SEARCH · Search PubMed

Results for “AI-assisted literature review”

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.

1,207 records · Page 2Linked to original sources

PubMed2026

Challenges and future directions in AI-driven biomaterials for microbiome-associated oral infectious diseases: A systematic review.

Oral biofilm-induced antimicrobial resistance is the core pathogenic mechanism of microbiome-associated oral infectious diseases (dental caries, periodontitis, peri-implantitis, and endodontic infection). Traditional therapies and biomaterials are limited by poor biofilm penetration, drug resistance induction, single functionality, and inadequate adaptation to dynamic oral microenvironmental changes (e.g., pH fluctuations, salivary rinsing, masticatory stimulation). Artificial intelligence (AI) has transformed the field by integrating materials science, microbiology, and stomatology data. Via machine learning, deep learning, and multi-physics simulation, AI optimizes biomaterial physicochemical properties, decodes microenvironmental signals, constructs precise sensing-response loops, and supports the full chain of material design, performance prediction, and action simulation, advancing treatment from empirical intervention to precision regulation. This systematic review retrieved literature from PubMed, Embase, and Web of Science (January 2016-January 2026) using keywords across three dimensions: AI, biomaterials, and oral microbiome. Following inclusion/exclusion criteria, 99 articles were included. It elaborates on five core mechanisms of AI-driven oral biomaterials (precise oral microbiome analysis, targeted material design/optimization, performance prediction/simulation, targeted delivery/intervention, effect evaluation/dynamic regulation), analyzes their applications in microbiome-targeted biomaterial research and development (R&D) and clinical practice for the four major oral infectious diseases, addresses technical bottlenecks (insufficient targeting specificity and precision of biomaterials, poor stability and durability in complex oral microenvironments, inadequate biofilm disruption capacity, and clinical translation obstacles), and proposes future directions (multimodal design to enhance targeting specificity, structural and component optimization to improve stability/durability, development of multi-mechanism synergistic biofilm disruption strategies, strengthening translational research for clinical application, and deep integration of AI in the full chain of biomaterial R&D). This work provides comprehensive theoretical and practical support for the R&D, optimization, and clinical translation of AI-driven microbiome-targeted oral biomaterials.

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

Meta-Analysis of the Efficacy of Ultrasound-Guided Mammotome Minimally Invasive Surgery and Traditional Open Surgery in the Therapy of Benign Breast Tumors.

ObjectiveTo systematically analyze the efficacy of ultrasound-guided mammotome minimally invasive surgery and traditional open surgery in the therapy of benign breast tumors.MethodsA computerized search retrieved original literature on the therapeutic effects of ultrasound-guided mammotome minimally invasive surgery and traditional open surgery for benign breast tumors from authoritative databases, including CNKI, Wanfang, VIP, Web of Science, PubMed, ScienceDirect, Cochrane Library, and Embase. The search covered from database inception to January 2024, using a strategy of subject terms combined with free terms. The retrieved literature was screened, data were extracted, and quality was evaluated. Meta-analysis was performed using RevMan 5.4 software.ResultsA total of 8 literatures were included in the study, and a total of 1909 patients with benign breast tumors were found from 2018 to 2023. The results of meta-analysis showed that the operation time [MD = -12.79, 95%CI (-14.04, -11.55), P < 0.00001], intraoperative blood loss [MD = -11.55, 95%CI (-14.74, -8.36), P < 0.00001], healing time [MD = -2.73, 95%CI (-4.03, -1.43), P < 0.00001] and complication rate [MD = 0.17, 95%CI (0.12, 0.26), P < 0.00001] was apparently different from traditional open surgery (P < 0.05).ConclusionUltrasound-guided mammotome minimally invasive surgery can effectively shorten the operation time of patients with benign breast tumors, reduce intraoperative blood loss, promote healing, and reduce the risk of complications. The effect is better than that of traditional open surgery.

Humans↗

PubMed2026

Efficacy of current approaches to non-invasive diagnosis of skin cancer and the potential impact of artificial intelligence: A systematic review and meta-analysis.

