SEARCH · Search PubMed

Results for “Clinical decision support system”

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.

1,493 records · Page 2Linked to original sources

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↗

PubMed2025

Enhanced fracture detection on radiographs with AI assistance for clinicians: a systematic review and meta-analysis.

BACKGROUND: Emergency radiographic interpretation for fractures is prone to missed or misdiagnoses. Artificial intelligence (AI) is expected to become a powerful tool to assist clinicians in fracture detection. PURPOSE: A systematic review and meta-analysis was performed to assess whether AI improves clinicians' ability to detect fractures on radiographs. MATERIALS AND METHODS: A literature search was conducted in PubMed, Web of Science, and Cochrane Library for studies published between January 1, 2010, and October 10, 2025. A meta-analysis of diagnostic accuracy studies was performed using a Summary Receiver Operating Characteristic (SROC) curve. The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Subgroup analysis and meta-regression were conducted to explore potential sources of heterogeneity. RESULTS: A total of 26 studies were included . The pooled sensitivity of clinicians increased from 77% (95% CI: 72-81) to 87% (95% CI: 83-90) with AI assistance, while the pooled specificity improved from 88% (95% CI: 85-90) to 92% (95% CI: 89-94). The corresponding AUC values were 0.90 (95% CI: 0.87-0.92) before and 0.95 (95% CI: 0.93-0.97) after AI assistance. Eight studies were rated as high risk of bias. Subgroup analysis and meta-regression identified potential sources of heterogeneity, including fracture location, AI model type, high risk of bias, and reference standards. CONCLUSION: AI assistance significantly improves clinicians' diagnostic performance in detecting fractures on radiographs for extremity and trunk fractures.

Humans↗

PubMed2026

Quantitative assessment of the fingerprint evidential value using machine learning.

Fingerprints as physical evidence have long supported criminal investigation and adjudication. In practice, however, fingerprint identification relies mainly on examiners' experience. Furthermore, expert opinions tend to be categorical, even though the opinions with the same conclusion could differ substantially in evidential strength. To quantitatively assess fingerprint evidential value, this study proposes a machine learning-based framework as an interpretable decision-support tool. A lightweight residual one-dimensional convolutional neural network was constructed, incorporating channel recalibration and a similarity-driven attention mechanism to learn adaptive contribution weights for different matched minutiae (minutiae for short). Controlled experiments revealed that the predicted evidential value increased with the number of minutiae and was significantly influenced by the quality of minutiae. With 10 minutiae, the mean predicted scores were 4.49, 7.00, and 9.09 for blurred, moderately blurred, and clear minutiae, respectively. Multiple regression analysis indicated that replacing a pair of blurred minutiae with a pair of clear minutiae increased the score by 0.492, whereas replacing it with a pair of moderately blurred minutiae increased the score by only 0.216. By mapping predicted scores to graded levels of evidential strength, the framework contributes to a paradigm shift from categorical expert opinions to graded ones, helping courts evaluate fingerprint evidence more scientifically.

Humans↗

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↗

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

Artificial Intelligence Technologies in Nursing Clinical Decision-Making: An Umbrella Review.

AIM: To describe contemporary peer-reviewed literature on artificial intelligence in nurses' clinical decision-making. METHODS: An umbrella review of literature reviews. DATA SOURCES: Four major databases were searched for reviews published between 2019 and 2024. RESULTS: Sixteen literature reviews reported on 965 nursing artificial intelligence primary studies. The studies focused on technology development and emerging performance evaluations, whilst real-world testing or implementation in nursing clinical settings was rare. Rigorous comparative analyses were lacking. While artificial intelligence demonstrates promise in decision-making, challenges such as a lack of controlled studies, algorithmic bias, limited reproducibility and insufficient clinical trials hinder its practical impact. Ethical concerns, transparency and patient data privacy issues pose barriers to AI integration in nursing practice. Ethical and legal guidelines for patient privacy are needed and should be taught along with AI literacy training for nurses. CONCLUSIONS: Artificial intelligence has the potential to enhance clinical nursing decision-making, although evidence is limited by too few examples of nurse participation during development. Underutilisation in administrative nursing functions hinders implementation. Nurses should assume a central role in the design and development of AI applications to ensure that these technologies address the realities of nursing practice. With such improvements, artificial intelligence can transform nursing practice, improve nurses' clinical decision-making and ultimately enhance consumer healthcare outcomes. PATIENT OR PUBLIC INVOLVEMENT: No Patient or Public Involvement. REPORTING METHOD: While there is no reporting checklist for umbrella reviews, the PRISMA guide for systematic reviews was followed.

