JMIR Medical Informatics

Machine learning models are increasingly used to predict patients at risk of high health care usage for targeted interventions.

Clinical decision support systems (CDSSs) have shown promise in improving diagnosis in primary care, particularly for chronic diseases. The SATURN (Smart Physician Portal for Patients With Unclear Disease) project developed a CDSS prototype for primary care in Germany that uses artificial intelligence to reduce diagnostic uncertainty in unclear and rare diseases. It generates recommendations based on clinical data from university hospitals stored in a standardized common data model. However, integrating primary care data in Germany remains challenging due to the use of country-specific vocabularies and heterogeneous data structures. Therefore, integration of medical concepts into general practitioners’ user interfaces (UIs) and improved workflow design is needed.

Nephrolithiasis affects approximately 15% of the population and often remains undetected in asymptomatic individuals. Current diagnostic approaches rely on imaging tools, such as ultrasound or computed tomography, which are costly, operator dependent, or involve radiation, making them unsuitable for large-scale screening. A standardized, practical, and low-cost screening strategy for early identification of clinically significant kidney stones is still lacking.

Artificial intelligence (AI) is increasingly applied to healthcare, yet concerns about fairness persist, particularly in relation to sociodemographic disparities. Prior studies suggest that socioeconomic status (SES) and sex may influence AI model performance, potentially affecting groups that are historically underserved or understudied.

Coal workers’ pneumoconiosis (CWP) is the most prevalent occupational disease that causes irreversible lung damage. Early prediction of CWP is the key to blocking the irreversible process of pulmonary fibrosis. The prediction of CWP based on imaging data and biomarker detection is constrained due to high cost and poor convenience.

There is increasing research on machine learning in predicting venous thromboembolism after joint arthroplasty, but the quality and clinical applicability of these models remain uncertain.

As health care delivery shifts toward value-based care, proactive strategies to close preventive care gaps are essential. However, patient engagement remains suboptimal due to logistical, behavioral, and socioeconomic barriers. Traditional outreach methods, such as phone calls, emails, and postal mail, have long been used, but emerging digital approaches, such as chatbot-based messaging, offer potential advantages in scalability and personalization. Their comparative effectiveness, however, remains underexplored.

The early detection of diseases is one of the tasks of general practice. AI (artificial intelligence)-based technologies could be useful to identify diseases at an early stage in general practices. As a good 90% of the population regularly consult a GP (general practitioner) during one year, this could increase the percentage of citizens who take part in meaningful screening measures.

Delirium is a frequent postoperative complication among patients who have undergone cardiac surgery and is associated with prolonged hospitalization, cognitive decline, and increased mortality. Early prediction of delirium is therefore critical for initiating timely interventions.

Exploring user satisfaction is crucial for enhancing and ensuring the sustainable development of mobile health (mHealth) apps, particularly in the fitness and weight management sectors. Analyzing user types and developing user profiles are valuable for understanding differences in satisfaction. However, prior research lacks a classification of user types based on self-management characteristics and an analysis of satisfaction disparities among these types.

General anesthesia comprises three essential components—hypnosis, analgesia, and immobility. Among these, maintaining an appropriate hypnotic state, or anesthetic depth, is crucial for patient safety. Excessively deep anesthesia may lead to hemodynamic instability and postoperative cognitive dysfunction, whereas inadequate anesthesia increases the risk of intraoperative awareness. Electroencephalography (EEG)–based monitoring has therefore become a cornerstone for evaluating anesthetic depth. However, processed EEG (pEEG) indices remain vulnerable to various sources of interference, including electromyographic activity, interindividual variability, and anesthetic drug effects, which can yield inaccurate numerical outputs.

AI scribes, software that can convert speech into concise clinical documents, have achieved remarkable clinical adoption at a pace rarely seen for digital technologies in healthcare. The reasons for this are understandable: the technology works well enough, it addresses a genuine pain point for clinicians, and it has largely sidestepped regulatory requirements. In many ways, clinical adoption of AI scribes has also occurred well ahead of robust evidence of their safety and efficacy. The papers in this theme issue demonstrate real progress in the technology and evidence of its benefit: documentation times are reported to decrease when using scribes, clinicians report feeling less burdened, and the notes produced are often of reasonable quality. Yet as we survey the emerging evidence base, there remains one outstanding and urgent unanswered question: Are AI scribes safe? We need to know the clinical outcomes achievable when scribes are used compared to other forms of note taking.