Treatment and prevention of cardiovascular diseases often rely on Electrocardiogram (ECG) interpretation. Dependent on the physician's variability, ECG interpretation is subjective and prone to errors. Machine learning models are often developed and used to support doctors; however, their lack of interpretability stands as one of the main drawbacks of their widespread operation. This paper focuses on an Explainable Artificial Intelligence (XAI) solution to make heartbeat classification more explainable using several state-of-the-art model-agnostic methods. We introduce a high-level conceptual framework for explainable time series and propose an original method that adds temporal dependency between time samples using the time series' derivative. The results were validated in the MIT-BIH arrhythmia dataset: we performed a performance's analysis to evaluate whether the explanations fit the model's behaviour; and employed the 1-D Jaccard's index to compare the subsequences extracted from an interpretable model and the XAI methods used. Our results show that the use of the raw signal and its derivative includes temporal dependency between samples to promote classification explanation. A small but informative user study concludes this study to evaluate the potential of the visual explanations produced by our original method for being adopted in real-world clinical settings, either as diagnostic aids or training resource.

BackgroundThere is increasing interest in individualized patient‐reported outcome measures (I‐PROMS), where patients themselves indicate the specific problems they want to address in therapy and these problems are used as items within the outcome measurement tool.ObjectiveThis paper examined the extent to which 279 items reported in an I‐PROM (PSYCHLOPS) added qualitative information which was not captured by two well‐established outcome measures (CORE‐OM and PHQ‐9).DesignComparison of items was only conducted for patients scoring above the “caseness” threshold on the standardized measures.Setting and patients107 patients were participating in therapy within addiction and general psychiatric clinical settings.Main resultsAlmost every patient (95%) reported at least one item whose content was not covered by PHQ‐9, and 71% reported at least one item not covered by CORE‐OM.DiscussionResults demonstrate the relevance of individualized outcome assessment for capturing data describing the issues of greatest concern to patients, as nomothetic measures do not always seem to capture the whole story.

No abstract

No abstract

Background In 2015, Portugal was the OECD country with the highest reported consumption of BZD. Physician’s perceptions and attitudes regarding BZD are main determinants of related prescription habits. This study aimed to characterize beliefs and attitudes of Portuguese physicians regarding the prescription, management challenges, benefits, risks and withdrawal effects of BZD. Methods A cross-sectional, observational study with online data collection through anonymous self-administered questionnaire. Physicians registered with the Portuguese Medical Association were invited to participate through direct e-mail message. Physicians were asked to give their opinion (using a 5-points Likert scale) regarding the prescription of BZD, their benefits and risks in the management of insomnia and anxiety, the possible adverse effects of chronic use and alternative non-pharmacologic approaches. Descriptive statistics were used and groups were compared through logistic regression. Results A total of 329 physicians participated in the study (56% family physicians). Mean age was 44.10 ± 15.2 years, with 19.03 ± 14.9 years of clinical experience. Fifty eight percent of participants were female. Physicians reported BZD’s negative impact on cognitive function (89%), association with road traffic accidents (88%) and falls (79%). Also, 58% shared the belief that chronic use is justified if the patient feels better and without adverse events. Although 68% reported to feel capable of helping patients to reduce or stop BZD, 55% recognized difficulties in motivating them. Compared to other medical specialists (altogether), family physicians were significantly more aware about the adverse effects of BZD and considered that chronic use may not be justified. Conversely, more family physicians expressed concerns about their skills to motivate patients engaging in withdrawal programs and to support them during the process. Conclusion Our results show that physicians’ awareness about risks of BZD chronic use is adequate though their attitudes and self-perceived skills towards promoting BZD withdrawal can be improved. Interventions in primary care are needed to capacitate physicians to better motivate patients for BZD withdrawal.