Opening the black box of clinical judgment-an overview. Interview by Abi Berger.
Ontology highlight
ABSTRACT:
SUBMITTER: Weed LL
PROVIDER: S-EPMC1129058 | biostudies-literature | 1999 Nov
REPOSITORIES: biostudies-literature
Publications
Opening the black box of clinical judgment-an overview. Interview by Abi Berger.
BMJ (Clinical research ed.) 19991101 7220
Similar Datasets
Project description:BackgroundThis study reports on the main criteria used by Canadian cardiac surgery residency program committees (RPCs) to select applicants and the perceptions of Canadian medical students interested in cardiac surgery.MethodsA 50-question online survey was sent to all 12 Canadian cardiac surgery RPCs. A similar 52-question online survey targeted at Canadian medical students interested in applying to cardiac surgery residency programs was distributed. Data from both surveys were analyzed using descriptive statistics.ResultsA total of 62% of all cardiac surgery RPC members (66 of 106) participated, including committee members from all 12 programs (range: 1-12 members per program; 9%-100% response rate per program) and 67% of program directors (8 of 12). Forty-one Canadian medical students (22 pre-clerks [54%], 2 MD/PhD students [5%], and 17 clinical clerks [41%]) participated. Committee members considered the following criteria to be most important when selecting candidates: on-service clinical performance, the interview, quality of reference letters from cardiac surgeons, and completing a rotation at the target program's institution. In contrast, the following criteria relating to the candidate were considered to be less important: wanting to practice in the city or province of training, having a connection to the program location, and personally knowing committee members. Medical students' perceptions were concordant regarding what factors are the most important but they overestimated the influence of non-clinical factors and research productivity in increasing their competitiveness.ConclusionCanadian cardiac surgery residency programs seek applicants who demonstrate clinical excellence, as assessed by surgical rotations and reference letters from colleagues, and strong interview performance.
| S-EPMC9700213 | biostudies-literature
Project description:State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features' importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.
| S-EPMC7135268 | biostudies-literature
Project description:Dogs and cats in Brazil serve as primary hosts for a considerable number of parasites, which may affect their health and wellbeing. These may include endoparasites (e.g., protozoa, cestodes, trematodes, and nematodes) and ectoparasites (i.e., fleas, lice, mites, and ticks). While some dog and cat parasites are highly host-specific (e.g., Aelurostrongylus abstrusus and Felicola subrostratus for cats, and Angiostrongylus vasorum and Trichodectes canis for dogs), others may easily switch to other hosts, including humans. In fact, several dog and cat parasites (e.g., Toxoplasma gondii, Dipylidium caninum, Ancylostoma caninum, Strongyloides stercoralis, and Toxocara canis) are important not only from a veterinary perspective but also from a medical standpoint. In addition, some of them (e.g., Lynxacarus radovskyi on cats and Rangelia vitalii in dogs) are little known to most veterinary practitioners working in Brazil. This article is a compendium on dog and cat parasites in Brazil and a call for a One Health approach towards a better management of some of these parasites, which may potentially affect humans. Practical aspects related to the diagnosis, treatment, and control of parasitic diseases of dogs and cats in Brazil are discussed.
| S-EPMC3914713 | biostudies-literature
Project description:In electronic health (eHealth) research, limited insight has been obtained on process outcomes or how the use of technology has contributed to the users' ability to have a healthier life, improved well-being, or activate new attitudes in their daily tasks. As a result, eHealth is often perceived as a black box. To open this black box of eHealth, methodologies must extend beyond the classic effect evaluations. The analyses of log data (anonymous records of real-time actions performed by each user) can provide continuous and objective insights into the actual usage of the technology. However, the possibilities of log data in eHealth research have not been exploited to their fullest extent. The aim of this paper is to describe how log data can be used to improve the evaluation and understand the use of eHealth technology with a broader approach than only descriptive statistics. This paper serves as a starting point for using log data analysis in eHealth research. Here, we describe what log data is and provide an overview of research questions to evaluate the system, the context, the users of a technology, as well as the underpinning theoretical constructs. We also explain the requirements for log data, the starting points for the data preparation, and methods for data collection. Finally, we describe methods for data analysis and draw a conclusion regarding the importance of the results for both scientific and practical applications. The analysis of log data can be of great value for opening the black box of eHealth. A deliberate log data analysis can give new insights into how the usage of the technology contributes to found effects and can thereby help to improve the persuasiveness and effectiveness of eHealth technology and the underpinning behavioral models.