Artificial Intelligence↗

PubMed2026

Subacute and long-term changes in cognitive functioning after administration of classic psychedelics, MDMA and ketamine: A systematic review of clinical and preclinical evidence.

Psychedelic agents induce a window of heightened neuroplasticity that extends beyond acute intoxication, during which neural circuits are more amenable to change. This period may facilitate changes in cognition relevant to the treatment of psychiatric disorders. This systematic review synthesised clinical and preclinical evidence of subacute and long-term (≥1 day) effects of classic and non-classic psychedelics on cognition. MEDLINE, EMBASE, APA PsycInfo and Web of Science were searched to identify human and animal studies investigating psychedelics and cognition (executive function, attention, decision-making). Sixty-seven (47 clinical, 20 preclinical) articles met inclusion criteria. Psilocybin demonstrated the most consistent evidence of subacute and longer-term cognitive improvement, particularly in cognitive flexibility and attention. Ketamine showed enhancement across cognitive domains, although findings were heterogeneous. LSD and DMT showed no consistent subacute changes, while MDMA was associated with transient cognitive impairments that resolved within days. Risk of bias assessments revealed selective outcome reporting, poor reporting of missing data and inadequate methodological detail, limiting the confidence of findings. Current evidence provides preliminary support for subacute changes in cognition following administration of select psychedelic agents. Cognitive improvements were more frequently seen in psychiatric populations than healthy subjects, which may reflect a remediation of existing cognitive deficit rather than enhancement above normal functioning. Adequately powered, controlled studies with standardised reporting of cognitive outcomes are required to determine the magnitude, durability and clinical relevance of psychedelic-associated cognitive change.

Hallucinogens↗

PubMed2026

Contemporary surgical decision-making for hallux valgus and hallux rigidus in Switzerland: A national cross-sectional survey using standardized clinical scenarios.

BACKGROUND: Surgical management of hallux valgus and hallux rigidus is influenced by deformity severity, surgeon training, and evolving techniques. Previous surveys in Australia (2012), Switzerland (2015), and Israel (2023) using identical hypothetical cases demonstrated marked regional differences and a recent rise in minimally invasive Chevron-Akin (MICA). Whether these advances have altered contemporary Swiss practice remains unclear. METHODS: An electronic survey replicating the original questionnaire was distributed to members of the Swiss Foot and Ankle Society. Three standardized clinical cases were presented: mild hallux valgus, severe hallux valgus, and hallux valgus et rigidus. Respondents selected nonoperative versus operative management and specified procedures and fixation methods. Demographics, subspecialty training, and surgical volume were recorded. Current results were compared with prior Swiss data to assess temporal change. RESULTS: Eighty surgeons completed the survey (94% foot and ankle specialists). For mild hallux valgus, 87.7% recommended surgery; Scarf osteotomy remained most common (49.4%), followed by Chevron (21.0%) and Minimally Invasive Hallux Valgus correction (14.8%). Minimally Invasive adopters were predominantly mid-career (83% aged 41-50), high-volume surgeons. For severe hallux valgus, 95.1% favoured surgery; MTPJ arthrodesis was preferred (50.6% isolated; 11.1% with Lapidus), while Minimally Invasive Hallux Valgus correction was rarely chosen (2.5%). In hallux valgus et rigidus, 96% selected MTPJ fusion, most commonly plate-and-screw fixation (45.1%). Compared with 2015, fixation strategies evolved, yet procedure selection remained largely unchanged. CONCLUSION: Despite global expansion of minimally invasive bunion surgery, Swiss surgeons continue to favour established open techniques, particularly Scarf osteotomy and fusion-based strategies. Adoption of MIS remains limited and concentrated among high-volume, mid-career specialists, indicating a cautious national diffusion pattern. LEVEL OF EVIDENCE: IV, survey study.

Hallux Valgus↗

PubMed2026

Toward real-time quantification of driving risks: a systematic review and research agenda of risk field theory.