BACKGROUND: Skin cancer is one of the most prevalent malignancies worldwide, particularly within Caucasian populations. This systematic review and meta-analysis aimed to quantitatively review the current literature on non-invasive diagnosis of skin cancer and evaluate the current evidence to support the use of tools in addition to, or in replacement of clinician face-to-face assessment. METHODS: A literature search was conducted for publications in PubMed, Medline and Embase databases. Articles describing accuracy, sensitivity, specificity and outcomes of their mode of assessment were included. A total of 208 articles met the inclusion criteria. RESULTS AND CONCLUSION: This systematic review and meta-analysis showed that the diagnostic performance of artificial intelligence (AI) in the interpretation of dermatoscopic images was high for melanoma diagnosis, basal cell carcinoma or malignancy, in comparison to dermatoscopic assessment alone by clinicians and experts. Although AI interpretation of images demonstrated higher sensitivity for melanoma diagnosis in comparison to clinical assessment combined with dermatoscopic assessment, it is unclear if this is also the case for basal cell carcinoma and squamous cell carcinoma diagnosis. Reflectance confocal microscopy, a non-invasive high resolution imaging technique, is known to have a high sensitivity for diagnosing cutaneous malignancy, and this may have applications within secondary care. Therefore, AI could help reduce resource burden and aid in clinical assessment, particularly within primary care settings.

Humans↗

PubMed2026

Artificial intelligence in treatment prediction for skeletal Class III malocclusion: A systematic review.

In skeletal Class III patients, treatment options range from orthodontics to orthognathic surgery. Choosing the optimal approach requires a comprehensive clinical evaluation, which may be supported by AI tools. The aim of this study was to assess the performance of AI models in predicting the need for orthognathic surgery and in identifying predictors influencing treatment decisions. A PRISMA-guided electronic database search (PubMed, Web of Science; 2009-2024; English/French) was performed to identify studies using machine learning (ML) or deep learning (DL) on cephalometric and clinical data. After screening and assessment for eligibility, 15 studies were critically appraised. Model performance was summarized using accuracy, sensitivity, specificity, and the area under the curve (AUC). ML algorithms (particularly Random Forest and XGBoost) and DL models (ResNet-based convolutional neural networks (CNNs)) achieved high accuracy for predicting surgical need. Frequently selected predictors included Wits appraisal, ANB angle, the maxillomandibular ratio (Mx/Md), overjet, and the divergence of the lower gonial angle. AI methods show promise for assisting treatment decisions in Class III malocclusion, with Random Forest and XGBoost performing well on tabular cephalometric data and CNNs on imaging. Larger, multicentre datasets and external validation are needed to improve reliability, address bias, and support clinical implementation.

Humans↗

PubMed2026

From fear to empowerment: the impact of employees AI awareness on workplace well-being - a new insight from the JD-R model.

PURPOSE: The primary purpose of the study was to explore the impact of health workers' awareness of artificial intelligence (AI) on their workplace well-being, addressing a critical gap in the literature. By examining this relationship through the lens of the Job demands-resources (JD-R) model, the study aimed to provide insights into how health workers' perceptions of AI integration in their jobs and careers could influence their informal learning behaviour and, consequently, their overall well-being in the workplace. The study's findings could inform strategies for supporting healthcare workers during technological transformations. DESIGN/METHODOLOGY/APPROACH: The study employed a quantitative research design using a survey methodology to collect data from 420 health workers across 10 hospitals in Ghana that have adopted AI technologies. The study was analysed using OLS and structural equation modelling. FINDINGS: The study findings revealed that health workers' AI awareness positively impacts their informal learning behaviour at the workplace. Again, informal learning behaviour positively impacts health workers' workplace well-being. Moreover, informal learning behaviour mediates the relationship between health workers' AI awareness and workplace wellbeing. Furthermore, employee learning orientation was found to strengthen the effect of AI awareness on informal learning behaviour. RESEARCH LIMITATIONS/IMPLICATIONS: While the study provides valuable insights, it is important to acknowledge its limitations. The study was conducted in a specific context (Ghanaian hospitals adopting AI), which may limit the generalizability of the findings to other healthcare settings or industries. Self-reported data from the questionnaires may be subject to response biases, and the study did not account for potential confounding factors that could influence the relationships between the variables. PRACTICAL IMPLICATIONS: The study offers practical implications for healthcare organizations navigating the digital transformation era. By understanding the positive impact of health workers' AI awareness on their informal learning behaviour and well-being, organizations can prioritize initiatives that foster a learning-oriented culture and provide opportunities for informal learning. This could include implementing mentorship programs, encouraging knowledge-sharing among employees and offering training and development resources to help workers adapt to AI-driven changes. Additionally, the findings highlight the importance of promoting employee learning orientation, which can enhance the effectiveness of such initiatives. ORIGINALITY/VALUE: The study contributes to the existing literature by addressing a relatively unexplored area - the impact of AI awareness on healthcare workers' well-being. While previous research has focused on the potential job displacement effects of AI, this study takes a unique perspective by examining how health workers' perceptions of AI integration can shape their informal learning behaviour and, subsequently, their workplace well-being. By drawing on the JD-R model and incorporating employee learning orientation as a moderator, the study offers a novel theoretical framework for understanding the implications of AI adoption in healthcare organizations.

