SEARCH · Search PubMed

Results for “Risk-sensitive decision-making”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

1,294 records · Page 4Linked to original sources

PubMed2026

Incidence and risk factors for malignancy in patients with incidental solitary pulmonary nodules: a systematic review and meta-analysis.

BACKGROUND: The increasing use of chest imaging has led to a higher detection rate of incidental solitary pulmonary nodules (SPNs), often causing patient anxiety. Determining the malignancy rate and associated risk factors is crucial for developing appropriate follow-up strategies to prevent overdiagnosis, overtreatment, or missed diagnoses. This meta-analysis aims to investigate the malignancy rate and risk factors in patients with incidental SPNs. METHODS: A systematic search of PubMed, Embase, Web of Science, and the Cochrane Library was conducted up to June 30, 2025. Data on malignancy rates and potential risk factors were extracted from eligible studies. All pooled analyses were performed using a random-effects model. RESULTS: Fifty-four studies involving 19,985 patients were included. The pooled malignancy rate for incidental SPNs was 56.7% (95% CI: 51.5-62.0), with significant between-study heterogeneity (I2 = 98.5%, p < 0.001). The pooled effect size showed a minimal change after adjustment for potential publication bias using the non-parametric Trim-and-Fill method (54.7%; 95%CI: 50.9-58.8). Risk factor analysis identified that older age, history of cancer, cigarette smoker, larger nodule diameter, spiculation, upper lobe location, lobulation, pleural indentation, vascular convergence, solid nodules, family history of cancer, and irregular or ill-defined margins were significantly associated with an increased risk of malignancy. Conversely, male sex, presence of calcification, and clear borders were significantly associated with a reduced risk of malignancy. CONCLUSION: This meta-analysis provides a comprehensive assessment of malignancy rates and risk factors in incidental SPNs. The high pooled malignancy rate should be interpreted considering the significant heterogeneity and the inclusion of a high proportion of retrospective studies and populations from high-risk regions. Nonetheless, these findings offer essential evidence for clinical risk stratification, supporting optimized follow-up and informed decision-making.

Humans↗

PubMed2026

Data-centric, robust, and explainable multimodal deep learning for clinical decision support: A systematic review.

PURPOSE: Multimodal deep learning is increasingly proposed for clinical decision support (CDS) under a "data-centric" framing that prioritizes label quality, missing-modality robustness, distribution shift, calibration, and explainability. Prior reviews have examined multimodal medical AI, CDS, and data-centric methods separately, but none address their intersection. We mapped the modalities, fusion strategies, and data-centric and explainability techniques used in this recent literature, quantified how often each is implemented rather than merely mentioned, assessed deployment-relevant evidence (external validation, clinical-outcome measurement, equity), and formally appraised study-level risk of bias. METHODS: Following the PRISMA 2020 statement (PROSPERO CRD420261427815; registered retrospectively), we screened 150 records and included primary, clinical, multimodal studies that applied machine or deep learning to a decision-support task and reported at least one quantitative result. Two reviewers screened and extracted data with consensus adjudication. Each study was coded against pre-specified operational definitions, separating implemented or empirically evaluated techniques from those only mentioned. Study-level risk of bias was assessed with PROBAST + AI. Synthesis was narrative. RESULTS: Thirty-one studies met inclusion; 30 (97%) were published between 2024 and 2026, with a median of three modalities (range 2-6), most commonly structured EHR (71%) and imaging (39%). Data-centric techniques were frequently reported (74-84% across label-noise, distribution-shift, calibration, missing-modality and class-imbalance handling; equity 61%). However, external validation was reported in only 4/31 studies (13%), a clinical or provider outcome in 3/31 (10%), and no study reported routine deployment. Overall risk of bias was high in 27/31 studies (87%), driven by the analysis domain. CONCLUSION: Within this recent, self-selected slice of the field, technical robustness and explainability techniques are widely reported but rarely validated out-of-distribution or against clinical outcomes, and the underlying evidence is at high risk of bias. Progress requires external multi-site validation, clinical-outcome measurement, formal bias appraisal, and adherence to AI reporting standards (e.g., TRIPOD + AI) before deployment can be justified.

Deep Learning↗

PubMed2026

Power as equal ability, knowledge and resistance: Systematic review of experiences of adults with noncommunicable diseases.

