Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Diagnosis, Computer-Assisted”

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.

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

401 records · Page 3Linked to original sources
PubMed2026

The Role of Artificial Intelligence Combined With Digital Cholangioscopy for Indeterminant and Malignant Biliary Strictures: A Systematic Review and Meta-analysis.

BACKGROUND: Current endoscopic retrograde cholangiopancreatography (ERCP) and cholangioscopic-based diagnostic sampling for indeterminant biliary strictures remain suboptimal. Artificial intelligence (AI)-based algorithms by means of computer vision in machine learning have been applied to cholangioscopy in an effort to improve diagnostic yield. The aim of this study was to perform a systematic review and meta-analysis to evaluate the diagnostic performance of AI-based diagnostic performance of AI-associated cholangioscopic diagnosis of indeterminant or malignant biliary strictures. METHODS: Individualized searches were developed in accordance with PRISMA and MOOSE guidelines, and meta-analysis according to Cochrane Diagnostic Test Accuracy working group methodology. A bivariate model was used to compute pooled sensitivity and specificity, likelihood ratio, diagnostic odds ratio, and summary receiver operating characteristics curve (SROC). RESULTS: Five studies (n=675 lesions; a total of 2,685,674 cholangioscopic images) were included. All but one study analyzed a deep learning AI-based system using a convoluted neural network (CNN) with an average image processing speed of 30 to 60 frames per second. The pooled sensitivity and specificity were 95% (95% CI: 85-98) and 88% (95% CI: 76-94), with a diagnostic accuracy (SROC) of 97% (95% CI: 95-98). Sensitivity analysis of CNN studies (4 studies, 538 patients) demonstrated a pooled sensitivity, specificity, and accuracy (SROC) of 95% (95% CI: 82-99), 88% (95% CI: 72-95), and 97% (95% CI: 95-98), respectively. CONCLUSIONS: Artificial intelligence-based machine learning of cholangioscopy images appears to be a promising modality for the diagnosis of indeterminant and malignant biliary strictures.

Humans↗
PubMed2026

Clinical applications of digital twin technology in In Vitro Fertilisation.

BACKGROUND: Digital twin technology, originating from aerospace and manufacturing industries, has emerged as a transformative tool in healthcare. In vitro fertilisation (IVF) faces persistent challenges including suboptimal embryo selection, unpredictable treatment outcomes, and limited personalisation of protocols. Despite advances in assisted reproductive technology, existing literature exhibits fragmentation: artificial intelligence applications in embryo selection, ovarian stimulation, and endometrial assessment have been developed independently without systematic integration into comprehensive treatment frameworks. Digital twin technology offers unprecedented opportunities to create virtual replicas of biological systems, enabling real-time monitoring, predictive modelling, and personalised treatment strategies. AIM: This narrative review aims to critically examine the current applications of digital twin technology in IVF, evaluate its potential benefits and limitations, synthesize existing evidence into an integrative conceptual model, and identify future directions for implementation in reproductive medicine. METHOD: A comprehensive narrative review was conducted using PubMed, Scopus, Web of Science, and IEEE Xplore databases. A narrative review approach was selected over systematic review to accommodate the heterogeneity of evidence types in this emerging field, including theoretical frameworks, simulation studies, and proof-of-concept implementations that would be excluded from systematic reviews. Search terms included "digital twin," "IVF," "in vitro fertilisation," "assisted reproductive technology," "embryo selection," and "predictive modelling." Studies published between 2015 and 2025 were included, focusing on original research articles, systematic reviews, and proof-of-concept studies describing digital twin applications in reproductive medicine. RESULTS: Digital twin technology in IVF demonstrates significant potential across multiple domains including embryo development simulation, ovarian response prediction, endometrial receptivity modelling, and personalised stimulation protocols. Current applications integrate artificial intelligence, machine learning algorithms, time-lapse imaging, and omics data to create comprehensive virtual models. Early evidence suggests improvements in embryo selection accuracy, ovarian response prediction, and treatment protocol optimization, though large-scale randomized controlled trials remain limited. Implementation challenges include data integration complexity, computational requirements, regulatory considerations, and validation requirements. CONCLUSION: Digital twin technology represents a paradigm shift in IVF practice, offering personalised, predictive, and precision medicine approaches. This review synthesizes existing evidence to propose an integrative conceptual model for digital twin implementation across the IVF treatment spectrum, identifies critical knowledge gaps, and establishes research priorities to advance clinical translation. Despite current limitations, continued advancement promises improved success rates and patient outcomes.