In complex traffic systems, driving risk often evolves in a continuous and progressive manner prior to crash occurrence. How to effectively represent and analyze such latent risk states remains a central challenge in traffic safety research. In recent years, risk field-based approaches have introduced spatial and spatiotemporal continuous modeling paradigms, providing new perspectives for characterizing the distribution of traffic risk and its dynamic evolution. Motivated by the rapid growth of this research area and the lack of a systematic synthesis, this paper presents a comprehensive review of studies applying risk field theory to driving safety and traffic risk analysis. Following the PRISMA guidelines, relevant literature was collected through multi-database searches and analyzed using a combination of bibliometric analysis and qualitative review. The review systematically summarizes the theoretical foundations, modeling elements, data sources, analytical methods, and application domains of risk field-related research. Particular attention is given to studies that conceptualize traffic risk as a continuous field, complemented by a broader review of traffic risk factor literature to identify key elements and analytical dimensions involved in risk field modeling. On this basis, the paper synthesizes research progress in major application areas, including traffic safety state representation, driving behavior analysis, traffic conflict assessment, and autonomous driving and human-machine cooperative systems. Differences and commonalities among existing studies are compared in terms of modeling strategies, data support, and application scenarios. Through this systematic review, the paper clarifies the main research themes and methodological trends of risk field-based studies, providing a structured framework for understanding the evolution and application of this approach and offering methodological insights for risk perception modeling and safety-oriented decision support in intelligent transportation systems (ITS).

Humans↗

PubMed2026

Prognostic Value of Frailty in Aortic Surgery: A Systematic Review and Meta-Analysis Comparing Frailty Assessment Tools.

BACKGROUND: Frailty is increasingly recognized as an important determinant of outcomes after aortic vascular surgery, but assessment methods vary substantially and the optimal tool for risk stratification remains uncertain. This systematic review and meta-analysis evaluated the prognostic value of preoperative frailty and compared the predictive performance of different frailty instruments in aortic surgery. METHODS: PubMed, Embase, and Cochrane Library were searched from inception to April 27, 2026. Eligible studies included patients undergoing open, endovascular, or hybrid aortic procedures involving abdominal, thoracic, thoracoabdominal, arch, and proximal aortic diseases, including aneurysms and dissections, assessed frailty preoperatively, and reported postoperative outcomes. RESULTS: Thirty studies comprising 419,459 patients were included. Frailty was associated with higher early mortality (odds ratio [OR] 2.20; 95% confidence interval [CI] 1.54-3.14) and late mortality (hazard ratio 2.18; 95% CI 1.64-2.90). Frail patients also had increased risks of major complications (OR 2.52; 95% CI 1.22-5.19), acute kidney injury (OR 1.64; 95% CI 1.34-2.02), and nonhome discharge (OR 5.50; 95% CI 3.05-9.92). Associations were consistent across surgical approaches and aortic segments. Judgment-based or phenotype-like tools yielded higher effect estimates than deficit-accumulation indices, although differences were not statistically significant; among index-based tools, Modified Frailty Index (mFI)-11 outperformed mFI-5. CONCLUSION: Preoperative frailty strongly predicts mortality, morbidity, and loss of functional independence after open, endovascular, and hybrid aortic surgery across different aortic segments and pathologies, including aneurysmal and dissecting aortic disease. Routine frailty assessment may improve risk stratification and perioperative decision-making.

Humans↗

PubMed2026

A systematic review of human avoidance learning: Cognition, computation, and methods.

Avoidance behaviour is fundamental for survival but can become maladaptive in clinical conditions. A large body of literature has accumulated on the dynamics of human avoidance learning. However, current theories and overviews do not provide an exhaustive account of this evidence. In this systematic review, we identify N = 116 studies on human avoidance learning. We analyse these studies with the goal of distilling robust empirical phenomena as a basis for theory-building, and examine their diagnostic value in differentiating between competing theories. We find that the evidence is difficult to reconcile with foundational two-factor and classical safety-signal accounts, and most strongly supports expectancy- and inference-based views, in which avoidance responses are selected with respect to represented consequences. At the same time, no current framework provides a complete account of the evidence: several findings point to an additional role for operant valuation, Pavlovian influences, and contextual or latent-state control over the expression of avoidance. Methodologically, we observe that the problem setting in the most common experimental paradigms is radically simpler than real-world avoidance and therefore unlikely to expose the limits of inferential or reflective mechanisms. Consequently, we argue that paradigms with greater computational demands and more realistic action affordances are required to identify the mechanisms underlying avoidance learning. Collectively, these insights provide a foundation for theoretical refinement, computational modelling, and methodological innovation, with implications for advancing interventions targeting maladaptive avoidance.

