JMIR Research Protocols

The promise of artificial intelligence (AI) in medicine depends on its ability to learn from data that reflect what matters to patients and clinicians in the care process. Most existing models are trained on electronic health records (EHRs), which primarily capture biological measures but rarely the interactions and relationships between patients and clinicians. These relationships, central to how care is understood, negotiated, and delivered, unfold across multiple modalities, including voice, text, and video, yet remain largely absent from current datasets. As a result, AI systems trained solely on EHRs risk perpetuating a narrow biomedical view of medicine and overlooking the lived exchanges that define clinical encounters.

Effective collaborative practice among health care professionals is crucial for addressing intimate partner violence (IPV) during pregnancy. Therefore, the development and evaluation of an evidence-based intervention for health care professionals is required to work toward meeting the key priorities of the National Plan to End Violence Against Women and Children 2022‐2032. The consistency, modality, and effectiveness of IPV-focused education vary, and some midwives lack the confidence to respond effectively to disclosures, often due to limited knowledge, education, and skills. This issue is further amplified in interdisciplinary settings, where a lack of cohesiveness and collaboration can negatively impact the experience for pregnant women seeking or needing support.

Piriformis syndrome is a neuromuscular condition with hip and buttock pain and other symptoms, including referred pain towards the lower back and leg and radiating towards the foot’s medial aspect. Similarly, low back pain caused by piriformis syndrome is undetected or difficult to diagnose because of similar symptoms of lumbar disc herniation, lumbar stenosis, or radiculopathy, as well as neurogenic pain. A study conducted in 2013 found 2910 patients experienced low back pain with sciatica, which is the most common cause of low back pain, because of piriformis muscle stiffness. The prevalence of low back pain in piriformis syndrome is 5%‐36%. It is more commonly seen in women than men.

Established treatments for granulomatosis with polyangiitis (GPA) or microscopic polyangiitis (MPA) include the use of immunosuppressive agents for remission induction followed by maintenance therapy. However, patients continue to experience disease progression, organ damage, and adverse events related to current therapies. Avacopan, an oral selective C5a receptor antagonist, was approved by the European Commission in January 2022 for the treatment of adult patients with severe, active GPA or MPA in combination with rituximab (RTX) or cyclophosphamide (CYC). In the pivotal phase 3 ADVOCATE (Avacopan Development in Vasculitis to Obtain Corticosteroid Elimination and Therapeutic Efficacy) study, avacopan was noninferior to prednisone taper in achieving remission at week 26 and superior in sustaining remission at week 52; furthermore, a greater improvement in estimated glomerular filtration rate with avacopan was also observed at week 52. The AvacoStar study will generate data on the benefit and risk and safety profile of avacopan in patients in a real-world context, including in those where treatment may potentially continue beyond 1 year.

The early onset of myopia in children has become a critical public health issue that requires urgent attention. Notably, high myopia-related retinal diseases have emerged as the leading cause of irreversible blindness in adults in certain regions of China. Physiological hyperopia, as a protective factor and one of the strongest predictors of myopia development, plays a key role in delaying the progression of early-onset myopia and reducing the risk of high myopia in adulthood. However, the dynamic changes, critical turning points, and factors contributing to the rapid regression of physiological hyperopia during childhood remain unclear.

Prostate cancer (CaP) disproportionately affects Black men in the United States, leading to significant disparities in incidence, survival, and quality of life (QoL). Treatment-related side effects, including urinary dysfunction, pain, fatigue, and psychological distress, contribute to poor long-term outcomes. There is an urgent need for culturally-tailored, technology-based interventions to support symptom self-management and survivorship care.

Metabolic dysfunction–associated steatotic liver disease (MASLD), formerly known as nonalcoholic fatty liver disease (NAFLD), is a major global health concern, affecting over 30% of adults worldwide. Closely associated with metabolic comorbidities such as obesity, type 2 diabetes, and dyslipidemia, MASLD relies heavily on health behavior modification for effective management. However, sustaining healthy behaviors remains challenging, particularly due to the disease’s asymptomatic nature in its early stages and low perceived severity among patients. Thus, understanding patient perceptions and identifying barriers and facilitators are essential for developing effective, patient-centered interventions.

The status of the axilla remains a significant prognostic factor and influences adjuvant systemic and locoregional treatment choices in early-stage breast cancer (EBC). Sentinel node (SN) biopsy continues to be the preferred technique for establishing axillary nodal status in clinically node-negative EBC. A multivariable prediction model with adequate accuracy and generalizability has been explored as a potential alternative to SN.

The exponential growth of electronic health records (EHRs), together with the recent entry into force of the European Health Data Space (EHDS) Regulation, highlights the urgent need for secure, interoperable environments that support the secondary use of health data. In response, HealthData@MAD-R&I emerges as a pioneering initiative in Madrid (Spain), aligned with the EHDS strategy and the European Commission’s vision for data sovereignty and trustworthy data reuse.

Epilepsy is a chronic neurological disorder marked by recurrent and apparently unpredictable seizures and associated with premature death, injury, and diminished quality of life. The unpredictability of seizures is a major concern for people with epilepsy. Thus, developing tools for seizure prediction is a research priority. The Artificial Intelligence to Optimise Seizure Prediction to Empower People With Epilepsy (ATMOSPHERE) project focuses on the development and evaluation of seizure forecasting technology involving mobile technology and machine learning to provide personalized seizure forecasting (risk of seizure in the near future). The project is informed by complex intervention frameworks, which recommend phases of development, feasibility study, clinical evaluation, and implementation.

The ethical, legal, and social issues accompanying the latest advancements in digital health technologies highlight the need to involve the public in their design, development, and deployment to align with societal values and needs. For public engagement to be meaningful, it should be participatory, inclusive, and scalable. However, studies in participatory digital health do not characterize public engagement strategies in terms of scalability, representativeness, and the extent of participation. Moreover, no reviews have examined how ethical debates shape the design and implementation of public engagement strategies in digital health ethics.

Drug-related deaths worldwide are most commonly attributed to opioids. Opioids and other sedative drugs can cause respiratory depression and airway compromise, leading to hypoxia and death. Device technology and artificial intelligence used to detect drug overdose has the potential to improve outcomes. PneumoWave Ltd has developed a small chest-worn respiratory monitoring device to detect concerning breathing patterns and alert an emergency response.