PURPOSE: To analyse subjective experiences of power of adults with noncommunicable diseases in relationships with healthcare practitioners as well as underlying facilitators and barriers of these experiences. METHODS: Systematic review (4 databases) of experiences using reflexive thematic analysis underpinned by critical realist approach. The analysis was conducted with an abductive reasoning using previous theories on social power as well as retroduction. RESULTS: Based on 24 studies, we formed three themes, which depict experiences of power as 1) the position, equal ability and freedom to make one's own choices and (re)negotiate within shared dialogue, 2) the ability to use knowledge to claim one's rights, 3) resistance. Facilitators were connected to acknowledgement as an equally valuable individual, positive healthcare practitioner attitudes and actions towards patient activity and views, safety in the relationship as well as to sufficient, clear and varied information. Main barriers were experiences of dehumanisation, negative healthcare practitioner attitudes and actions, perceived or assumed practitioner domination in interactions, lack of or incomprehensible knowledge and testimonial smothering. CONCLUSION: Results suggest that adults with noncommunicable diseases may experience power primarily as a positive power: being acknowledged as having legitimate position to make decisions and being in possession of varied knowledge through which they can gain agency to protect and claim their rights, by resisting, if necessary. Healthcare practitioners are in key position to support these experiences through positive transforming actions, while knowledge asymmetries, persistent inequality and paternalistic structures continue to hinder it.

Humans↗

PubMed2026

Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis.

BACKGROUND: Early and accurate diagnosis of systemic lupus erythematosus (SLE) and its organ involvement is essential. Previous reviews of machine learning (ML) in SLE combined heterogeneous tasks and validation strategies and may have overinterpreted model performance. OBJECTIVE: This study evaluated the diagnostic performance of ML and deep learning (DL) models for 3 clinically distinct SLE-related tasks: SLE classification or diagnosis, lupus nephritis (LN) diagnosis, and neuropsychiatric systemic lupus erythematosus (NPSLE) discrimination. We also assessed methodological quality and certainty of evidence. METHODS: PubMed, Embase, Cochrane Library, Web of Science, and IEEE Xplore were searched from January 2014 to April 2026. Eligible peer-reviewed diagnostic accuracy studies developed or validated ML or DL models for 1 of the 3 prespecified tasks, used an accepted reference standard, and provided data for a 2×2 contingency table. Bivariate random-effects meta-analyses with the Hartung-Knapp-Sidik-Jonkman adjustment were used to pool sensitivity and specificity. We reported 95% prediction intervals (PIs), assessed risk of bias using the Quality Assessment of Diagnostic Accuracy Studies for Artificial Intelligence tool (QUADAS-AI; Viknesh Sounderajah [Imperial College London]), and evaluated certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation framework for diagnostic test accuracy. RESULTS: Twenty-nine studies were included: 17 for SLE classification, 5 for LN diagnosis, and 7 for NPSLE discrimination. In the primary task-stratified analysis, pooled sensitivity was 0.91 (95% CI 0.86-0.94; 95% PI 0.56-0.99), and pooled specificity was 0.94 (95% CI 0.91-0.96; 95% PI 0.69-0.99), with low heterogeneity (I²=23.9% and 22.9%, respectively). DL models showed a sensitivity of 0.93 and specificity of 0.95, compared with 0.88 and 0.94 for traditional ML models. Certainty of evidence was high for most analyses but low for LN diagnosis because of inconsistency and imprecision. All studies were retrospective, and only 9 of 29 (31%) performed independent external validation. Overall risk of bias was high or unclear in 22 of 29 (75.9%) studies. No study reported model calibration, decision-curve analysis, or net clinical benefit. CONCLUSIONS: ML models showed promising diagnostic accuracy across 3 distinct SLE-related tasks, but wide PIs, limited external validation, and pervasive risk of bias restrict conclusions about real-world generalizability. Prospective multicenter studies with standardized tasks and reference standards, independent external validation, and formal assessment of calibration and clinical utility are required before clinical implementation.

Humans↗

PubMed2026

Civil liability in oral & maxillofacial surgery: Α systematic review.