Humans↗
PubMed2026

Higher Rates of PASS and SCB After Arthroscopic Subspine Decompression Are Associated With a Positive Diagnostic AIIS Injection: A Propensity Score-Matched Cohort Study.

BACKGROUND: Hip arthroscopy effectively treats femoroacetabular impingement syndrome (FAIS), but persistent pain may be related to concomitant extra-articular pathology such as subspine impingement syndrome (SSI). Standard diagnosis of SSI often relies on 3-dimensional computed tomography (3D-CT) morphology (Hetsroni type II/III), although this morphology is common in individuals who are asymptomatic and correlates poorly with symptoms. PURPOSE: To compare minimum 2-year clinical outcomes after arthroscopic subspine decompression in patients with concurrent FAIS and type II/III anterior inferior iliac spine (AIIS) morphology, stratified by diagnostic method: 3D-CT morphology alone versus 3D-CT morphology plus a positive ultrasound-guided diagnostic injection. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: This study included patients aged 18 to 55 years with type II/III AIIS morphology who underwent primary hip arthroscopy for FAIS and SSI between January 2021 and November 2023 and had minimum 2-year follow-up. Patients diagnosed by CT morphology alone (CT classification group) were propensity score matched 1:1 to patients with a positive ultrasound-guided AIIS injection (injection group), with 57 patients per group. Matching variables were age, sex, body mass index, lateral center-edge angle, alpha angle, T&#xf6;nnis grade, and Beighton score. All patients underwent arthroscopic subspine decompression. Patient-reported outcomes and rates of achieving the minimal clinically important difference, Patient Acceptable Symptom State (PASS), and substantial clinical benefit (SCB) were compared. RESULTS: Preoperative patient-reported outcome scores were similar between groups (all P > .05). At minimum 2-year follow-up, the injection group had significantly better scores on the modified Harris Hip Score (90.8 vs 84.2), Hip Outcome Score-Activities of Daily Living (88.4 vs 82.4), Hip Outcome Score-Sports Subscale (71.9 vs 64.1), 12-item International Hip Outcome Tool (83.9 vs 76.1), and visual analog scale for pain (1.2 vs 2.0) (all P < .001). Minimal clinically important difference rates were high in both groups, with higher rates in the injection group for modified Harris Hip Score (93% vs 77%; P = .033) and Hip Outcome Score-Activities of Daily Living (91% vs 75%; P = .042). PASS and SCB rates were significantly higher in the injection group across all patient-reported outcome measures (all P < .05). Revision and complication rates were low and did not differ significantly between groups. CONCLUSION: Both groups improved significantly after arthroscopic subspine decompression. However, patients with a positive ultrasound-guided diagnostic AIIS injection achieved higher PASS and SCB rates than those selected by CT morphology alone, suggesting that injection-confirmed SSI may improve patient selection for subspine decompression.

Humans↗
PubMed2026

Privacy, security, and reliability risks of artificial intelligence in healthcare: a systematic review of empirical evidence.

BACKGROUND: Artificial intelligence (AI) is increasingly integrated into healthcare information systems, supporting clinical decision-making, imaging analysis, and predictive modeling. While these applications offer operational and clinical benefits, they also introduce emerging risks to patient privacy, data security, and system reliability. OBJECTIVE: To systematically review empirical evidence on privacy breaches, security vulnerabilities, and misuse associated with AI applications in healthcare settings. METHODS: PubMed, Embase, Web of Science, Scopus, IEEE Xplore, and ACM Digital Library were searched for empirical studies published between January 2015 and November 2025 that evaluated AI use or misuse in clinical diagnosis, treatment, or decision-making. Two reviewers independently screened studies and extracted data using a standardized form. Findings were synthesized narratively due to heterogeneity in study designs, AI methods, and reported outcomes. RESULTS: Of 7,285 records identified through database searches and 205 through citation screening, 22 empirical studies met the inclusion criteria, spanning multiple clinical domains and data modalities, predominantly medical imaging applications. Five recurring threat categories were identified: patient re-identification, membership inference, unauthorized access and adversarial exploitation, input manipulation, and misuse or overinterpretation of AI outputs. Across studies, AI models were shown to encode latent biometric signals across diverse data types, limiting the effectiveness of traditional anonymization and synthetic data approaches. Adversarial attacks and input manipulation were also shown to compromise diagnostic performance and system integrity. CONCLUSION: This systematic review provides empirical evidence suggesting that contemporary AI systems in healthcare introduce privacy and security risks that may challenge traditional assumptions about data protection. These findings underscore the need for privacy- and security-by-design approaches and governance frameworks that address risks across the AI lifecycle.