Humans↗

PubMed2026

Improved quality of life and prolonged survival with add-on homeopathic treatment in patients with non-small cell lung cancer: a prospective, randomized, placebo-controlled, double-blind, three-arm, multicenter study.

BACKGROUND: Alongside conventional anticancer treatment, add-on homeopathy might help to alleviate adverse effects of conventional therapy. AIM: The aim of this study was to replicate previous studies on the effect of adjunctive homeopathy on quality of life (QoL) and survival in non-small cell lung cancer (NSCLC) patients. METHOD: In this prospective, randomized, placebo-controlled, double-blind, three-arm multicenter phase III study with quadruple-checked data analysis, we investigated the potential effects of an add-on homeopathic treatment compared to placebo in patients with stage IV NSCLC in terms of QoL. Ninety-eight received either individualized homeopathic medicinal products (HMPs; n = 51) or placebo (n = 47) in a double-blinded fashion. Fifty-two control patients without homeopathic treatment were only observed in terms of their survival rate. The ingredients of the various HMPs were mainly prepared of plant, mineral, or animal origin. The data entry and statistical analysis were subject to an exceptional quadruple-checked data analysis process. The analysis presented in this article was inspired by our earlier report of this trial published in The Oncologist in 2020, which was retracted by that journal in November 2025 after two corrections; a majority of the co-authors disagreed with this decision. The present article is based on the same trial dataset but was deliberately designed to highlight the unique research methodology: design and preparation by a lead statistician, data entry, data clearing and independent statistical evaluation were performed in four mutually independent steps, reporting follows the CONSORT statement, and the interpretation of the findings has been reframed conservatively. RESULTS: Global health status (QoL) was higher in the homeopathy group than in the placebo group after 9 weeks and after 18 weeks (p < 0.001). With the exception of cognitive functioning at 9 weeks and of pain, diarrhea and financial difficulties at 9 weeks, all functional and symptom scales of the EORTC QLQ-C30 favored the homeopathy group (p < 0.001 for the multivariate comparisons), with between-group differences exceeding the threshold of 10 points that is generally regarded as clinically meaningful. Median survival time over the 730-day observation period was 435 days in the homeopathy group, 257 days in the placebo group (p = 0.010), and 228 days in the non-randomized control group (p < 0.001); the corresponding 2-year survival rates were 45.1%, 23.4%, and 13.5% (homeopathy vs. placebo p = 0.020; homeopathy vs. control p < 0.001). The difference between the placebo group and the non-randomized control group was not statistically significant (p = 0.154). CONCLUSION: In this trial, add-on homeopathy was associated with better quality of life across most functional and symptom domains, with clinically meaningful effect sizes congruently to a previous open study. Survival time was significantly longer in the homeopathy group compared to both the placebo and control groups. Independent replication, ideally within contemporary immuno-oncological treatment regimens is required. TRIALS REGISTRATION: ClinicalTrials.gov; No.: NCT01509612; January 7, 2012.

Humans↗

PubMed2026

An exploratory analysis of decision-making in population affinity estimation among forensic anthropology practitioners in the United States.

Population affinity estimation in forensic anthropology often involves the integration of multiple pieces of information, including visual (nonmetric) and metric data. This study examines how practitioners interpret and synthesize visual and metric information and their decision-making processes. A Qualtrics survey was developed using two cases: Case 1 presented clear nonmetric signal but ambiguous metric signal, while Case 2 showed more ambiguous nonmetric signal but clear metric signal. Practitioners were asked to estimate population affinity based on visual assessment, Fordisc data, and provide a final, integrated assessment. A total of 22 valid survey responses were received, with the majority of survey respondents reporting more than 10 years of forensic anthropology experience and holding a PhD degree. Results showed that there is substantial variability in Fordisc use and interpretation. Across both cases, participants synthesized conflicting visual and metric information, converged toward the stronger signal, and came to more consistent final estimates relative to the more ambiguous input. These findings highlight variability in practitioner decision-making but suggest that integration of nonmetric and metric information in population affinity estimation can moderate decision-making uncertainty. The results have implications for forensic anthropology education, training, and proficiency testing.

Humans↗

PubMed2026

Longitudinal functional trajectory and surgical outcomes after intracranial meningioma resection: implications for surgical decision-making in older patients.

