To healthcare professionals consider alerts, it is necessary to adapt the CDSS to their activity. Thus, it is necessary to consider contextualisation aspects in the system design. In this article, we propose a taxonomy integrating contextualisation elements issued from an activity analysis to guide the design of a contextualised CDSS. This taxonomy has been developed within the framework of the European project PSIP (Patient Safety through Intelligent Procedures in medication) aiming to make easier the identification and the prevention of Adverse Drug Events.

2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text.

The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for Clinical Records presented three tasks: a concept extraction task focused on the extraction of medical concepts from patient reports; an assertion classification task focused on assigning assertion types for medical problem concepts; and a relation classification task focused on assigning relation types that hold between medical problems, tests, and treatments. i2b2 and the VA provided an annotated reference standard corpus for the three tasks. Using this reference standard, 22 systems were developed for concept extraction, 21 for assertion classification, and 16 for relation classification. These systems showed that machine learning approaches could be augmented with rule-based systems to determine concepts, assertions, and relations. Depending on the task, the rule-based systems can either provide input for machine learning or post-process the output of machine learning. Ensembles of classifiers, information from unlabeled data, and external knowledge sources can help when the training data are inadequate.

Automated concept-level information extraction to reduce the need for custom software and rules development.

OBJECTIVE: Despite at least 40 years of promising empirical performance, very few clinical natural language processing (NLP) or information extraction systems currently contribute to medical science or care. The authors address this gap by reducing the need for custom software and rules development with a graphical user interface-driven, highly generalizable approach to concept-level retrieval. MATERIALS AND METHODS: A 'learn by example' approach combines features derived from open-source NLP pipelines with open-source machine learning classifiers to automatically and iteratively evaluate top-performing configurations. The Fourth i2b2/VA Shared Task Challenge's concept extraction task provided the data sets and metrics used to evaluate performance. RESULTS: Top F-measure scores for each of the tasks were medical problems (0.83), treatments (0.82), and tests (0.83). Recall lagged precision in all experiments. Precision was near or above 0.90 in all tasks. Discussion With no customization for the tasks and less than 5 min of end-user time to configure and launch each experiment, the average F-measure was 0.83, one point behind the mean F-measure of the 22 entrants in the competition. Strong precision scores indicate the potential of applying the approach for more specific clinical information extraction tasks. There was not one best configuration, supporting an iterative approach to model creation. CONCLUSION: Acceptable levels of performance can be achieved using fully automated and generalizable approaches to concept-level information extraction. The described implementation and related documentation is available for download.

The Yale cTAKES extensions for document classification: architecture and application.

BACKGROUND: Open-source clinical natural-language-processing (NLP) systems have lowered the barrier to the development of effective clinical document classification systems. Clinical natural-language-processing systems annotate the syntax and semantics of clinical text; however, feature extraction and representation for document classification pose technical challenges. METHODS: The authors developed extensions to the clinical Text Analysis and Knowledge Extraction System (cTAKES) that simplify feature extraction, experimentation with various feature representations, and the development of both rule and machine-learning based document classifiers. The authors describe and evaluate their system, the Yale cTAKES Extensions (YTEX), on the classification of radiology reports that contain findings suggestive of hepatic decompensation. RESULTS AND DISCUSSION: The F(1)-Score of the system for the retrieval of abdominal radiology reports was 96%, and was 79%, 91%, and 95% for the presence of liver masses, ascites, and varices, respectively. The authors released YTEX as open source, available at http://code.google.com/p/ytex.

A study of machine-learning-based approaches to extract clinical entities and their assertions from discharge summaries.

OBJECTIVE: The authors' goal was to develop and evaluate machine-learning-based approaches to extracting clinical entities-including medical problems, tests, and treatments, as well as their asserted status-from hospital discharge summaries written using natural language. This project was part of the 2010 Center of Informatics for Integrating Biology and the Bedside/Veterans Affairs (VA) natural-language-processing challenge. DESIGN: The authors implemented a machine-learning-based named entity recognition system for clinical text and systematically evaluated the contributions of different types of features and ML algorithms, using a training corpus of 349 annotated notes. Based on the results from training data, the authors developed a novel hybrid clinical entity extraction system, which integrated heuristic rule-based modules with the ML-base named entity recognition module. The authors applied the hybrid system to the concept extraction and assertion classification tasks in the challenge and evaluated its performance using a test data set with 477 annotated notes. MEASUREMENTS: Standard measures including precision, recall, and F-measure were calculated using the evaluation script provided by the Center of Informatics for Integrating Biology and the Bedside/VA challenge organizers. The overall performance for all three types of clinical entities and all six types of assertions across 477 annotated notes were considered as the primary metric in the challenge. RESULTS AND DISCUSSION: Systematic evaluation on the training set showed that Conditional Random Fields outperformed Support Vector Machines, and semantic information from existing natural-language-processing systems largely improved performance, although contributions from different types of features varied. The authors' hybrid entity extraction system achieved a maximum overall F-score of 0.8391 for concept extraction (ranked second) and 0.9313 for assertion classification (ranked fourth, but not statistically different than the first three systems) on the test data set in the challenge.