Humans↗
PubMed2026

The prevalence of isthmic and degenerative lumbar spondylolisthesis: an analysis of 1376 patients.

INTRODUCTION: Typically, spondylolisthesis is an asymptomatic spinal condition that is often captured accidently in radiographic studies. The limited studies reviewing incidence primarily used lateral radiographs, which lack the granularity of advanced imaging. In response, computed tomography (CT) has been recommended to enhance the accuracy of spondylolisthesis diagnosis (degenerative versus isthmic). In the present study, we sought to determine the prevalence of isthmic and degenerative spondylolisthesis using CT imaging. METHODS: We conducted a retrospective study of 1,680 patients who underwent abdominal/pelvic CT scans at a single level-1 trauma center from January 1, 2017, to January 31, 2017. RESULTS: A total of 1,680 CT scans were screened, of which 1,376 patient scans met the inclusion criteria of having undergone complete imaging (axial and sagittal images). The average age of the study population was 57.1 (standard deviation, 18.7) years; 51.1% were female, and 83.2% were Caucasian. The prevalence of isthmic spondylolisthesis was 5.4% (n&#xa0;=&#xa0;71): 3.6% of cases were at the L5-S1 level, 2.1% were at the L4-L5 level, and 0.6% were at the L3-L4 level. The female-to-male ratio was 0.73:1. The prevalence of degenerative spondylolisthesis was higher at 21.5% (n&#xa0;=&#xa0;285), and the level most commonly affected was L4-L5 (11.8%), followed by L5-S1 (9.7%) and L3-L4 (4.6%). The female-to-male ratio was 1.3:1. There was a higher prevalence of degenerative spondylolisthesis in women at L4-L5 (51.2% vs. 35.6%; P&#xa0;<&#xa0;0.001). CONCLUSION: We found that degenerative spondylolisthesis was more prevalent, occurring primarily in older women, between the L4-L5 vertebrae. On the other hand, isthmic spondylolisthesis more commonly occurred within male patients between the L5-S1 vertebrae. Our study is one of the first to recognize a high rate of degenerative spondylolisthesis within the L5-S1 region, highlighting the utility of CT scan to visualize spinal translation. LEVEL OF EVIDENCE: IV.

Humans↗
PubMed2026

Three-Dimensional Fracture Mapping of the Terrible Triad of the Elbow: Morphological Characteristics and Clinical Implications.

BACKGROUND: The morphology of fractures in the terrible triad of the elbow (TTE) is complex, and precise management relies on a profound understanding of this morphology. This study aims to systematically analyze, for the first time, the distribution and morphological characteristics of TTE fracture lines using three-dimensional (3D) imaging technology. METHODS: Clinical data and thin-slice CT scans of 112 patients with TTE from January 2021 to December 2024 were retrospectively included. 3D fracture models were reconstructed using Mimics software. Virtual reduction and standardized alignment were performed using 3-matic software. Fracture lines were mapped onto standard ulnar and radial templates, and 3D fracture heat maps were generated using the E-3D software to demonstrate the high-frequency distribution zones of the fracture lines visually. Statistical analysis was performed using SPSS software (version 21.0, IBM Corp., Armonk, NY, USA). Continuous variables were compared using one-way analysis of variance (ANOVA), and categorical variables were compared using the chi-square test (&#x3c7;2 test). A two-tailed p&#x2009;<&#x2009;0.05 was considered statistically significant. RESULTS: The study revealed distinct patterns in the distribution of TTE fracture lines. In the coronoid process, the fracture "hot zone" presented as an annular high-density band extending from the lateral middle aspect to the tip. In the radial head, an oblique high-density band was observed in the anterolateral quadrant of the articular surface. The radial neck exhibited a circumferential high-density zone, which was most prominent in the anterolateral aspect. Statistical analysis indicated a significant correlation between age and fracture complexity; the proportion of Regan-Morrey type III coronoid fractures and Mason type III radial head fractures was significantly higher in elderly patients (>&#x2009;60&#x2009;years) (p&#x2009;<&#x2009;0.05), suggesting that advanced age is a significant risk factor for complex fractures. CONCLUSION: This study is the first to visually reveal the Collaborative Distribution Patterns of TTE fracture lines using 3D fracture mapping technology. This model provides morphological evidence for understanding the injury mechanism of TTE and offers an anatomical framework that may assist surgeons in individualizing surgical approaches and fixation strategies.