OBJECTIVE: As the population ages, meningiomas are increasingly encountered in older patients, yet longitudinal functional outcomes following surgery across age groups remain incompletely characterized. This study evaluated age-related differences in clinical and tumor characteristics, functional trajectory, and surgical outcomes. METHODS: This was a retrospective cohort study of 396 consecutive patients who underwent surgery for intracranial meningiomas at a single academic center between January 2023 and September 2025. Patients were stratified into 5 age groups (< 65, 65-69, 70-74, 75-79, and ≥ 80 years). Neurological deficits and Karnofsky Performance Status (KPS) were assessed preoperatively, at discharge, and at last follow-up. Logistic regression analyses identified predictors of prolonged length of stay (LOS) (> 5 days) and poor functional outcome at discharge (KPS < 80). RESULTS: Older patients presented with greater comorbidity burden, larger tumors, and lower preoperative KPS (all p < 0.05), while gross-total resection was achieved at comparable rates across all age groups (p = 0.504). A clinically meaningful inflection point was observed around age 75 years, with KPS < 80 at discharge rising from 7.4% and 9.7% in the < 65-year and 70- to 74-year subgroups and to 36.2% and 57.1% in the 75- to 79-year and ≥ 80-year subgroups (p < 0.001), and median LOS increased from 4 days in the younger groups to 9 and 7 days in the 75- to 79-year and ≥ 80-year groups (p < 0.001). However, recovery rates among patients who experienced functional decline at discharge were comparable across age strata. On multivariable analysis, independent predictors of prolonged LOS were age ≥ 75 years (OR 2.31, p = 0.019), diabetes mellitus (OR 2.85, p = 0.004), posterior fossa location (OR 2.1, p = 0.008), tumor diameter (OR 1.33, p < 0.001), postoperative edema (OR 2.58, p = 0.015), and neurosurgical complications (OR 3.18, p = 0.002). Independent predictors of poor functional outcome at discharge were age ≥ 75 years (OR 5.84, p < 0.001), lower preoperative KPS (OR 2.8, p < 0.001), posterior fossa location (OR 3.72, p = 0.003), neurosurgical complications (OR 3.56, p = 0.008), and recurrent meningioma (OR 2.89, p = 0.025). Among 70 endoscopic endonasal approach patients, higher preoperative deficit burden and subtotal resection rates were observed compared to open craniotomy, though overall functional outcomes were comparable. CONCLUSIONS: Surgical risk in meningioma resection increases from age 75 years onwards, yet recovery capacity following initial functional decline remains similar across all age groups. Preoperative functional status, tumor location, comorbidity burden, and recurrence history should guide surgical decision-making rather than age alone.

Humans↗

PubMed2026

Automated CEAP Classification of Venous Duplex Reports Using Multimodal Artificial Intelligence.

OBJECTIVE: To develop and internally validate a prototype multimodal artificial intelligence system for automated CEAP (Clinical, Etiological, Anatomical and Pathophysiological) classification of venous duplex ultrasound (VDUS) reports, integrating natural language processing of free-text components with computer vision analysis of hand-drawn anatomical diagrams. METHODS: Single centre retrospective observational study using routinely collected clinical data. One thousand consecutive venous duplex ultrasound reports from Cambridge University Hospitals NHS Foundation Trust, UK (July 2024 - May 2025) were labelled according to the CEAP classification, excluding the Etiological component, which could not be reliably determined from duplex reports alone. Transfer learning was applied using ClinicalBERT for text and MobileNetV3 for diagrammatic data. Clinical classes were predicted from request line text. Text- and image-based pathophysiological models were developed for four anatomical territories (Great Saphenous Vein, Small Saphenous Vein, Deep system, Perforators), combined using late fusion with probability averaging. RESULTS: The clinical CEAP model achieved accuracy of 0.91, macro-F1 of 0.82, and macro-AUC of 0.98. Pathophysiological prediction varied, with text models broadly outperforming image models. Fusion yielded heterogeneous benefits, improving SSV performance but reducing Deep system accuracy. The performance of the final pathophysiological CEAP fusion models varied across anatomical territories: accuracy ranged from 0.70-0.92 and macro-AUC from 0.80-0.92. CONCLUSION: This study demonstrates the feasibility of automated CEAP classification from VDUS reports. Despite class imbalance affecting minority class predictions, the strong discriminatory performance validates this multimodal ML model for extracting clinically meaningful information from real-world data. This approach offers potential, pending external validation, to streamline vascular services through automated triage and guideline-compliant decision making.