Humans↗

PubMed2026

Failure modes and effects analysis for clinical implementation of online adaptive radiotherapy: A systematic review.

BACKGROUND: The accuracy of radiotherapy is limited by anatomical variations occurring over time scales ranging from sub-seconds to days. Online Adaptive Radiotherapy (OART) addresses this by enabling daily plan adaptation based on real-time imaging. While OART offers improved dose conformity, its dynamic, time-constrained workflow introduces novel failure modes that challenge traditional quality assurance protocols. PURPOSE: This study aims to synthesize the existing literature on Failure Modes and Effects Analysis (FMEA) for OART to systematically catalog risks and identify mitigation strategies. METHODS: A systematic literature search was conducted to identify studies applying FMEA to OART workflows. Eleven studies were included, covering MR-guided (ViewRay MRIdian, Elekta Unity), CBCT-guided (Varian Ethos), and MR-enhanced C-arm linac systems. To address heterogeneity in risk scoring methodologies (e.g., TG-100 10-point scales vs. 5-point rankings), extracted failure modes were harmonized into a standardized three-tier risk classification system (Class I: Low, Class II: Intermediate, Class III: High). RESULTS: A total of 300 unique failure modes were identified, with 49.6 percent classified as high-risk (Class III). Analysis revealed that the majority of high-risk failures were concentrated in the online treatment delivery phase, specifically within human-computer interactions and anatomical contouring steps. CONCLUSIONS: This study supports the development of tailored, robust QA frameworks that prioritize human factors and process consistency to guide safe implementation in diverse clinical settings.

Humans↗

PubMed2026

Experimental validation of an AI-driven digital healthcare platform for oral health behavior and plaque assessment among vietnamese children.

BACKGROUND: Oral health among children in developing countries, including Vietnam, remains a significant public health concern. Innovative approaches leveraging artificial intelligence AI-based digital health platforms may offer effective strategies for managing dental plaque and promoting better oral hygiene behaviors among school-aged children. This study aimed to evaluate the effectiveness of an AI-driven oral healthcare platform (Denti-i Vietnam) in improving oral hygiene and behavioral outcomes among Vietnamese primary school students. METHODS: A total of 204 primary school students aged 8-10 years in Hanoi, Vietnam, participated in this experimental study. Participants were randomly assigned to an intervention group (n = 107), which used the AI-driven oral healthcare platform, and a comparison group (n = 97), which received traditional oral health education via pamphlets. Oral health behaviors, dental plaque levels (Simplified Oral Hygiene Index; OHI-S), and caries indices (dft/DMFT) were assessed at baseline and after the intervention period. RESULTS: The intervention group demonstrated a significant reduction in the OHI-S score compared to baseline (2.49 ± 0.60 to 1.70 ± 0.76, p < 0.001), particularly in the debris component, indicating enhanced plaque control. Notable improvements were also observed in oral hygiene behaviors, including increased frequency of toothbrushing before and after breakfast (p < 0.01) and more frequent parental assistance during brushing (p = 0.03). Furthermore, parental awareness of dental caries significantly increased in the intervention group (p = 0.001). CONCLUSIONS: The AI-driven oral healthcare platform significantly improved both oral hygiene behaviors and plaque control among Vietnamese primary school children. These findings suggest that AI-driven digital health tools can serve as practical and scalable solutions for promoting oral health in developing countries.