Maxillofacial surgery is a surgical specialty with anatomical, functional, and aesthetic requirements, which makes it a field at increased risk of medical negligence and subsequent legal claims. The review was conducted in accordance with the PRISMA guidelines and used international medical and legal databases. Studies that analyzed court decisions, insurance claims, or recorded compensation data related to maxillofacial surgery were included. The extracted data included, among others, the year and country of publication, the causes of action, and the amounts of financial compensation. Most lawsuits originate from countries with developed medical liability systems, primarily the United States and the United Kingdom, and there has been an increasing trend in publications over the last two decades. The most common causes of lawsuits involve nerve injuries, delayed or incorrect diagnoses, technical errors during surgery, and inadequate informed consent. The amounts of compensation vary widely, from lower five-digit amounts in milder cases to particularly high amounts in cases of permanent functional or aesthetic damage, placing a significant overall financial burden on health systems. Medical negligence in maxillofacial surgery constitutes an important forensic and socioeconomic issue. Understanding the causes of lawsuits and their financial consequences can help improve clinical practice, inform patients, and prevent legal disputes.

Humans↗

PubMed2026

Integrated multi-omics profiling of amniotic fluid identifies predictive biomarkers for fetal growth restriction trajectories.

BACKGROUND: Fetal growth restriction (FGR) is a complex condition with highly heterogeneous clinical outcomes, making prenatal distinction between transient and persistent growth failure challenging. This study aims to identify amniotic fluid (AF) biomarkers capable of differentiating distinct FGR trajectories and characterizing persistent growth failure mechanisms. METHODS: Integrated proteomic and metabolomic profiling was performed on AF samples from transient FGR (n = 11), persistent FGR (n = 9), and healthy controls (n = 13). Diagnostic and prognostic models were developed using multivariate analysis. Selected protein candidates were validated via ELISA in an independent cohort (n = 69). RESULTS: Multi-omics analysis revealed distinct molecular signatures for FGR stratification. A two-protein diagnostic panel (PDGFA and phospho-STAT5A) achieved an AUC of 1.000 in the discovery stage and 0.780 in the external validation cohort. For prognostic assessment, a molecular signature including IREB2, HLA-C, and PLXNB2 accurately predicted persistent growth failure from transient recovery (AUC = 0.966). Cross-platform integration highlighted the mass spectrometry-derived WASHC2C as a central hub protein with a significant progressive increase across the control, transient, and persistent groups (p < 0.001). CONCLUSIONS: This study establishes a multi-omics framework for prenatal FGR stratification. Our findings identify distinct molecular signatures reflecting the intrauterine environment and provide high-performance molecular tools for predicting divergent fetal growth trajectories to guide personalized clinical decision-making.

Humans↗

PubMed2026

The Natural History of Residual and Recurrent Disease in Advanced Juvenile Nasopharyngeal Angiofibroma: A Systematic Review.

OBJECTIVE: This systematic review explores the natural history of residual and recurrent juvenile nasopharyngeal angiofibromas (JNAs) to inform clinical decision-making. DATA SOURCES: PubMed, Embase, Scopus, and Web of Science. REVIEW METHODS: A systematic literature review was conducted according to PRISMA guidelines across PubMed, Embase, Scopus, and Web of Science from inception to February 20, 2025 and was re-run on September 21, 2025. Studies included patients with advanced JNA and documented follow-up of residual or recurrent disease. Descriptive statistics, chi-squared analysis, and analysis of variance were used to evaluate treatment outcomes across different modalities including surgery, radiotherapy, gamma knife surgery, and medical therapies. RESULTS: Twenty-one studies encompassing 131 male patients (mean age 16.3 years) were included. Residual or recurrent disease demonstrated complete involution in 41%, stable disease in 29%, and reduction in size in 25% of cases. Only 2% of patients had progressive disease. A statistically significant association was observed between treatment modality and outcome (p = 0.015), with radiotherapy, either alone, or as part of a multimodal approach, showing the highest rates of spontaneous involution. CONCLUSION: Residual and recurrent JNAs often remain stable or regress without further intervention. Close surveillance with imaging is a safe and effective strategy for asymptomatic patients, minimizing the risks of additional treatment in a young patient population with disease near critical anatomical structures.

Humans↗

PubMed2026

Maternal vaccination with RSVpreF and risk of hypertensive disorders of pregnancy: a systematic review and meta-analysis.

