Diagnosis, Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 3, 2024
Diagnostic scope is the range of diagnoses found in a clinical setting. Although diagnostic an essential feature training and evaluating artificial intelligence (AI) systems to promote excellence, its impact on AI process remains under-explored.
Language: Английский
Journal of the American Medical Informatics Association, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 7, 2025
Abstract The primary practice of healthcare artificial intelligence (AI) starts with model development, often using state-of-the-art AI, retrospectively evaluated metrics lifted from the AI literature like AUROC and DICE score. However, good performance on these may not translate to improved clinical outcomes. Instead, we argue for a better development pipeline constructed by working backward end goal positively impacting clinically relevant outcomes leading considerations causality in validation, subsequently pipeline. Healthcare should be “actionable,” change actions induced improve Quantifying effect changes is causal inference. evaluation, validation therefore account intervening Using lens, make recommendations key stakeholders at various stages Our aim increase positive impact
Language: Английский
Citations
2
Annals of Internal Medicine, Journal Year: 2024, Volume and Issue: 177(7), P. 964 - 967
Published: June 3, 2024
Internal medicine physicians are increasingly interacting with systems that implement artificial intelligence (AI) and machine learning (ML) technologies. Some health care even developing their own AI models, both within outside of electronic record (EHR) systems. These technologies have various applications throughout the provision care, such as clinical documentation, diagnostic image processing, decision support. With growing availability vast amounts patient data unprecedented levels clinician burnout, proliferation these is cautiously welcomed by some physicians. Others think it presents challenges to patient-physician relationship professional integrity dispositions understandable, given "black box" nature for which specifications development methods can be closely guarded or proprietary, along relative lagging absence appropriate regulatory scrutiny validation. This American College Physicians (ACP) position paper describes College's foundational positions recommendations regarding use AI- ML-enabled tools in care. Many recommendations, those related patient-centeredness, privacy, transparency, founded on principles ACP Ethics Manual. They also derived from considerations safety effectiveness well potential consequences disparities. The calls more research ethical implications effects well-being.
Language: Английский
Citations
17
NEJM AI, Journal Year: 2024, Volume and Issue: 1(8)
Published: July 10, 2024
Language: Английский
Citations
17
Clinical Pharmacology & Therapeutics, Journal Year: 2024, Volume and Issue: 116(3), P. 619 - 636
Published: July 11, 2024
Precision dosing, the tailoring of drug doses to optimize therapeutic benefits and minimize risks in each patient, is essential for drugs with a narrow window severe adverse effects. Adaptive dosing strategies extend precision concept time-varying treatments which require sequential dose adjustments based on evolving patient conditions. Reinforcement learning (RL) naturally fits this paradigm: it perfectly mimics decision-making process where clinicians adapt administration response evolution monitoring. This paper aims investigate potentiality coupling RL population PK/PD models develop algorithms, reviewing most relevant works field. Case studies were integrated within algorithms as simulation engine predict consequences any action have been considered discussed. They mainly concern propofol-induced anesthesia, anticoagulant therapy warfarin variety anticancer differing administered agents and/or monitored biomarkers. The resulted picture highlights certain heterogeneity terms approaches, applied methodologies, degree adherence clinical domain. In addition, tutorial how problem should be formulated key elements composing framework (i.e., system state, agent actions reward function), could enhance approaches proposed readers interested delving Overall, integration into RL-framework holds great promise but further investigations advancements are still needed address current limitations applicability methodology requiring adaptive strategies.
Language: Английский
Citations
9
Journal of Medicine Surgery and Public Health, Journal Year: 2024, Volume and Issue: 3, P. 100138 - 100138
Published: Aug. 1, 2024
Language: Английский
Citations
7
npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)
Published: Feb. 6, 2025
The European CORE–MD consortium (Coordinating Research and Evidence for Medical Devices) proposes a score medical devices incorporating artificial intelligence or machine learning algorithms. Its domains are summarised as valid clinical association, technical performance, performance. High scores indicate that extensive investigations should be undertaken before regulatory approval, whereas lower which less pre-market evaluation may balanced by more post-market evidence.
Language: Английский
Citations
0
Progress in Retinal and Eye Research, Journal Year: 2025, Volume and Issue: unknown, P. 101353 - 101353
Published: March 1, 2025
Language: Английский
Citations
0
Global Clinical Engineering Journal, Journal Year: 2025, Volume and Issue: 7(1), P. 5 - 16
Published: March 31, 2025
In an era of rapid digital transformation, patient safety is increasingly intertwined with technological advancements in healthcare. This article explores the dual nature these innovations, where tools like telemedicine, artificial intelligence (AI), and electronic health records (EHRs) offer significant potential to enhance care delivery introduce new risks such as algorithmic bias, cybersecurity threats, challenges minimizing risks. A balanced approach focusing on robust protocols continuous learning required ensure technology enhancement without undermining safety. The paper aims advance discourse integrating patient-centric care, proposing future research policy development strategies sustain a high standard healthcare environment.
Language: Английский
Citations
0
JAMA Network Open, Journal Year: 2025, Volume and Issue: 8(4), P. e258052 - e258052
Published: April 30, 2025
Importance The primary objective of any newly developed medical device using artificial intelligence (AI) is to ensure its safe and effective use in broader clinical practice. Objective To evaluate key characteristics AI-enabled devices approved by the US Food Drug Administration (FDA) that are relevant their generalizability reported public domain. Design, Setting, Participants This cross-sectional study collected information on all received FDA approval were listed website as August 31, 2024. Main Outcomes Measures For each device, detailed for at time summarized, specifically examining evaluation aspects, such presence design performance studies, availability discriminatory metrics, age- sex-specific data. Results In total, 903 FDA-approved analyzed, most which became available last decade. primarily related specialties radiology (692 [76.6.%]), cardiovascular medicine (91 [10.1%]), neurology (29 [3.2%]). Most software only (664 [73.5%]), 6 (0.7%) implantable. Detailed descriptions development absent from publicly provided summaries. Clinical studies 505 (55.9%), while 218 (24.1%) explicitly stated no conducted. Retrospective designs common (193 [38.2%]), with 41 (8.1%) being prospective 12 (2.4%) randomized. Discriminatory metrics 200 summaries (sensitivity: 183 [36.2%]; specificity: 176 [34.9%]; area under curve: 82 [16.2%]). Among less than one-third data (145 [28.7%]), 117 (23.2%) addressed age-related subgroups. Conclusions Relevance this study, approximately half devices, yet was often insufficient a comprehensive assessment generalizability, emphasizing need ongoing monitoring regular re-evaluation identify address unexpected changes during use.
Language: Английский
Citations
0
npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)
Published: May 6, 2025
Language: Английский
Citations
0