Tejas S Athni reported in the Journal of Medical Internet Research that conversational medical AI systems are increasingly simulating licensed health care providers while disclaiming legal responsibil…
Fraudulent papers and false authorship are surging across scientific publishing, driven by predatory journals and AI, according to a report by JMIR correspondent Cliff Dominy.…
A systematic review by Mohamed Ebraheem et al., published in J Med Internet Res, surveys Explainable AI (XAI) methods applied to deep learning for audio-based voice and speech clinical applications. T…
Researchers from Peking University developed ECG-R1, a multimodal vision-language model trained with reinforcement learning to differentiate ischemic from nonischemic T-wave inversion on ECGs. The mod…
Researchers combined prescription records with free-text anamneses from a 10% sample of the Estonian population (2012-2019) and applied Llama-3.1-70B and GPT-4o to extract drug discontinuation events …
Researchers Kumar and Varshney proposed a six-pillar framework to mitigate homogenizing bias in AI models for facial aesthetic evaluation, as detailed in a JMIR preprint. The framework addresses under…
A simulation-based study published in the Journal of Medical Internet Research found that patient cognitive bias reduced large language model diagnostic accuracy by 10 to 40 percentage points across s…
A qualitative study by Kim et al., published as a JMIR preprint, found that South Korean psychiatrists encounter generative AI through patient-facing chatbots, self-help tools, and clinician workflow …
Artificial intelligence is being integrated across preclinical drug discovery stages, from target identification to lead optimization, using techniques including virtual screening, molecular docking, …
A pre-post time-motion study of a domain-specific AI speech assistant used by nurses in German long-term care found substantial reductions in self-reported documentation time and increased satisfactio…
Researchers integrated radiology report text with structured electronic health record data to predict renal tumor malignancy, achieving an area under the ROC curve of 0.818 using an early fusion strat…