BACKGROUND: A bivalent respiratory syncytial virus (RSV) prefusion F protein-based vaccine (RSVpreF) was approved in the United States in August 2023 for use during pregnancy to prevent infant RSV-associated lower respiratory tract disease. The pivotal phase 3 trial identified a numerical imbalance in hypertensive disorders of pregnancy (HDP) that did not reach statistical significance; postmarketing observational studies have since reported inconsistent findings. We conducted a systematic review and meta-analysis to assess this association. METHODS: We searched MEDLINE, Embase, CENTRAL, Scopus, ClinicalTrials.gov, and WHO ICTRP from inception to Jan 26, 2026, for randomized controlled trials (RCTs) and observational studies comparing HDP outcomes in RSVpreF-vaccinated versus unvaccinated or placebo-receiving pregnant individuals. Unadjusted risk ratios (RRs) were pooled using a random-effects model; adjusted estimates from observational studies were pooled separately by inverse variance methods. This study is registered with PROSPERO (CRD420251026835). RESULTS: Nine studies were included (3 RCTs, 6 retrospective cohort studies; n = 148,267). RSVpreF vaccination was associated with a small but statistically significant increase in overall HDP risk (RR 1·08, 95% CI 1·02-1·13; p = 0·004; I2 = 44%), driven by the observational studies group (1·08, 1·02-1·14; I2 = 61%); RCTs showed a directionally consistent but non-significant RR (1·12, 0·87-1·43; I2 = 0%). The association was attributable to gestational hypertension, with no significant association for preeclampsia/eclampsia. CONCLUSION: Maternal RSVpreF vaccination was associated with a small increase in HDP attributable to gestational hypertension and driven primarily by observational studies, in which residual confounding remains possible. The benefits of infant RSV prevention remain substantial, and these findings support continued postmarketing surveillance and informed shared decision-making.

Humans↗

PubMed2026

Complicated urinary tract infections: evolving definitions, clinical burden, and treatment landscape amid antimicrobial resistance.

INTRODUCTION: Complicated urinary tract infection (cUTI) is a common and heterogeneous infection associated with substantial morbidity, high healthcare utilization, and increasing antimicrobial resistance. Evolving definitions, increasing device use, and changing patient populations have altered its epidemiology and management. Marked variability in diagnostic criteria, clinical trial endpoints within and outside registrational settings, and treatment strategies complicates clinical decision-making and interpretation of therapeutic advances. AREAS COVERED: This review examines contemporary cUTI epidemiology, classification frameworks, and drivers of disease burden. It evaluates resistance trends and their therapeutic implications, alongside stewardship-based management strategies, including empiric antibiotic selection, intravenous-to-oral transition, treatment duration, and source control. Challenges in catheter-associated infection, recurrence, and regulatory endpoint design are discussed, together with the emerging role of novel agents targeting resistant Gram-negative pathogens. EXPERT OPINION: Rising multidrug resistance and limited oral options are reshaping cUTI management, necessitating individualized, stewardship-aligned therapy guided by illness severity and local epidemiology. Current regulatory endpoints inadequately reflect patient-centered outcomes, particularly in the context of asymptomatic bacteriuria. Expanding availability of effective oral agents may enable earlier discharge and outpatient care. Integration of rapid diagnostics and risk stratification will be essential to optimize therapy, limit resistance, and improve outcomes.

Humans↗

PubMed2026

How Following Medical Artificial Intelligence Advice Can Mitigate Malpractice Liability: Cross-National Insights from a Randomized Trial.

