AIM & SCOPE
Aim
The Journal of AI-Integrated Medical Sciences (JAIMS) is an international, peer-reviewed, open-access medical sciences journal dedicated to advancing evidence-based healthcare through the rigorous evaluation and responsible application of artificial intelligence (AI). JAIMS publishes high-quality clinical, translational, epidemiological, public health, and health systems research investigating the role of AI in disease prevention, diagnosis, treatment, monitoring, prognosis, patient management, clinical decision-making, and healthcare delivery.
The journal emphasizes evidence demonstrating how AI-enabled approaches influence clinical practice, patient safety, health outcomes, quality of care, healthcare efficiency, equity, and patient and healthcare professional experience. JAIMS particularly welcomes clinically meaningful research in which AI technologies are evaluated within appropriate medical or healthcare contexts rather than on technical performance alone. The journal seeks to strengthen the evidence base for AI-enabled healthcare through research addressing clinical effectiveness, diagnostic and prognostic performance, safety, reliability, implementation, usability, health equity, ethics, and real-world impact.
Scope
JAIMS considers original and evidence-based research addressing the application, evaluation, validation, implementation, and impact of artificial intelligence in medicine and healthcare. The journal welcomes multidisciplinary research in which AI is examined in relation to clinically meaningful questions, patient outcomes, healthcare delivery, clinical decision-making, patient safety, and health system performance.
AI in Clinical Medicine
JAIMS welcomes research evaluating AI applications across the continuum of patient care, including AI-assisted diagnosis and clinical decision-making, prognostic and predictive modelling, risk stratification, treatment selection and personalization, disease monitoring and progression prediction, AI-assisted patient management, precision and personalized medicine, clinical outcome prediction, screening and early disease detection, and clinical effectiveness and utility. Studies should demonstrate meaningful medical relevance and, where appropriate, evaluate clinical validity, generalizability, patient outcomes, or clinical utility rather than technical performance alone.
Diagnostic, Imaging, and Laboratory Sciences
The journal welcomes research evaluating AI in diagnostic medicine, including radiology and medical imaging, digital pathology and histopathology, laboratory and diagnostic medicine, ophthalmic and dermatological imaging, endoscopy, image-guided diagnosis, ultrasound, computed tomography, magnetic resonance imaging, positron emission tomography, computer vision for clinical diagnosis, AI-assisted screening and detection, and multimodal diagnostic systems. Research addressing diagnostic accuracy, external validation, clinical applicability, patient outcomes, and diagnostic utility is particularly encouraged.
Surgical and Procedural Medicine
JAIMS considers clinically relevant AI research in surgical and procedural care, including surgical decision-making, preoperative risk prediction, surgical planning, intraoperative AI, robotic and computer-assisted surgery, image-guided interventions, perioperative risk assessment, postoperative monitoring, complication prediction, and AI-assisted procedural training and decision support.
Clinical Research and Real-World Evidence
JAIMS prioritizes prospective clinical studies, clinical and pragmatic trials, prospective and retrospective cohort studies, case-control and cross-sectional studies where appropriate, electronic health record-based studies, real-world evidence, external and prospective validation, diagnostic and prognostic accuracy studies, comparative effectiveness research, patient- reported and clinician-reported outcomes, and clinical utility and impact studies. Studies using public or secondary datasets may be considered when they address important medical questions and demonstrate appropriate methodological rigor, validation, clinical relevance, and translational significance.
Human–AI Interaction and Clinical Decision-Making
JAIMS considers research examining clinician–AI interaction, patient–AI interaction, AI-assisted shared decision-making, trust and appropriate reliance on AI, explainability and interpretability, human factors, cognitive workload, automation bias and decision errors, clinical usability, patient and healthcare professional experience, communication, decision quality, and human oversight of AI-supported decisions.
AI Safety, Reliability, and Clinical Quality
Research addressing AI-related clinical errors, diagnostic and therapeutic errors, model failure and uncertainty, algorithmic bias and fairness, performance across diverse populations, dataset shift and model degradation, robustness and reliability, clinical risk assessment, post-deployment monitoring, AI-related adverse events, patient safety, quality assurance, human oversight, and accountability is a priority area. JAIMS welcomes both positive and negative findings when they provide important evidence regarding the clinical effectiveness, limitations, or safety of AI.
Generative AI and Emerging Technologies in Medicine
The journal welcomes rigorous medical research involving large language models, generative AI, multimodal AI, foundation models, natural language processing, computer vision, AI-assisted clinical documentation, clinical summarization and information retrieval, AI-assisted patient education and communication, AI-supported clinical decision-making, and AI in medical education and professional training. Research involving generative or emerging AI should, where appropriate, evaluate accuracy, factuality, reliability, hallucination, safety, usability, bias, reproducibility, and clinical utility.
Public Health, Preventive Medicine, and Population Health
JAIMS considers AI research addressing disease surveillance, outbreak prediction, screening and prevention, population risk prediction, epidemiological modelling, public health decision support, population health management, health resource allocation, health disparities and equity, and AI applications in low- and middle-income healthcare settings.