Humans↗

PubMed2026

Hysteroscopic platelet-rich plasma and medically assisted reproduction outcomes: a systematic review and SWOT analysis.

BACKGROUND: Platelet-rich plasma (PRP) has been proposed as an adjuvant treatment in reproductive medicine. While most evidence refers to blind intrauterine instillation, subendometrial administration under hysteroscopic guidance allows targeted delivery under direct visualisation. This systematic review aimed to synthesise the available evidence on hysteroscopic PRP administration and its impact on clinical medically assisted reproduction (MAR) outcomes. METHODS: A systematic search was conducted from inception to December 2025 across major databases. Studies were included if they evaluated hysteroscopic PRP administration in women undergoing MAR, comparing reproductive outcomes between treated and control groups. RESULTS: Out of 142 records, 3 studies met the inclusion criteria. Study populations were heterogeneous and included women with refractory thin endometrium and/or a history of implantation failure. Hysteroscopic PRP administration protocols varied in timing, technique, and dosage. In a prospective case-control study, hysteroscopic intraendometrial PRP injection at a depth of 2-3 mm in the four uterine walls, using an ovum aspiration needle, on days 11-13 of the cycle prior to euploid frozen embryo transfer (ET), was associated with higher implantation (IR), clinical pregnancy (CPR), and live birth rates (LBR) compared with standard therapy. Conversely, no significant differences in CPR, miscarriage rate, or LBR were observed in an observational study evaluating a single intraendometrial PRP injection (35-40 mL, 2-3 mm depth), administered via endoscopic needle on days 6-8 of the menstrual cycle preceding frozen ET, alone or after electrical impulse therapy. A randomised controlled trial in women undergoing intrauterine insemination reported a significant improvement in CPR following hysteroscopic subendometrial PRP instillation in the four uterine walls (1.0 mL each). CONCLUSIONS: Current literature on hysteroscopic PRP administration in reproductive medicine is limited, and robust conclusions cannot yet be drawn. Well-designed randomised controlled trials with standardised protocols are needed to clarify its clinical role.

Humans↗

PubMed2026

Molecular Landscape and Advanced Diagnostic Technologies for BRAF Mutations in Cancer: From Quantitative PCR and ddPCR to CRISPR-Based Platforms.

BRAF mutations are key oncogenic alterations across multiple malignancies, including melanoma, thyroid carcinoma, colorectal cancer, non-small cell lung cancer, glioma, and hairy cell leukemia. The most prevalent variant, BRAF-V600E, induces constitutive activation of the MAPK signaling pathway, promoting tumor progression and influencing therapeutic responsiveness. Accurate detection of BRAF alterations is therefore essential for molecular classification, prognostic assessment, treatment selection, and resistance surveillance. This review summarizes the molecular heterogeneity of BRAF mutations and critically evaluates current diagnostic methodologies. Conventional approaches such as allele-specific PCR and Sanger sequencing are compared with advanced quantitative platforms, including high-resolution melting analysis, droplet digital PCR, and next-generation sequencing, with emphasis on analytical sensitivity, mutation coverage, and clinical applicability. Emerging technologies such as CRISPR-based assays, rolling circle amplification systems, and nanoparticle-based biosensors and point-of-care diagnostic platforms are also discussed for their potential to enhance ultra-sensitive detection, particularly in liquid biopsy settings. These emerging tools are highlighted for their potential to enable ultra-sensitive, rapid, and decentralized mutation detection, particularly in liquid biopsy settings. Key challenges, including intratumoral heterogeneity, low allele-frequency variants, FFPE-associated artifacts, and clonal evolution under therapeutic pressure, are examined within a translational framework. In addition, we examine critical barriers to clinical implementation, including standardization, cost, and global accessibility of molecular diagnostics, and outline potential solutions through scalable technologies and decentralized testing strategies. We propose that optimal BRAF testing requires a mutation subclass-informed and clinically integrated strategy combining comprehensive baseline profiling with longitudinal molecular monitoring. Future diagnostic paradigms will likely integrate multi-omics data and artificial intelligence (AI)-assisted interpretation to refine precision oncology implementation. Looking forward, we propose that optimal BRAF testing will require integration of multi-omics profiling with AI-assisted interpretation, enabling automated variant classification, real-time clinical decision support, and improved prediction of therapeutic response and resistance.