Artificial intelligence (AI) increasingly influences clinical decision-making, yet its recommendations may diverge from standard care. Although malpractice concerns are thought to discourage physicians from following AI advice, experimental evidence from the United States suggests the opposite: lay jurors are more likely to hold physicians liable when they reject AI recommendations. Whether this pattern extends to systems in which court-appointed experts, not lay jurors, determine liability remains unknown. Methods: To examine how physicians and laypeople in expert-based and lay-juror legal systems evaluate physicians' acceptance or rejection of AI recommendations, particularly when those recommendations deviate from standard care, we designed a randomized vignette study: a 2 × 2 factorial design varying the AI recommendation (standard vs. nonstandard care) and a fictional physician's decision (accept vs. reject). The study was conducted online in 2023 among nationally representative samples of U.S. and German adults and from 2023 to 2024 among German physicians. In total, 387 German physicians, 2291 U.S. adults, and 2283 German adults participated; those not completing the survey or failing attention checks were excluded per preregistered criteria. Participants were randomly assigned to 1 of 4 vignettes, varying the AI recommendation (standard vs. nonstandard care) and physician's decision (accept vs. reject). The reasonableness of the fictional physician's decision was measured, rated by participants on a Likert scale. Results: Analysis, following preregistered exclusion criteria, included 248 German physicians, 1202 U.S. adults, and 1358 German adults. Physicians accepting standard-care AI recommendations were rated more reasonable than those rejecting them (U.S. laypeople: t = 5.36; 95% CI, 0.45-0.97; P < 0.001; German physicians: t = 2.47; 95% CI, 0.14-1.30; P = 0.02; German laypeople: t = 4.14; 95% CI, 0.27-0.76; P < 0.001). Ratings of physicians accepting versus rejecting AI nonstandard-care recommendations were statistically equivalent. Equivalence was tested at an α-value of 0.05 using a two 1-sided tests procedure, reported with 90% CIs per standard convention (U.S. laypeople: t = -4.90; 90% CI, -0.1 to 0.36; P < 0.001; German physicians: t = -1.76; 90% CI, -0.12 to 0.67; P = 0.04; German laypeople: t = 5.35; 90% CI, -0.35 to 0.06; P < 0.001). Conclusion: Across the United States and Germany, samples representative of lay jurors and court-appointed experts viewed accepting standard-care AI advice as more reasonable, whereas accepting or rejecting nonstandard-care AI advice was judged similarly. Contrary to predictions, malpractice liability regimes do not necessarily pose a barrier to AI use in precision medicine.

Artificial Intelligence↗

PubMed2026

Germline variants and impact on lung cancer outcomes following chemotherapy: A systematic review.

BACKGROUND: Lung cancer is the primary cause of cancer deaths in the UK and globally, and the main subtypes are non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). Many treatment options are available, with platinum-based chemotherapy being a key component for many patients. However, variation in survival outcomes exists among individuals of European ancestry, which makes it important to identify germline genetic variants that help guide decision-making and optimise patient treatment and outcomes. METHOD: A systematic literature search was conducted in PubMed and Web of Science for lung cancer studies investigating the impact of germline genetic variants on systemic anti-cancer therapy (SACT) outcomes in populations of European ancestry. The review was conducted according to the Preferred Reporting Items of Systematic Review and Meta-Analysis (PRISMA) and Synthesis without Meta-Analysis (SWiM) guidelines. RESULTS: A total of 20 studies were included in the review out of 4469 on NSCLC and SCLC, encompassing 3639 patients. The most thoroughly investigated area was NSCLC treated with platinum-based chemotherapy. Genetic variants associated with overall survival and/or progression-free survival included XPD Lys751Gln, XPD Asp312Asn, ERCC1 C118T, and XRCC1 Arg399Gln. For non-platinum-treated NSCLC and SCLC, there was insufficient evidence to conduct a meaningful investigation. CONCLUSION: The XPD Lys751Gln, XPD Asp312Asn, ERCC1 C118T, and XRCC1 Arg399Gln variants showed potential associations with survival outcomes among patients of European ancestry with NSCLC after platinum-based chemotherapy. To support clinical implementation, large real-world pharmacogenomics studies stratified by ancestry are needed to overcome statistical power and heterogeneity limitations.

Humans↗

PubMed2026

The future of pediatric vesicoureteral reflux management.

