The interpretation of lung auscultation is highly subjective and relies on non-specific nomenclature. Computer-aided analysis has the potential to better standardize and automate evaluation. We used 35.9 hours of auscultation audio from 572 pediatric outpatients to developDeepBreath: a deep learning model identifying the audible signatures of acute respiratory illness in children. It comprises a convolutional neural network followed by a logistic regression classifier, aggregating estimates on recordings from eight thoracic sites into a single prediction at the patient-level. Patients were either healthy controls (29%) or had one of three acute respiratory illnesses (71%) including pneumonia, wheezing disorders (bronchitis/asthma), and bronchiolitis). To ensure objective estimates on model generalisability,DeepBreathis trained on patients from two countries (Switzerland, Brazil), and results are reported on an internal 5-fold cross-validation as well as externally validated (extval) on three other countries (Senegal, Cameroon, Morocco).DeepBreathdifferentiated healthy and pathological breathing with an Area Under the Receiver-Operator Characteristic (AUROC) of 0.93 (standard deviation [SD] ± 0.01 on internal validation). Similarly promising results were obtained for pneumonia (AUROC 0.75 ± 0.10), wheezing disorders (AUROC 0.91 ± 0.03), and bronchiolitis (AUROC 0.94 ± 0.02). Extval AUROCs were 0.89, 0.74, 0.74 and 0.87 respectively. All either matched or were significant improvements on a clinical baseline model using age and respiratory rate. Temporal attention showed clear alignment between model prediction and independently annotated respiratory cycles, providing evidence thatDeepBreathextracts physiologically meaningful representations.DeepBreathprovides a framework for interpretable deep learning to identify the objective audio signatures of respiratory pathology.

Background: Adolescent mental health care is constrained not only by limited treatment capacity but also by the absence of precise and efficient tools to identify and triage those in need. Measurement-based mental health care relies on standardized assessments to guide identification, treatment selection, and ongoing monitoring of mental disorders. However, conventional assessments present a trade-off: diagnostic interviews lack feasibility at scale, while brief screening tools result in misclassification and suboptimal allocation of limited mental health resources. Computerized adaptive testing addresses this trade-off by dynamically tailoring assessments to individuals, maximizing measurement precision while minimizing assessment burden. Despite these advances, no adaptive assessment for adolescent mental health has been developed or calibrated using African data. Objective: The AfriCAT study aims to develop and internally validate a precision computerized adaptive assessment of adolescent depression and anxiety using nationally representative Kenyan data, with the longer-term goal of supporting measurement-based mental health care across diverse African contexts. Methods: AfriCAT is a mixed methods study integrating psychometric modeling, adaptive simulation, modular clinical decision support networks, participatory workshops, discrete choice experiments (DCEs), and stakeholder interviews. Diagnostic Interview Schedule for Children, version 5 ( DISC-5 ) modules assessing major depressive disorder, generalized anxiety disorder, social phobia, and posttraumatic stress disorder among adolescents aged 10 to 17 years from the Kenya National Adolescent Mental Health Survey (N=5155) will form the item bank. Adaptive engines will be developed using a bifactor multidimensional item response theory framework and a modular neural architecture. Simulation-based internal validation will evaluate precision, efficiency, and diagnostic classification relative to DISC-5 diagnoses. Participatory workshops in Kenya and South Africa, DCEs to quantify adolescent preferences, and stakeholder interviews will inform refinement of adolescent- and provider-facing prototypes. Results: Ethical approval has been obtained from the Human Research Ethics Committee (Medical) at the University of the Witwatersrand and the Aga Khan University Institutional Scientific and Ethics Review Committee. Data preparation and model development are underway. Participatory workshops and DCEs are ongoing. Simulation-based validation and prototype refinement will follow. Conclusions: AfriCAT aims to develop the first adaptive mental health assessment calibrated using nationally representative African adolescent data. By integrating precision psychometrics with participatory co-design, the study seeks to enable more accurate triage and support scalable, measurement-based adolescent mental health care in resource-constrained settings.

BACKGROUND Adolescent mental health care is constrained not only by limited treatment capacity, but by the absence of precise and efficient tools to identify and triage those in need. Measurement-based mental healthcare (MBMH) relies on standardized assessments to guide identification, treatment selection, and ongoing monitoring of mental disorders. However, conventional assessments present a trade-off: diagnostic interviews lack feasibility at scale; while brief screening tools result in misclassification and suboptimal allocation of limited mental health resources. Computerized adaptive testing (CAT) addresses this trade-off by dynamically tailoring assessments to individuals, maximizing measurement precision while minimizing assessment burden. Despite these advances, no adaptive assessment for adolescent mental health has been developed or calibrated using African data. OBJECTIVE The AfriCAT study aims to develop and internally validate a precision computerized adaptive assessment of adolescent depression and anxiety to support measurement-based mental healthcare in African contexts. METHODS AfriCAT is a mixed-methods study integrating psychometric modeling, adaptive simulation, modular clinical decision support networks, participatory workshops, discrete choice experiments (DCEs), and stakeholder interviews. Diagnostic Interview Schedule for Children, version 5 (DISC-5) modules assessing major depressive disorder, generalized anxiety disorder, social phobia and post-traumatic stress disorder among adolescents aged 10-17 years from the Kenya-National Adolescent Mental Health Survey (N=5,155) will form the item bank. Adaptive engines will be developed using a bifactor multidimensional item response theory framework and a modular neural architecture. Simulation-based internal validation will evaluate precision, efficiency, and diagnostic classification relative to DISC-5 diagnoses. Participatory workshops in Kenya and South Africa, DCEs to quantify adolescent preferences, and stakeholder interviews will inform refinement of adolescent- and provider-facing prototypes. RESULTS Ethical approval has been obtained from the Human Research Ethics Committee (Medical) at the University of the Witwatersrand and the Aga Khan University Institutional Scientific and Ethics Review Committee (ISERC). Data preparation and model development are underway. Participatory workshops and DCEs are ongoing. Simulation-based validation and prototype refinement will follow. CONCLUSIONS AfriCAT aims to develop the first adaptive mental health assessment calibrated using nationally representative African adolescent data. By integrating precision psychometrics with participatory co-design, the study seeks to enable more accurate triage and support scalable, measurement-based adolescent mental healthcare in resource-constrained settings.

A critical factor contributing to the burden of childhood asthma is the lack of effective self-management in homecare settings. Artificial intelligence (AI) and lung sound monitoring could help address this gap. Yet, existing AI-driven auscultation tools focus on wheeze detection and often rely on subjective human labels. To improve the early detection of asthma worsening in children in homecare setting, we trained and evaluated a Deep Learning model based on spirometry-labelled lung sounds recordings to detect asthma exacerbation. A single-center prospective observational study was conducted between November 2020 and September 2022 at a tertiary pediatric pulmonology department. Electronic stethoscopes were used to record lung sounds before and after bronchodilator administration in outpatients. In the same session, children also underwent spirometry, which served as the reference standard for labelling the lung sound data. Model performance was assessed on an internal validation set using receiver operating characteristic (ROC) curves. A total of 16.8 h of lung sound recordings from 151 asthmatic pediatric outpatients were collected. The model showed promising discrimination performance, achieving an AUROC of 0.763 in the training set, but performance in the validation set was limited (AUROC = 0.398). This negative result demonstrates that acoustic features alone may not provide sufficient diagnostic information for the early detection of asthma attacks, especially in mostly asymptomatic outpatients typical of homecare settings. It also underlines the challenges introduced by differences in how digital stethoscopes process sounds and highlights the need to define the severity threshold at which acoustic monitoring becomes informative, and clinically relevant for home management.