Healthcare Systems, Implementation, and Health Services Research
Research examining implementation science, effectiveness- implementation research, clinical workflow integration, healthcare service delivery, organizational adaptation, adoption and sustainability, health workforce implications, healthcare efficiency, resource utilization, health economics and cost-effectiveness, scalability, sustainability, and implementation across primary, secondary, and tertiary care is welcomed.
Ethics, Health Equity, and Responsible AI
JAIMS welcomes rigorous research addressing patient autonomy and informed consent, privacy and confidentiality, data governance, algorithmic fairness, health equity, digital and AI literacy, access to AI-enabled healthcare, accountability and responsibility, ethical clinical decision-making, regulatory and governance considerations, and responsible implementation of AI in healthcare.
Evidence Synthesis and Methodological Research
The journal publishes rigorous systematic reviews, meta-analyses, diagnostic accuracy reviews, prognostic evidence syntheses, scientifically justified scoping reviews, methodological reviews, evidence mapping, health technology assessments, implementation reviews, and reviews addressing AI safety, bias, and health equity. Authors should follow appropriate reporting and methodological standards, including PRISMA and relevant AI-specific guidance where applicable.
Clinical Case Reports and Case Series
JAIMS selectively considers case reports and case series that provide substantial clinical or scientific value, particularly those describing novel AI-assisted diagnostic or therapeutic applications, important human–AI clinical interactions, unexpected AI-related diagnostic findings, clinically significant AI failures, AI-related safety events, and novel applications with implications for clinical practice. Routine case reports without a substantive medical or AI-related contribution are not a priority.
Clinical AI Protocols and Research Methodology
JAIMS considers well-designed research protocols and methodological studies addressing clinically important questions in AI-enabled medicine, particularly those involving prospective evaluation, clinical validation, implementation, safety, and patient outcomes. Where applicable, authors should follow appropriate study design and reporting frameworks, including CONSORT-AI, SPIRIT-AI, DECIDE-AI, TRIPOD+AI, STARD-AI, and other relevant standards.
Medical and Health Disciplines
JAIMS adopts a broad, pan-medical scope and welcomes clinically relevant AI research across internal medicine and subspecialties, surgery and surgical subspecialties, cardiology and cardiovascular medicine, neurology and neuroscience, oncology, pulmonology and respiratory medicine, gastroenterology and hepatology, nephrology and urology, endocrinology, infectious diseases, rheumatology and immunology, hematology, pediatrics, obstetrics and gynecology, reproductive medicine, psychiatry and behavioral medicine, dermatology, ophthalmology, otorhinolaryngology and head and neck medicine, emergency and critical care medicine, anesthesiology and perioperative medicine, geriatric medicine, rehabilitation medicine, family medicine and primary care, dentistry and oral health, nursing and allied health sciences, and public health and preventive medicine. Interdisciplinary studies connecting clinical medicine with epidemiology, biostatistics, informatics, implementation science, health economics, ethics, health policy, and related disciplines are also welcomed when they have clear medical or healthcare significance.
Article Types
JAIMS considers Original Research Articles, Clinical Trials, Pragmatic and Comparative Effectiveness Studies, Prospective and Retrospective Cohort Studies, Diagnostic and Prognostic Accuracy Studies, Real-World Evidence Studies, Implementation and Health Services Research, Health Economics and Health Technology Assessment, Systematic Reviews and Meta-Analyses, Scoping and Methodological Reviews, Research Protocols, Methodological and Validation Studies, Clinical Case Reports and Case Series, Short Communications, Perspectives and Expert Commentaries, Editorials, and Special Communications.
Scope Boundaries
JAIMS does not primarily consider manuscripts whose principal contribution is purely computational, engineering-oriented, or technological without meaningful medical or healthcare relevance. Generally outside the journal's scope are pure algorithm development without meaningful medical evaluation, machine-learning studies based solely on benchmark datasets without a clinically meaningful research question or translational relevance, purely in-silico studies without a credible connection to clinical or healthcare applications, software engineering or computational architecture studies without substantive medical evaluation, hardware or sensor research without clinically relevant assessment, basic computational or bioinformatics research without a clear medical or healthcare application, and algorithm comparisons based solely on technical performance metrics without appropriate clinical context.
The use of public or secondary datasets is not, by itself, a reason for exclusion. Studies using electronic health records, clinical databases, imaging repositories, or other publicly available datasets may be considered when they address clinically meaningful questions and demonstrate appropriate methodological rigor, validation, reproducibility, and medical significance.
Medical Sciences First, with Artificial Intelligence as the Scientific Specialization
The central editorial criterion is the medical and healthcare significance of the research. Manuscripts should demonstrate not merely that an AI system can perform a computational task, but whether and how that capability contributes to diagnosis, treatment, prevention, patient safety, clinical decision-making, healthcare delivery, or health outcomes. JAIMS therefore welcomes rigorous evidence demonstrating both the benefits and limitations of AI in medicine, including positive findings, negative results, failed implementations, unexpected failures, safety concerns, external validation, reproducibility studies, and evidence demonstrating when AI does not improve clinical or healthcare outcomes.