BACKGROUND AND OBJECTIVE: Vesicoureteral reflux (VUR) is a common condition in pediatric urology, yet important uncertainties persist regarding risk stratification, imaging strategies, and prevention of long-term renal damage. Emerging technologies may help address these challenges. This review provides a forward-looking overview of recent advances in artificial intelligence (AI) and immunomodulation that may influence future management of pediatric VUR. METHODS: A forward-looking literature review was performed using the PubMed database (January 2000-March 2025), focusing on studies addressing AI, immunomodulation, or vaccination in the context of VUR and urinary tract infections. Criteria of inclusion were the relevance to pediatric VUR, the novelty of the proposed concept, the potential clinical implications and, for the AI literature, the existence of a clinical evaluation of the algorithm on a dataset from patients. KEY FINDINGS AND LIMITATIONS: AI-based models show promising performance in supporting clinical decision-making, including prediction of the need for voiding cystourethrography, automated grading of VUR, estimation of recurrent urinary tract infection risk and prediction of chemoprophylaxis. These tools may facilitate more individualized diagnostic and therapeutic strategies, although current evidence is largely retrospective and requires prospective validation. Immunization and immunomodulatory approaches aim to reduce infection burden and modulate inflammatory pathways associated with renal scarring. While early experimental and adult clinical data are encouraging, pediatric-specific evidence remains limited, and clinical applicability in children with VUR is not yet established. CONCLUSION: Artificial intelligence and immunologically targeted strategies represent complementary, emerging approaches that may contribute to more personalized management of pediatric VUR. At present, both should be regarded as exploratory tools whose clinical impact will depend on further validation and appropriately designed pediatric studies.

Humans↗

PubMed2026

Evaluation of intravenous sedation in dental implant surgeries: A prospective cohort study.

PURPOSE: This study aimed to evaluate the impact of intravenous sedation on patient-centered outcomes during implant and bone augmentation surgeries. METHOD: A prospective observational cohort study included 40 patients undergoing placement of ≥3 implants, with or without bone augmentation. Patients underwent surgery under either intravenous sedation (n = 20) or local anesthesia alone (n = 20), according to routine clinical decision-making and patient preference. The sedation group received intravenous sedation with a multimodal regimen comprising remimazolam, dexmedetomidine, alfentanil, and low-dose esketamine, whereas the control group received local anesthesia only. Patient-reported outcome measures, hemodynamic parameters (SBP, DBP, HR, SpO2), postoperative pain (0-10 scale), and OHRQoL (OHIP-14) were recorded from baseline through 7 days post-surgery. RESULTS: Intravenous sedation was associated with significantly lower intraoperative pain (0.5 [IQR: 0∼2.75] vs. 3.25 ± 2.40, p = 0.003), anxiety (1 [IQR: 0∼2.75] vs. 4 [IQR: 3∼6], p = 0.001), and experienced discomfort (2 [IQR: 1∼3.75] vs. 4.15 ± 2.16, p = 0.016), and shortened perceived treatment duration (2.90 ± 2.34 vs. 5 [IQR: 4∼5], p = 0.020). Early postoperative pain was lower in the sedation group from Days 1-4 (p = 0.003-0.010). Hemodynamic parameters were more stable under sedation, with lower SBP (116.42 ± 13.32 vs. 144.11 ± 17.42 mmHg, p < 0.001), DBP (73.21 ± 10.28 vs. 82.37 ± 11.03 mmHg, p = 0.012), and HR (71.00 [IQR: 62.50∼79.25] vs. 85.00 ± 10.72 bpm, p = 0.021). OHRQoL scores favored the sedation group in swallowing, diet, malaise, and daily activities, particularly during the first three postoperative days (p=0.006-0.040). CONCLUSION: Intravenous sedation may enhance the patient experience during implant and/or bone augmentation procedures by reducing intraoperative pain and anxiety, improving hemodynamic stability, and promoting better early-postoperative recovery and OHRQoL. These findings suggest that intravenous sedation provides a safe and effective alternative for implant dentistry surgery, particularly for anxious or pain-sensitive individuals.

Humans↗

PubMed2026

Financial incentives and social messaging for repeat SARS-CoV-2 antibody testing among the underserved: A randomized trial.

Financial incentives may influence health behavior beyond their expected monetary value, and their effectiveness may depend on how the behavior is framed. Behavioral theories of decision making suggest that individuals may value protection against small-stakes losses more than expected utility predicts, while theories of family-centered health behavior suggest that messages emphasizing benefits to family members may strengthen participation in preventive health activities. We tested these ideas in a 2×2 factorial randomized trial involving 625 households recruited from a Federally Qualified Health Center serving low-income Latino/Hispanic communities. Participants completed repeat SARS-CoV-2 antibody testing. The trial crossed two messaging strategies (Family vs. Personal) with two incentive structures (Loss Protection vs. Lottery) that offered equivalent expected monetary value. Family Messaging emphasized protecting one's family from COVID-19, whereas Personal Messaging emphasized protecting oneself. Loss Protection allowed participants to secure an at-risk reward through repeat testing, whereas the Lottery condition offered a chance of a large reward. Repeat testing was approximately 8 percentage points higher under Family Messaging and 7 percentage points higher under Loss Protection. Baseline trust in medical providers, financial barriers to vaccination, and risk aversion were associated with initial testing, whereas household characteristics were not associated with repeat testing. Incentive design may matter beyond expected monetary value and that framing health behaviors in terms of family welfare may increase participation in repeated healthy activities. Broadly, the results support behavioral theories emphasizing loss aversion, anticipated regret, and family-centered motivations, and suggest practical approaches for improving engagement in repeat health behaviors. CLINICALTRIALS.GOV REGISTRATION NUMBER:: NCT01901624.