| S-EPMC5565791 | biostudies-literature
Project description:ObjectiveThe internal workings ofmachine learning algorithms are complex and considered as low-interpretation "black box" models, making it difficult for domain experts to understand and trust these complex models. The study uses metabolic syndrome (MetS) as the entry point to analyze and evaluate the application value of model interpretability methods in dealing with difficult interpretation of predictive models.MethodsThe study collects data from a chain of health examination institution in Urumqi from 2017 ~ 2019, and performs 39,134 remaining data after preprocessing such as deletion and filling. RFE is used for feature selection to reduce redundancy; MetS risk prediction models (logistic, random forest, XGBoost) are built based on a feature subset, and accuracy, sensitivity, specificity, Youden index, and AUROC value are used to evaluate the model classification performance; post-hoc model-agnostic interpretation methods (variable importance, LIME) are used to interpret the results of the predictive model.ResultsEighteen physical examination indicators are screened out by RFE, which can effectively solve the problem of physical examination data redundancy. Random forest and XGBoost models have higher accuracy, sensitivity, specificity, Youden index, and AUROC values compared with logistic regression. XGBoost models have higher sensitivity, Youden index, and AUROC values compared with random forest. The study uses variable importance, LIME and PDP for global and local interpretation of the optimal MetS risk prediction model (XGBoost), and different interpretation methods have different insights into the interpretation of model results, which are more flexible in model selection and can visualize the process and reasons for the model to make decisions. The interpretable risk prediction model in this study can help to identify risk factors associated with MetS, and the results showed that in addition to the traditional risk factors such as overweight and obesity, hyperglycemia, hypertension, and dyslipidemia, MetS was also associated with other factors, including age, creatinine, uric acid, and alkaline phosphatase.ConclusionThe model interpretability methods are applied to the black box model, which can not only realize the flexibility of model application, but also make up for the uninterpretable defects of the model. Model interpretability methods can be used as a novel means of identifying variables that are more likely to be good predictors.
| S-EPMC9419421 | biostudies-literature
Project description:A broad research programme in Arabidopsis thaliana has provided estimates of selection on specific alleles in specific contexts, and identified geographic patterns of alleles in genes linked to timing of flowering. A closely related field has successfully captured many key axes of the evolution of timing of flowering in other monocarpic species through statistical and demographic modelling of large empirical databases. There has as yet been no synthesis between these two fields. Here we examine ways in which the two fields inform each other, and how this synergy will shape our knowledge of life-history evolution as a whole.
| S-EPMC2819306 | biostudies-literature
Project description:ObjectivesA Gateway to Medicine programme, developed in partnership between a further and higher education setting and implemented to increase the socioeconomic diversity of medicine, was examined to identify precisely what works within the programme and why.DesignThis study employed realist evaluation principles and was undertaken in three phases: document analysis and qualitative focus groups with widening access (WA) programme architects; focus groups and interviews with staff and students; generation of an idea of what works.SettingParticipants were recruited from a further/higher education setting and were either enrolled or involved in the delivery of a Gateway to Medicine programme.ParticipantsTwelve staff were interviewed either individually (n=3) or in one of three group interviews. Nine focus groups (ranging from 5 to 18 participants in each focus group) were carried out with Gateway students from three consecutive cohorts at 2-3 points in their Gateway programme year.ResultsData were generated to determine what 'works' in the Gateway programme. Turning a realist lens on the data identified six inter-relating mechanisms which helped students see medicine as attainable and achievable and prepared them for the transition to medical school. These were academic confidence (M1); developing professional identity (M2); financial support/security (M3); supportive relationships with staff (M4) and peers (M5); and establishing a sense of belonging as a university student (M6).ConclusionsBy unpacking the 'black box' of a Gateway programme through realist evaluation, we have shown that such programmes are not solely about providing knowledge and skills but are rather much more complex in respect to how they work. Further work is needed to further test the mechanisms identified in our study in other contexts for theory development and to identify predictors of effectiveness in terms of students' preparedness to transition.