Humans↗

PubMed2026

The role of artificial intelligence in the diagnosis and prognosis of traumatic brain injury based on brain CT scans: a systematic review.

Traumatic brain injury (TBI) is a leading cause of emergency department visits and a major contributor to injury-related mortality and long-term neurological disability. Non-contrast computed tomography (CT) is the gold-standard imaging modality for the rapid diagnosis of TBI. Clinical outcomes depend strongly on early detection and prompt acute management. Artificial intelligence (AI)-based models may support faster automated identification of traumatic findings and early prediction of patient prognosis. A systematic literature search was conducted in PubMed/MEDLINE, Scopus, IEEE Xplore, ACM Digital Library, and the Cochrane Library in accordance with PRISMA 2020 guidelines to evaluate AI-based models for automated detection of TBI-related findings on CT and for prediction of clinical outcomes. Risk of bias and applicability were assessed using QUADAS-2 for diagnostic accuracy studies and PROBAST + AI for prediction model studies. Twenty-two studies were included. Sixteen studies evaluated diagnostic tasks and 10 evaluated prognostic outcomes, with four studies contributing to both categories. Diagnostic performance was generally high, with many studies reporting AUC values approaching or exceeding 0.90, particularly for larger lesion volumes.Prognostic performance was more variable, with moderate to high discrimination and substantial heterogeneity. Only 9 studies incorporated independent external validation, and performance was frequently lower in external cohorts. All prognostic model studies were judged to be at high overall risk of bias using PROBAST + AI, and most diagnostic accuracy studies also demonstrated high or unclear risk of bias in at least one QUADAS-2 domain, most frequently in patient selection. AI-based models applied to brain CT demonstrate strong technical performance for both diagnostic and prognostic tasks in TBI. However, most studies relied on retrospective designs and lacked independent external validation which limits models generalizability and raises concern for potential overfitting. Prospective, multicenter studies with standardized methodologies and rigorous external validation are required before widespread clinical implementation.

Humans↗

PubMed2026

Artificial intelligence for anticancer drug discovery from natural products of macroalgae and sponges: A systematic review.

Marine natural products (MNPs) from macroalgae and marine sponges have inspired clinically important anticancer agents, including the cytarabine pharmacophore and the eribulin scaffold, while cyanobacterial dolastatin chemistry supplies the auristatin payloads of several marine-inspired antibody-drug conjugates (ADCs) such as brentuximab vedotin. Artificial intelligence (AI) methods, encompassing both classical machine learning (ML) with hand-engineered features and modern deep learning (DL) with many-layered neural networks, are increasingly supporting key decisions in natural-product anticancer drug discovery, including bioactivity prediction, target identification, absorption, distribution, metabolism, excretion and toxicity (ADMET) filtering, generative analogue design, and the selection of preclinical candidates. DL architectures relevant to this field include graph neural networks, transformer-based molecular generators, diffusion models for protein-ligand docking, and convolutional networks for mass spectrometry, while classical ML contributes interpretable fingerprint-based bioactivity models and molecular networking for dereplication. This review follows a systematic literature review methodology to organize the landscape of AI methods now applied to MNP anticancer discovery, distinguishing ML and DL approaches where relevant, situating them within the chemical context of macroalgal and sponge-derived oncology leads, and critically examining published case studies, including validation level (computational, in vitro, in vivo, clinical). The principal bottleneck for medical translation has shifted partly from algorithmic capability toward data infrastructure and experimental validation. Sparse, heterogeneous, and taxonomically biased bioactivity records limit what current models can learn and reduce the reliability of AI-prioritized candidates entering the preclinical pipeline. A roadmap is proposed that prioritizes open MNP-specific benchmarks, symbiont-aware modeling, and active learning loops with synthesizability and ADMET constraints. These AI workflows may accelerate the prioritization of marine-derived anticancer leads and support earlier, more evidence-based translational decisions in oncology drug development.