MITRE system for clinical assertion status classification.

OBJECTIVE: To describe a system for determining the assertion status of medical problems mentioned in clinical reports, which was entered in the 2010 i2b2/VA community evaluation 'Challenges in natural language processing for clinical data' for the task of classifying assertions associated with problem concepts extracted from patient records. MATERIALS AND METHODS: A combination of machine learning (conditional random field and maximum entropy) and rule-based (pattern matching) techniques was used to detect negation, speculation, and hypothetical and conditional information, as well as information associated with persons other than the patient. RESULTS: The best submission obtained an overall micro-averaged F-score of 0.9343. CONCLUSIONS: Using semantic attributes of concepts and information about document structure as features for statistical classification of assertions is a good way to leverage rule-based and statistical techniques. In this task, the choice of features may be more important than the choice of classifier algorithm.

Development and evaluation of a comprehensive clinical decision support taxonomy: comparison of front-end tools in commercial and internally developed electronic health record systems.

BACKGROUND: Clinical decision support (CDS) is a valuable tool for improving healthcare quality and lowering costs. However, there is no comprehensive taxonomy of types of CDS and there has been limited research on the availability of various CDS tools across current electronic health record (EHR) systems. OBJECTIVE: To develop and validate a taxonomy of front-end CDS tools and to assess support for these tools in major commercial and internally developed EHRs. STUDY DESIGN AND METHODS: We used a modified Delphi approach with a panel of 11 decision support experts to develop a taxonomy of 53 front-end CDS tools. Based on this taxonomy, a survey on CDS tools was sent to a purposive sample of commercial EHR vendors (n=9) and leading healthcare institutions with internally developed state-of-the-art EHRs (n=4). RESULTS: Responses were received from all healthcare institutions and 7 of 9 EHR vendors (response rate: 85%). All 53 types of CDS tools identified in the taxonomy were found in at least one surveyed EHR system, but only 8 functions were present in all EHRs. Medication dosing support and order facilitators were the most commonly available classes of decision support, while expert systems (eg, diagnostic decision support, ventilator management suggestions) were the least common. CONCLUSION: We developed and validated a comprehensive taxonomy of front-end CDS tools. A subsequent survey of commercial EHR vendors and leading healthcare institutions revealed a small core set of common CDS tools, but identified significant variability in the remainder of clinical decision support content.

Advanced practice nursing in Canada: overview of a decision support synthesis.

The objective of this decision support synthesis was to identify and review published and grey literature and to conduct stakeholder interviews to (1) describe the distinguishing characteristics of clinical nurse specialist (CNS) and nurse practitioner (NP) role definitions and competencies relevant to Canadian contexts, (2) identify the key barriers and facilitators for the effective development and utilization of CNS and NP roles and (3) inform the development of evidence-based recommendations for the individual, organizational and system supports required to better integrate CNS and NP roles into the Canadian healthcare system and advance the delivery of nursing and patient care services in Canada. Four types of advanced practice nurses (APNs) were the focus: CNSs, primary healthcare nurse practitioners (PHCNPs), acute care nurse practitioners (ACNPs) and a blended CNS/NP role. We worked with a multidisciplinary, multijurisdictional advisory board that helped identify documents and key informant interviewees, develop interview questions and formulate implications from our findings. We included 468 published and unpublished English- and French-language papers in a scoping review of the literature. We conducted interviews in English and French with 62 Canadian and international key informants (APNs, healthcare administrators, policy makers, nursing regulators, educators, physicians and other team members). We conducted four focus groups with a total of 19 APNs, educators, administrators and policy makers. A multidisciplinary roundtable convened by the Canadian Health Services Research Foundation formulated evidence-informed policy and practice recommendations based on the synthesis findings. This paper forms the foundation for this special issue, which contains 10 papers summarizing different dimensions of our synthesis. Here, we summarize the synthesis methods and the recommendations formulated at the roundtable.

Automation in surgery: a systematic approach.

This chapter proposes a classification of surgical assistance systems with respect to their type and level of automation. This classification is based on previous work in the field of human factors and takes two aspects into consideration, the type of information-processing function of the surgeon that is supported by the system, as well as the type of function allocation between surgeon and systems. With respect to the former, three basic functions are distinguished, referred to as information acquisition and analysis, decision making and planning, and execution of surgical action. With respect to the type of function allocation, the status of being either "passive" or "active" comes into consideration for both objects of reference (i.e. the surgeon and the machine), depending on whether a given function is mainly performed by the surgeon, by the system, or collaboratively by both. Hence, a classification results for intraoperative assistance systems in six categories, each of these representing a different degree of automation. The classification scheme is explained and illustrated on the basis of examples of surgical assistance systems from various fields.