| S-EPMC8280889 | biostudies-literature
Project description:PurposeLittle is known about how health-care professionals communicate with patients about consenting to genome sequencing. We therefore examined what topics health-care professionals covered and what questions patients asked during consent conversations.MethodsTwenty-one genome sequencing consent appointments were audio recorded and analyzed. Participants were 35 individuals being invited to participate in the 100,000 Genomes Project (14 participants with rare diseases, 21 relatives), and 10 health-care professionals ("consenters").ResultsTwo-thirds of participants' questions were substantive (e.g., genetics and inheritance); one-third administrative (e.g., filling in the consent form). Consenters usually (19/21) emphasized participant choice about secondary findings, but less often (13/21) emphasized the uncertainty about associated disease risks. Consenters primarily used passive statements and closed-ended, rather than open-ended, questions to invite participants' questions and concerns. In two appointments, one parent expressed negative or uncertain views about secondary findings, but after discussion with the other parent opted to receive them.ConclusionHealth-care professionals need to be prepared to answer patients' questions about genetics to facilitate genome sequencing consent. Health-care professionals' education also needs to address how to effectively listen and elicit each patient's questions and views, and how to discuss uncertainty around the disease risks associated with secondary findings.
| S-EPMC6752270 | biostudies-literature
Project description:Collisions with windows on buildings are a major source of bird mortality. The current understanding of daytime collisions is limited by a lack of empirical data on how collisions occur in the real world because most data are collected by recording evidence of mortality rather than pre-collision behaviour. Based on published literature suggesting a causal relationship between bird collision risk and the appearance of reflections on glass, the fact that reflections vary in appearance depending on viewing angle, and general principles of object collision kinematics, we hypothesized that the risk and lethality of window collisions may be related to the angle and velocity of birds' flight. We deployed a home security camera system to passively record interactions between common North American bird species and residential windows in a backyard setting over spring, summer and fall seasons over 2 years. We captured 38 events including 29 collisions and nine near-misses in which birds approached the glass but avoided impact. Only two of the collisions resulted in immediate fatality, while 23 birds flew away immediately following impact. Birds approached the glass at variable flight speeds and from a wide range of angles, suggesting that the dynamic appearance of reflections on glass at different times of day may play a causal role in collision risk. Birds that approached the window at higher velocity were more likely to be immediately killed or stunned. Most collisions were not detected by the building occupants and, given that most birds flew away immediately, carcass surveys would only document a small fraction of window collisions. We discuss the implications of characterizing pre-collision behaviour for designing effective collision prevention methods.
| S-EPMC9784330 | biostudies-literature
Project description:Phosphorus (P) is an essential macronutrient in agriculture; however, lack of reporting makes its supply chain a black box. By using literature synthesis on the P challenge, we identify four areas where the reporting process is problematic: P reserves and resources; P losses along the supply chain; P externalities; and access to data. We find that in these areas, the reporting system is inconsistent, inaccurate, incomplete, fragmented and non-transparent. We use systems analysis to discuss implications of reporting on the sustainability of the P supply chain. We find that reporting is essential for the achievement of global P governance and the human right to adequate food. It can also inform decision makers and other impacted stakeholders on policies on agriculture, food security, pollution and international conflict. An improved P reporting process also allows a better evaluation of global sustainability commitments such as the United Nations Sustainable Development Goals.
| S-EPMC7028792 | biostudies-literature