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&#x2009;433 patients (mean age, 62 years &#xb1; 14.2 [SD]; 21&#x2009;814 men; 39&#x2009;323 chest CT examinations, 19&#x2009;190 pre-AI, and 20&#x2009;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&#x2009;000-22&#x2009;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. &#xa9; 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↗
PubMed2025

Artificial Intelligence in Diagnosing Depression Through Behavioural Cues: A Diagnostic Accuracy Systematic Review and Meta-Analysis.

AIM: To synthesise existing evidence concerning the application of AI methods in detecting depression through behavioural cues among adults in healthcare and community settings. DESIGN: This is a diagnostic accuracy systematic review. METHODS: This review included studies examining different AI methods in detecting depression among adults. Two independent reviewers screened, appraised and extracted data. Data were analysed by meta-analysis, narrative synthesis and subgroup analysis. DATA SOURCES: Published studies and grey literature were sought in 11 electronic databases. Hand search was conducted on reference lists and two journals. RESULTS: In total, 30 studies were included in this review. Twenty of which demonstrated that AI models had the potential to detect depression. Speech and facial expression showed better sensitivity, reflecting the ability to detect people with depression. Text and movement had better specificity, indicating the ability to rule out non-depressed individuals. Heterogeneity was initially high. Less heterogeneity was observed within each modality subgroup. CONCLUSIONS: This is the first systematic review examining AI models in detecting depression using all four behavioural cues: speech, texts, movement and facial expressions. IMPLICATIONS: A collaborative effort among healthcare professionals can be initiated to develop an AI-assisted depression detection system in general healthcare or community settings. IMPACT: It is challenging for general healthcare professionals to detect depressive symptoms among people in non-psychiatric settings. Our findings suggested the need for objective screening tools, such as an AI-assisted system, for screening depression. Therefore, people could receive accurate diagnosis and proper treatments for depression. REPORTING METHOD: This review followed the PRISMA checklist. PATIENTS OR PUBLIC CONTRIBUTION: No patients or public contribution.

Humans↗
PubMed2026

SGLF-Net:Staged Global-to-Local Cross-Scale Fusion Network for Colonoscopic Polyp Segmentation.

Polyp segmentation in colonoscopy images plays a pivotal role in computer-aided medical diagnosis and the early prevention of colorectal cancer. However, existing methods often suffer from performance degradation when confronted with extreme polyp scale variation and polyp boundary ambiguity. To address these challenges, we propose the Staged Global-to-Local Cross-Scale Fusion Network (SGLF-Net), which adopts a novel staged global-to-local learning paradigm to progressively refine segmentation from coarse global semantics to fine-grained local details. Specifically, the Global Semantic Perception Stage integrates a Swin Transformer Encoder and a Dynamic Attentive Decoder (DAD) to construct comprehensive multi-scale contextual representations. The Local Detail Refinement Stage employs an Edge-aware Dynamic Attentive Decoder (E-DAD) to enhance structural fidelity and boundary precision through explicit edge-guided supervision. Furthermore, we introduce the Cross Spatial-Scale Feature Aggregation and Reconstitution (CSSAR) module, equipped with hybrid attention mechanisms, to facilitate efficient semantic structural interaction between the two cascaded stages. Extensive experiments on five public benchmark datasets demonstrate that SGLF-Net consistently outperforms state-of-the-art methods in both segmentation accuracy and boundary preservation.

Journal Article↗
PubMed2026

Unraveling a Diagnostic Enigma: A TECPR2 Case Solved Through Multi-Omic Genomics.

