Objective: The interpretation of time series data collected in free-living has gained importance in chronic disease management. Some data are collected objectively from sensors and some are estimated and entered by the individual. In type 1 diabetes (T1D), blood glucose concentration (BGC) data measured by continuous glucose monitoring (CGM) systems and insulin doses administered can be used to detect the occurrences of meals and physical activities and generate the personal daily living patterns for use in automated insulin delivery (AID). Methods: Two challenges in time-series data collected in daily living are addressed: data quality improvement and the detection of unannounced disturbances of BGC. CGM data have missing values for varying periods of time and outliers. People may neglect reporting their meal and physical activity information. In this work, novel methods for preprocessing real-world data collected from people with T1D and the detection of meal and exercise events are presented. Four recurrent neural network (RNN) models are investigated to detect the occurrences of meals and physical activities disjointly or concurrently. Results: RNNs with long short-term memory (LSTM) with 1D convolution layers and bidirectional LSTM with 1D convolution layers have average accuracy scores of 92.32% and 92.29%, and outperform other RNN models. The F1 scores for each individual range from 96.06% to 91.41% for these two RNNs. Conclusions: RNNs with LSTM and 1D convolution layers and bidirectional LSTM with 1D convolution layers provide accurate personalized information about the daily routines of individuals. Significance: Capturing daily behavior patterns enables more accurate future BGC predictions in AID systems and improves BGC regulation.

Acute psychological stress (APS) is a complex and multifactorial phenomenon that affects metabolism, necessitating real-time detection and interventions to mitigate its effects on glycemia in people with type 1 diabetes. This study investigates the detection of APS using physiological variables measured by the Empatica E4 wristband and employs explainable machine learning to evaluate the importance of the physiological signals. The extreme gradient boosting model is developed for classification of APS and non-stress (NS) with weighted training, achieving an overall accuracy of 99.93%. The Shapley additive explanations (SHAP) technique is employed to interpret the global importance of the physiological signals, determining the order of importance for the variables from most to least as galvanic skin response (GSR), heart rate (HR), skin temperature (ST), and motion sensors (accelerometer readings). The increase in GSR and HR are positively correlated with the occurrence of APS as indicated by high positive SHAP values. The SHAP technique is also used to explain the local signal importance for particular instances of misclassified samples. The detection of APS can inform multivariable automated insulin delivery systems to intervene to counteract the APS-induced glycemic excursions in people with type 1 diabetes.

Objectives: Case reports and case series comprise a significant portion of the biomedical literature, yet unlike case reports, the National Library of Medicine does not index case series as a Publication Type. This hurts clinicians’ and researchers’ ability to retrieve, identify and analyze evidence from this type of study. Materials and Methods: PubMed articles mentioning “case series” in title or abstract were characterized to learn what are considered to be case series by the authors themselves. We then set aside articles better indexed as other standard publication types – case reports, cohort studies, reviews and clinical trials -- as well as those that discuss (rather than report the results of) case series studies, to create a corpus of typical case series articles. A random sample of these articles was evaluated by two annotators who confirmed that the great majority satisfy a formal definition of “case series”. Results: The corpus was utilized in an automated transformer-based machine learning indexing model. Case series performance of this model on hold-out data was excellent (precision = 0.887, recall = 0.952, F1 = 0.918, PR-AUC = 0.941) and manual evaluation of 100 articles tagged as “case series” revealed that 88% satisfied a formal definition of case series. Discussion and Conclusion: This study demonstrates the feasibility of automatically indexing case series articles. Indexing should enhance their discoverability, and hence their medical value, for evidence synthesis groups as well as general users of the biomedical literature.

Accurate, consistent indexing of biomedical publications is important for retrieving and evaluating evidence, that in turn can affect clinical decisions, evidence syntheses and research directions. Adaptive trials are arguably among the most complex clinical trial designs, being defined as trials in which the allocation or intervention given to subjects is not fixed in advance, but can vary according to the responses or characteristics of the participants. In the course of preparing to tackle the automated indexing of adaptive clinical trial articles, we manually examined the PubMed articles bearing the Adaptive Clinical Trial publication type to date and identified a surprisingly high proportion of erroneous and questionable indexing decisions. If one agrees that each article should be indexed according to its own study design (rather than the study design of the larger trial that it is linked to), then 46.7% of the articles were mis-assigned. If we consider that articles which presented partial results (e.g., one arm of a multi-arm trial) might be broadly deserving of being indexed as adaptive trials, then the adjusted error rate would still be 24.2%. These errors are worth discussing in detail because they have more general lessons to teach us – not only for biomedical end-users who want to utilize indexing terms for efficient retrieval, but for indexers who need to annotate articles accurately and consistently.