Background Data modeling for electronic health records (EHRs) is complex, requiring technological and cognitive sophistication. The openEHR approach leverages the tacit knowledge of domain experts made explicit in a model development process aiming at interoperability and data reuse. Objective The purpose of our research was to explore the process that enabled the aggregation of the tacit knowledge of domain experts in an explicit form using the Clinical Knowledge Manager (CKM) platform and associated assets. The Tobacco Smoking Summary archetype is used to illustrate this. Methods Three methods were used to triangulate findings: (1) observation of CKM discussions by crowdsourced domain experts in two reviews, (2) observation of editor discussions and decision-making, and (3) interviews with eight domain experts. CKM discussions were analyzed for content and editor discussions for decision-making, and interviews were thematically analyzed to explore in depth the explication of tacit knowledge. Results The Detailed Clinical Model (DCM) process consists of a set of reviews by domain experts, with each review followed by editorial discussions and decision-making until an agreement is reached among reviewers and editors that the DCM is publishable. Interviews revealed three themes: (1) data interoperability and reusability, (2) accurate capture of patient data, and (3) challenges of sharing tacit knowledge. Discussion The openEHR approach to developing an open standard revealed a complex set of conditions for a successful interoperable archetype, such as leadership, maximal dataset, crowdsourced domain expertise and tacit knowledge made explicit, editorial vision, and model-driven software. Aggregated tacit knowledge that is explicated into a DCM enables the ability to collect accurate data and plan for the future. Conclusion The process based on the CKM platform enables domain experts and stakeholders to be heard and to contribute to mutually designed standards that align local protocols and agendas to international interoperability requirements.

Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide. The information cues of depression can be harvested from diverse heterogeneous resources, e.g., audio, visual, and textual data, raising demand for new effective multi-modal fusion approaches for its automatic estimation. In this work, we tackle the task of automatically identifying depression from multi-modal data and introduce a sub-attention mechanism for linking heterogeneous information while leveraging Convolutional Bidirectional LSTM as our backbone. To validate this idea, we conduct extensive experiments on the public DAIC-WOZ benchmark for depression assessment featuring different evaluation modes and taking gender-specific biases into account. The proposed model yields effective results with 0.89 precision and 0.70 F1-score in detecting major depression and 4.92 MAE in estimating the severity. Our attention-based fusion module consistently outperforms conventional late fusion approaches and achieves a competitive performance compared to the previously published depression estimation frameworks, while learning to diagnose the disorder end-to-end and relying on far less preprocessing steps.