Adult↗

PubMed2026

How AI-supported intelligent systems support infection prevention and control training in healthcare: A systematic review of educational functions and outcomes.

AIMS: Artificial intelligence (AI)-supported intelligent systems have been increasingly incorporated into infection prevention and control (IPC) education and training, primarily to support the monitoring of observable behaviors and the provision of feedback. However, existing evidence has focused largely on short-term compliance outcomes, with limited synthesis of the educational role of AI-supported intelligent systems in supporting sustained IPC competence. This systematic review examined how AI-supported intelligent systems have been designed and used to support IPC education and training, with a focus on system characteristics, educational functions, and reported outcomes. DESIGN: A systematic literature search was conducted across the PubMed/MEDLINE, Embase, Cochrane, and CINAHL databases. DATA SOURCES: A total of 18 studies met the inclusion criteria. Findings were qualitatively synthesized according to system design characteristics, educational functions, and outcome domains. REVIEW METHODS: Methodological quality was appraised using the Mixed Methods Appraisal Tool. RESULTS: Most AI-supported intelligent systems focused on hand hygiene and relied on fully automated monitoring systems to capture behaviors and provide performance feedback. Educational functions were predominantly limited to performance assessment, automated feedback, and reminders. Outcomes were mainly measured using compliance or performance metrics, whereas sustained behavioral change and decision quality were rarely assessed. CONCLUSIONS: AI-supported intelligent systems have been used primarily to reinforce short-term IPC performance and compliance. However, their current applications for supporting sustained competence over time remain limited. The findings of this review suggest that AI-supported intelligent systems may serve as maintenance-oriented educational support by extending learning beyond initial instruction through repeated practice and feedback. Future research should prioritize outcome measures that capture the durability of performance and decision-making processes to better align AI-supported intelligent systems used in IPC education and training with the educational demands of clinical practice.

Humans↗

PubMed2026

Artificial intelligence-supported double reading in European population breast cancer screening: A systematic review and meta-analysis of prospective programs.

BACKGROUND: Most European population mammography screening programs rely on double reading with arbitration, a model that delivers mortality benefit but is increasingly challenged by radiologist workload, variable specificity, and interval cancers. Artificial intelligence (AI) is being evaluated to support or optimize these established European screening pathways. PURPOSE: To synthesize prospective or program-embedded evaluations of AI conducted within European-style population screening programs and to estimate exploratory program-level absolute risk differences (RDs) per 1000 examinations for cancer detection rate (CDR) and recall. MATERIALS AND METHODS: We performed a prespecified, focused evidence synthesis of three large studies embedded within routine population screening programs operating under European-relevant workflows: MASAI (randomized AI-supported risk triage within a national program), ScreenTrustCAD (prospective paired-reader evaluation with AI as an independent reader in a double-reading framework), and PRAIM (nationwide decision-referral implementation). Outcomes were harmonized as AI-control RDs per 1000 examinations. Random-effects pooling used Hartung-Knapp-Sidik-Jonkman models. For the paired-reader design, sensitivity analyses applied a Kish effective sample-size approach across plausible within-examination correlations (ρ = 0.3-0.8). Positive predictive value (PPV) and workflow/time outcomes were summarized descriptively. RESULTS: Across 597,419 examinations, the pooled CDR RD was +0.9 per 1000 (95% CI -0.0 to +1.8; I2 ≈ 12%), consistent with a modest directional increase with borderline statistical uncertainty. The pooled recall RD was -0.6 per 1000 (95% CI -3.1 to +2.1; I2 ≈ 41-43%), indicating no consistent recall increase across screening programs. Where reported, PPV was higher with AI-supported screening. Efficiency signals included 44.3% fewer total readings in MASAI and shorter reading times for AI-normal examinations in PRAIM; in PRAIM, a program-level safety-net mechanism recovered 204 cancers that would otherwise have been missed. CONCLUSION: In European population screening programs characterized by double reading and arbitration, prospective program-embedded evidence suggests that AI integration may yield a small absolute increase in cancer detection (≈1/1000) without a consistent increase in recall, alongside improved PPV and efficiency signals. These findings suggestAI primarily as a complementary reader within European screening workflows, with implementation requiring explicit quality assurance and monitoring of interval cancers and stage distribution.