Biological Products↗

PubMed2026

Artificial intelligence enabled social robotic interventions (PARO) in Australian dementia care: A systematic review and meta-analysis.

BACKGROUND: Although there is a growing body of research indicating that Personal Robot/Social Robot could be used in various aspects of care for individuals with dementia, little is known about how well these types of interventions work in an actual hospital setting in Australia. AIMS & OBJECTIVES: The objective of the present systematic review and meta-analysis is to assess the effectiveness of PARO-based socially assistive robotic intervention in terms of its effectiveness outcomes towards the reduction of dementia-related behavioural and psychological symptoms in Australian based healthcare settings. METHODS: A systematic search was conducted across five electronic databases, including MEDLINE (PubMed), EMBASE, CINAHL, PsycINFO, and the Cochrane Library, to identify randomised controlled trials (RCTs) investigating PARO-based socially assistive robotic interventions for dementia in Australian healthcare settings. This review was registered with PROSPERO (CRD420251251916) and followed the PRISMA 2020 guidelines. In addition, the Cochrane Risk of Bias tool (RoB 2) was used to evaluate the risk of bias across all studies. Pooled standardised mean differences (SMD) with 95 % confidence intervals (CI) were calculated for agitation, anxiety, and depression. Heterogeneity across studies was evaluated using the I2 statistic. RESULTS: Six RCTs involving 1444 participants were identified for inclusion in this review. AI-enabled socially assistive robotic interventions, specifically the PARO therapeutic robot, significantly reduced agitation and anxiety when compared to standard treatment or control conditions. The pooled analysis showed that agitation [SMD = -0.44 (95 % CI: -0.70, -0.18) p = 0.0008] and anxiety [SMD = -0.59 (95 % CI: -0.91, -0.27) p = 0.0003] were reduced significantly, while the decrease in depression [SMD = -0.44 (95 % CI: -0.95, -0.07) p = 0.09] scores was non-significant among dementia patients receiving PARO-based socially assistive robotic interventions as compared to the control. The overall risk of bias across all six studies was considered low to moderate. CONCLUSION: PARO-based socially assistive robotic interventions may provide preliminary evidence of effectiveness in reducing agitation and anxiety in individuals with dementia in Australian healthcare, but the evidence regarding the reduction of depression remains unclear. Therefore, additional high-quality trials with consistent methodology and extended follow-up will be necessary to determine both the short-term and long-term clinical efficacy and practicality of implementing these interventions into practice.

Humans↗

PubMed2026

Impact of Commercial Artificial Intelligence on Radiologist Reading Time for Pulmonary Nodule Evaluation at Chest CT.

Background Chest CT is a primary method for identifying pulmonary nodules, yet interpreting scans remains time-intensive and demanding. Currently, artificial intelligence (AI) is expected to reduce reading times, but the effect of AI on reporting times in this setting is unknown. Purpose To evaluate the impact of a commercial AI software on radiologists' reading time for pulmonary nodule assessment on chest CT scans within a real-world clinical setting. Materials and Methods This retrospective study included patients who underwent chest CT examinations at a tertiary medical center between September 2021 and May 2024. The study period was divided into pre- and post-AI phases. The primary outcome was radiology reporting time. The association between AI implementation and reporting time was evaluated using a multivariable parametric Weibull shared frailty survival model adjusted for reader function, examination type, patient location, and requesting specialty, with clustering at the radiologist level. Interaction analyses assessed heterogeneity across prespecified subgroups. An exploratory extrapolation estimated projected workforce and financial impact. Results This study included 19 433 patients (mean age, 62 years ± 14.2 [SD]; 21 814 men; 39 323 chest CT examinations, 19 190 pre-AI, and 20 133 post-AI). AI implementation was associated with faster report completion (adjusted hazard ratio, 1.17; 95% CI: 1.14, 1.21; P < .001). The adjusted median reporting time decreased from 21.3 minutes pre-AI to 18.2 minutes post-AI (14.6% reduction; P < .001). Heterogeneity was observed across reader function (P < .001), examination type (P = .048), and requesting specialty (P = .03). The largest relative reductions were observed for CT thorax electrocardiogram-gated examinations (-41.1%; P < .001) and thoracic radiologists (-25.0%; P < .001), whereas emergency department examinations showed increased median reporting time (7.1%; P < .001). At institutional scan volumes (approximately 20 000-22 000 chest CT examinations annually), exploratory modeling suggested an approximate reduction of 0.5 full-time equivalent radiologist workload. Conclusion Implementation of commercial AI-assisted pulmonary nodule assessment on chest CT scans reduced radiologist reporting time in a real-world clinical setting. © The Author(s) 2026. Published by the Radiological Society of North America under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Iwasawa in this issue.