TECPR2 is a key regulator of autophagy, encoded by the TECPR2 gene. Pathogenic variants in this gene have been linked to a rare hereditary sensory and autonomic neuropathy with intellectual disability (HSAN9). We report a teenage female with a syndromic intellectual disability disorder associated with neuromuscular abnormalities. Multi-omics analysis including genomics, transcriptomics, and proteomics, together with muscle biopsy from the affected individual, were used in this clinical case. Through trio exome sequencing we identified two heterozygous variants in the TECPR2 gene, NM_014844.4: c.480G>A; p.(Gln160=) and c.2846C>A; p.(Ala949Glu). Both were classified as variants of uncertain significance due to the lack of supporting evidence for pathogenicity. Subsequent long-read sequencing phased the variants and confirmed they were in trans. Additional functional studies using RNAseq and proteomics analyses verified the pathogenicity of the variants. This case study demonstrated the value of a multi-omics assisted analysis, which complemented the traditional phenotype-first approach in reaching a definitive clinical diagnosis.

Humans↗
PubMed2026

Multimodal alignment improves generalizability of genomic biomarker prediction in computational pathology.

Computational pathology models that use digitized histopathology whole-slide images have the potential to become a cost-effective and scalable alternative to molecular assays for the prediction of genomic biomarkers, a key task in precision oncology. However, as new genomic biomarkers are discovered or quantified, large, labeled datasets must be prospectively collected to train new models. To address this challenge, we developed multimodal alignment for biomarker learning and generalization (MARBLE), a multimodal contrastive pretraining strategy that integrates structured biomarker knowledge into representation learning of histopathology images. MARBLE aligns histopathology-derived representations with representations of genomic biomarkers generated by a large language model (LLM) and a protein language model (PLM). This biologically informed alignment enables data-efficient generalization to novel, out-of-distribution biomarkers. Using the MSK-IMPACT cohort of over 40,000 patients across multiple biomarker panel versions, we design experiments grounded in real-world data to demonstrate the value of our proposed approach.

CP: computational biology↗
PubMed2026

Recovery of polysaccharides from marc and pomace through sequential extractions assisted by ultrasound, enzymes and acid maceration.

This study evaluated the pilot-scale recovery of polysaccharides from Vitis vinifera pomace/marc using sequential extraction strategies combining high-power ultrasound (UAE), enzymes (EAE), and acid maceration (AAE). Laboratory-scale trials identified optimal conditions for enzyme dosage and liquid/solid ratio (L/S). Pilot-scale trials demonstrated that the extraction sequence and the processing byproducts influenced extraction efficiency, total soluble polysaccharide in the extract (TSP), and polysaccharide composition. Post-maceration at pH&#xa0;3.2, with/without the maximum enzyme dose after UAE in a L/S of 1.3/1, improved structural polysaccharide extraction from Viura pomace, while Tempranillo marc showed better recovery of pectic families and TSP with UAE&#xa0;+&#xa0;EAE. Separating grape pomace extract (UAE) from the post-maceration stage at pH&#xa0;3.2 produced two extracts: E1, with higher yield (19.9%), enriched in structural polysaccharides and oligosaccharides, and E2, enriched in high and medium molecular weight pectic polysaccharides (58.03%), a low degree of esterification (17.1%) and more complex rhamnogalacturan structures.

Polysaccharides↗
PubMed2026

Implicit and explicit statistical learning in reading: Evidence from a randomized controlled-learning study and computational modeling.

A key challenge in reading acquisition is understanding how learners extract the complex probabilistic mappings between print, meaning, and sound. Statistical learning (SL) theory offers a mechanistic account of how such mappings are acquired, whether implicitly through exposure or explicitly through instruction. We conducted a randomized controlled-learning study in Chinese, a writing system characterized by multiple sub-lexical regularities linking orthography, semantics, and phonology. Ninety-five 2nd-3rd graders with or at risk for dyslexia were randomly assigned to one of three groups: an implicit-SL training group exposed to repeated lexical and sublexical orthography-semantics-phonology associations, an explicit-SL training group receiving the same input plus explicit instruction on the sublexical print-sound mapping, and a no-SL control group. Both SL groups outperformed controls on the characters they were trained on, as well as on untrained characters that required generalization. However, only the explicit group demonstrated abstraction of print-sound mapping to novel items. Neural network simulations further revealed distinct mechanisms supporting implicit and explicit SL, consistent with a dual-system account of reading acquisition. Together, these findings (1) clarify how implicit and explicit learning distinctly support the discovery of statistical structure in written language and (2) underscore the implicit-explicit dual learning mechanism underlying reading acquisition.