Humans↗

PubMed2026

Indigenous and local knowledge inclusion in forest fauna research: A systematic review in the tropics.

Indigenous and Local Knowledge (ILK) is an expression of biocultural diversity and is vital for inclusive and sustainable forest management and epistemic justice. We examine how researchers studying tropical forest fauna engage with ILK and the Indigenous Peoples and Local Communities (IPLC) who are holders of this knowledge. We conducted a systematic review of 62 articles that focus on tropical forest fauna and ILK. We used a category-based quantitative and qualitative content analysis on the types of forest fauna studied and how research engages with, defines and represents ILK. We also evaluated the varied forms of inclusion of IPLC in the research. We find that less than half of the reviewed studies (25) explicitly define ILK, and only four studies reported including IPLC in the decision-making processes. Our findings reveal that science has not fully acknowledged and understood the depth of ILK and we suggest ways to address this in future research.

Forests↗

PubMed2026

Artificial Intelligence Cannot Replace Peer Reviewers but May Help Editors Triage: A Comparative Analysis of a Large Language Model and Human Reviewer Recommendations at the American Journal of Sports Medicine.

BACKGROUND: The peer review system faces increasing strain from rising manuscript volumes, reviewer fatigue, and well-documented interreviewer disagreement. Large language models (LLMs) have shown potential to support the peer review process, but their ability to replicate editorial decisions at high-impact medical journals and their utility as manuscript screening tools remain unknown. PURPOSE: To compare the agreement between an LLM and the final editorial decision on manuscripts submitted to the American Journal of Sports Medicine and to evaluate the potential of LLMs as a manuscript screening tool. STUDY DESIGN: Cross-sectional agreement study. METHODS: Fifty-four manuscripts randomly selected from submissions to the American Journal of Sports Medicine (September 2024-October 2024) were reviewed by a locally deployed LLM (Ministral 3 14B; Mistral AI) using a standardized prompt. The artificial intelligence (AI) produced a categorical recommendation (reject, cascade, revision, or accept) and a numerical score (0-100) for each manuscript. Agreement with the final editorial decision was assessed by Cohen kappa (4-category model) for pooled human reviewers (n = 139 reviews) and the AI (n = 54). Screening performance was evaluated by positive predictive value (PPV), sensitivity, and specificity. RESULTS: Pooled human reviewers demonstrated fair agreement with the final decision (κ = 0.181 [P < .001]; 42.4% agreement), while the AI demonstrated slight, nonsignificant agreement (κ = 0.126 [P = .099]; 37.0% agreement). The AI recommended revision for 61.1% of manuscripts, of which 72.7% were ultimately rejected or cascaded, demonstrating systematic "revision bias." When the AI recommended rejection, 54.5% of those manuscripts were ultimately rejected and 27.3% were cascaded; when the AI recommended cascade, 50% were rejected and 50% were cascaded. However, when the AI recommended rejection or cascade (n = 21), 90.5% received a final decision of rejection or cascade (PPV, 90.5%; specificity, 81.8%). Manuscripts with an AI score <70 were rejected or cascaded 88.0% of the time (PPV, 88.0%). CONCLUSION: AI cannot replicate the nuanced judgment of human peer reviewers at a high-impact sports medicine journal. When AI recommended rejection or cascade, 90.5% of manuscripts received that final decision (descriptive PPV, 90.5%; 95% CI, 71.1%-97.3%), suggesting potential utility as an exploratory first-pass screening tool warranting further validation in larger cohorts. However, AI could not reliably distinguish manuscripts destined for outright rejection from those that would be cascaded to a sister journal-an important limitation for editorial triage applications.

Sports Medicine↗