Artificial intelligence↗

PubMed2026

Cost-Effectiveness and the Economics of Genomic Testing and Molecularly Matched Therapies.

Cost-effectiveness analysis of precision oncology can help guide value-driven care. Next-generation sequencing is increasingly cost-efficient over single gene testing because diagnostic algorithms require multiple individual gene tests to determine biomarker status. Matched targeted therapy is often not cost-effective due to the high cost associated with drug treatment. However, genomic profiling can promote cost-effective care by identifying patients who are unlikely to benefit from therapy. Additional applications of genomic profiling such as universal testing for hereditary cancer syndromes and germline testing in patients with cancer may represent cost-effective approaches compared with traditional history-based diagnostic methods.

Humans↗

PubMed2026

Behaviourally informed text message reminders to increase cervical screening attendance in people with severe mental illness: the OPTIMISE pilot randomised controlled trial.

OBJECTIVES: This study assessed the feasibility of both the delivery and evaluation of 'enhanced' (behaviourally informed) text message reminders containing links to existing co-designed resources supporting decision-making for people with severe mental illness (SMI) regarding attendance of cervical screening. DESIGN: A pilot randomised controlled trial (RCT). SETTING: 13 General Practice (GP) practices in London were recruited. PARTICIPANTS: GP practices identified people with SMI aged 24-64 years who were overdue cervical screening. Target sample size was 120 participants (60 per arm) based on existing guidance for pilot trials. INTERVENTION: In March 2025, participants were randomised (1:1) to receive either the enhanced (intervention) or the standard (control) SMS reminder. PRIMARY AND SECONDARY OUTCOME MEASURES: 18 weeks later, feasibility outcomes were collected (primary outcomes) and data analysis for a definitive RCT was rehearsed (secondary outcome). RESULTS: Of the 150 participants across 13 GP practices that were randomised (n=75 per arm), 132 (88%) texts delivered (intervention n=64/75 (85%), control n=68/75 (91%)). 10 practices (76.9%) provided follow-up data for 102 participants (intervention n=50, control n=52). Five participants (intervention n=4, control n=1) attended screening within the trial period. Participant survey response rate was low (9/132 (7%), intervention n=5, control n=4). Both SMS messages were low cost, with the intervention SMS a 50% higher cost to deliver (7.5p vs 5p per SMS). Primary feasibility measures of recruitment rate of GP practices (27%), retention of GP practices (77%) and participants (100%), SMS delivery (88%) and data completeness (64%) indicated viability, although survey response rate (7%) did not. CONCLUSIONS: Achieving adequate recruitment and retention, data completeness and comparable groups is viable with some amendments, although an alternative method is required to assess fidelity. Behaviourally informed SMS reminders are feasible to deliver to people with SMI, although it is uncertain if the extra resources are accessed and used. With changes to data collection, a definitive trial could be feasible. Given the low observed cervical screening attendance, additional intervention is needed for this group. TRIAL REGISTRATION NUMBER: ISRCTN12558681.

Humans↗

PubMed2026

Identification of molecular subtypes in clear cell renal cell carcinoma based on chromatin regulators and tumor immune microenvironment profiling.

In the histological classification of renal cell carcinoma, clear cell renal cell carcinoma (ccRCC) accounts for the highest proportion and is the most common subtype. Despite advances in management, it continues to be associated with considerable incidence and mortality. Although surgery and systemic therapies are available, their efficacy is constrained by pronounced intratumoral heterogeneity and treatment resistance. Identifying robust biomarkers and clarifying the underlying biological mechanisms are therefore essential to improving diagnosis, risk stratification and therapeutic decision-making. In this work, we identified two ccRCC molecular subtypes displaying divergent chromatin regulator (CR) profiles and different clinical prognoses. Using the genes differentially expressed between these subgroups, we constructed a CR-related score (CRS) that effectively stratified patients according to survival. More analysis concluded that the low expression of CR was more linked with the immune-activated tumors, which encompassed the immune pathway enrichment, as well as the elevation of numerous immune cell subtypes. Moreover, elevated CRS was associated with improved immunotherapy responsiveness. Drug-sensitivity analyses nominated several candidate agents, and SMARCD3 knockdown in 786-O cells inhibited proliferation and migration and reduced sensitivity to masitinib. Collectively, these findings support the prognostic and therapeutic relevance of CR-related states in ccRCC and provide a framework for future experimental validation of chromatin-regulated tumor-immune interactions.

Humans↗