Humans↗
PubMed2026

Computational metabolomics at scale: from open data to insight.

Metabolomics data are currently generated at scale thanks to the evolution of technologies that have led to marked improvements in the number of metabolites detected, spanning all chemical classes. These data are increasingly submitted to public repositories for data reuse, integration, and interpretation. Despite the availability of public resources and associated computational tools, the field still lacks a widely adopted, consistent data and analytics infrastructure capable of transforming this wealth of information into scientific insight. Indeed, the metabolomics field is just now scratching the surface of being able to harness the power of new computational technologies. In this review, we summarize discussions from the "Dagstuhl-Seminar 24181 Computational Metabolomics: Towards Molecules, Models, and their Meaning" with a focus on public data availability, open data standards, data and knowledge integration, and education. Our goal is to raise awareness and adoption of the latest open science resources while highlighting key areas needing further development.

Metabolomics↗
PubMed2026

Identifying and Prioritizing Core Components of Relationship Education Programs: a Case Study of an Artificial Intelligence (AI) Assisted Systematic Review.

The field of prevention science seeks to identify and implement effective strategies to address social, emotional, and health challenges. A critical aspect of this endeavor is determining the core components of prevention programs that drive positive outcomes. This article presents a case study utilizing artificial intelligence (AI)-assisted systematic review methods to identify key components of healthy marriage and relationship education programs. Given the growing body of research in this domain, AI tools offer a promising means to enhance the efficiency and accuracy of literature reviews. This study employed AI to screen, code, and validate research articles, demonstrating its effectiveness in expediting systematic reviews while maintaining high accuracy in inclusion screening. This case study involved a systematic review of 22,028 resources (identified from PsycINFO, Academic Search Ultimate, and Google) and a final data set of 268 relevant studies. AI screening was integral in effectively conducting multiple rounds of screening. However, findings also highlight challenges in AI-assisted qualitative data abstraction, underscoring the continued need for human expertise in complex coding tasks. The study contributes to the ongoing discourse on integrating AI into prevention science methodologies and offers insights for optimizing AI applications in systematic reviews.

Artificial Intelligence↗
PubMed2026

Effectiveness and usability of artificial intelligence-powered assistive technologies in Supporting daily activities of children with cerebral palsy: a systematic review.

BACKGROUND: Cerebral Palsy (CP) is the main cause of motor disabilities in childhood, necessitating innovative approaches to rehabilitation and assistive technology (AT). Simultaneously, artificial intelligence (AI) is increasingly being integrated into devices to create more adaptive, personalized, and effective AT. This systematic review aimed to evaluate the effectiveness and usability of AI-powered assistive technologies designed to support daily activities and rehabilitation in children with CP. MATERIALS AND METHODS: Five databases, including Scopus, Web of Science, PubMed, Embase, and IEEE Xplore, were systematically searched, and 23 articles were included in the final analysis. Articles were identified, selected, and categorized into emerging thematic areas based on the primary function and application of the technology. RESULTS: Five key thematic topics were identified: 1) AI-driven motor rehabilitation and gait training for functional mobility; 2) intelligent assessment and monitoring systems for clinical decision support; 3) AI-supported communication, social interaction, and intention recognition tools; 4) gamified and virtual reality-based interventions to enhance engagement and usability; and 5) smart assistive systems supporting daily living and independent mobility. The findings demonstrate a strong trend toward the application of AI technologies in personalized, engaging, and data-driven interventions for children with CP. However, the field is predominantly in the proof-of-concept stage, with limitations including small sample sizes, lack of long-term clinical validation, challenges in user-centered design, and usability for children with CP. CONCLUSION: AI-powered assistive technologies hold significant potential for transforming the care of children with CP by enabling highly personalized and engaging interventions. To actualize this potential, future work must realize that practical application remains challenging owing to limited clinical validation, technological integration, and usability barriers for children with CP. Future research must prioritize user-centered design and multidisciplinary collaboration to ensure that AI and robotic advancements improve the usability and quality of life for children with CP.

Humans↗