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

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

Alignment strategies in total knee arthroplasty and the patellofemoral joint: A systematic review.

BACKGROUND: Different alignment strategies in total knee arthroplasty (TKA) may affect the patellofemoral joint. Mechanical alignment (MA) is commonly used but may alter native anatomy. Newer strategies such as kinematic alignment (KA), restricted kinematic alignment (rKA), and functional alignment (FA) aim to better restore native joint mechanics. This study provides an overview of the effects of alignment strategies on patellofemoral outcomes after TKA. METHODS: A literature search in July 2025 identified studies comparing patellofemoral outcomes in TKA using different alignment strategies. Of 166 studies screened, eight met inclusion criteria. Three studies were considered medium quality and five studies low quality. RESULTS: KA and rKA more closely restored native trochlear morphology than MA and FA, reducing outliers in the anterior trochlear line compared with MA and FA. MA showed greater trochlear translation, suggesting worse patellar tracking. Trochlear angles were more anatomical in KA and rKA. However, KA was associated with increased internal femoral component rotation and more outliers beyond safe thresholds. FA showed more consistent rotational positioning, generally within safe limits. Lateral patellar shift and intraoperative lateral release rates did not differ significantly between KA and MA. Only one study reported patella-specific clinical outcome scores, finding no difference between FA and adjusted MA. CONCLUSION: KA and rKA better restore trochlear morphology, but risk excessive internal femoral component rotation. FA provides a more balanced approach. MA, while widely used, is linked to altered trochlear shape and worse patellar tracking. The clinical impact of these radiological differences remains unclear, and higher-quality studies are needed.

Humans↗

PubMed2026

Reliability-aware hierarchical learning for Chagas disease screening from 12-lead ECGs: tackling label uncertainty and class imbalance.

Objective.Chagas disease, a neglected tropical disease (NTD) with significant cardiovascular impact, remains underdiagnosed in resource-limited regions. Electrocardiogram (ECG) screening offers a low-cost tool for detecting cardiac involvement, yet algorithm development is challenged by label noise, data scarcity, and the latent nature of infection. This study proposes a robust ECG-based screening framework that explicitly addresses these constraints.Approach.We introduce aReliability-Aware Hierarchical Learningstrategy that calibrates supervision according to data provenance, prioritizing serology-confirmed labels over noisy self-reports. To mitigate data scarcity, we compare a specialized convolutional neural network (CNN) trained from scratch with a transfer learning approach based on a Spatio-Temporal ECG foundation Model (FM). Performance is evaluated across varying data scales, and the representation structure is analyzed to interpret model behavior.Main results.On the official hidden test set of the George B. Moody PhysioNet/Computing in Cardiology Challenge 2025, our approach achieved a Challenge Score of 0.163. We observe that while the specialized CNN performs competitively in data-rich regimes, the FM exhibits superior robustness in extreme low-resource settings. Furthermore, performance reaches a plateau imposed by underlying disease physiology. Bimodal score distributions suggest that models distinguish established cardiomyopathy from indeterminate infection, which remains electrophysiologically indistinguishable from healthy controls.Significance.These findings clarify both the potential and intrinsic limits of ECG-based AI screening for NTD-associated cardiac involvement. Reliability-aware supervision and data-efficient transfer learning provide a practical framework toward scalable and clinically meaningful ECG screening systems in resource-constrained environments.

Humans↗