Biology Methods and Protocols

Background Endoscopic pituitary surgery involves navigating high-stakes anatomy where complications, such as carotid artery injury, cause devastating morbidity. While computer vision AI offers potential for real-time anatomical recognition to mitigate these risks, successful translation requires rigorous human-factors and performance evaluation. We present the iterative development and preclinical evaluation of a surgeon-controlled, real-time AI-assisted navigation system. Methods Guided by IDEAL Stage 0 and DECIDE-AI frameworks, the study was conducted in two phases. Phase 1 was an exploratory study where surgeons used the system during high-fidelity simulated surgery and provided feedback via "Think Aloud" protocols and surveys. Following prototype iteration, a Phase 2 randomized crossover comparative trial was conducted with 19 neurosurgeons (15 trainees, 4 experts) performing high-fidelity simulated tumour resections with and without AI assistance, separated by a minimum 2-week washout. The primary outcome was surgical technical performance (OSATS). Workload, educational value, usability, trust, and implementation outcomes were also assessed. Results Phase 1 informed hardware, model, and interface refinements, including optimized pedal-controlled overlays and prediction confidence metrics. In the comparative trial, AI assistance significantly improved overall technical performance (OSATS 19.79+/-4.06 vs. 17.32+/-4.11; p=0.027). This gain was experience-dependent; AI significantly augmented trainee performance (19.20+/-3.76 vs. 16.60+/-3.78), narrowing the proficiency gap, while expert performance remained high and stable. 100% of participants identified the system as a useful training tool. However, subjective workload was significantly higher in the AI arm (SURG-TLX 26.42+/-9.56 vs. 22.26+/-7.81; p=0.014). Despite this, usability (SUS 75.13+/-14.31) and implementation feasibility, acceptability, and appropriateness scores were consistently high (means >4.4/5). Conclusions This study provides a stepwise process for real-time AI development using pituitary surgery as a high-stakes exemplar. The refined surgeon-centric AI system improves training and technical performance, particularly for trainees. Next steps involve first-in-human studies and further exploration of longer-term human factors such as over-reliance, cognitive overload mitigation and trust calibration.

Background: Endoscopic endonasal transsphenoidal surgery (EETS) requires navigation around neurocritical anatomy. Today, artificial intelligence clinical decision support systems (AI-CDSSs) can orientate surgeons, but clinician trust in AI remains unclear, limiting safe deployment. This study evaluates how modifiable design affects trust and performance in a real-world pituitary surgery AI-CDSS. Method: Online, 70 clinicians with pituitary surgery experience were randomised evenly to a Basic or Enhanced AI-CDSS which outline the sella on EETS operative video. The Enhanced group additionally received explanation of the model and previous publications, alongside confidence labels depicting outline reliability. Both groups annotated the sella on six video clips, first alone then with the optional AI-CDSS. Clips were ordered by declining AI performance, except for the final clip. Self-reported trust was measured using a 1-7 scale after each annotation, and performance was the DICE overlap between user annotations and the ground truth. Comparisons used Mann-Whitney U and permutation analysis. Results: Sixty-four participants (91%) finished the exercise (31 Basic, 33 Enhanced). When AI performed best, median trust was 5.00 in both arms (U=559, p=.521). However, when AI performed worst, trust was significantly lower for the Enhanced group (3.00 vs 3.67, U=668, p=.035), sustained in the final clip (3.67 vs 4.33 U=687, p=.019). User performance improved with the AI-CDSS, but with no significant difference between the groups on the best or worst AI performing clips. Nevertheless, for the best AI, senior clinicians had higher median performance in the Enhanced group (0.95 vs 0.90, U=75, p=.066). There was also less dispersion in the Enhanced group when AI was inaccurate (IQR: 0.07 vs 0.21, p=.004). Conclusion: Interface design can improve trust calibration in a surgical AI-CDSS and may increment performance in seniors when AI is accurate, and consistency when AI is inaccurate. In future, these features may form important safety checks during translation to the operating room.

Skin cancer requires early detection for improved survival rates. Most existing methods rely on deep learning based image classification, which is affected by visual similarity among lesions. Fewer studies use Gene Expression (GE) analysis, which captures molecular characteristics but lacks structural and visual details. To overcome limitations of individual modalities, this paper proposes a multimodal framework integrating dermoscopic images and GE profiles for skin cancer classification. EfficientNet and logistic regression are used for image based analysis and genomic skin lesion profiling, respectively, followed by fuzzy rule based decision systems to reduce uncertainty within individual modalities. Finally, fuzzy fusion combines predictions from both modalities using uncertainty based weighting of classifier outputs. The experimental findings show that both the image based and GE based classification models individually achieved accuracies of nearly 92%. However, the integration of prediction results through the proposed fuzzy fusion strategy further enhanced the classification performance, achieving an overall accuracy of 94.25%. The results obtained outperform contemporary methods, highlighting the effectiveness of combining complementary multimodal information compared with single modality approaches.

High-frequency physiological monitoring in ICUs can identify impending deterioration hours before clinical recognition yet extracting reliable early-warning signals from noisy vital-sign streams remains challenging. We present SIgnose, an interpretable prediction framework for early detection of abnormal shock index (SI), built from routinely monitored vital signs using physiologic variability and nonlinear time-series features. SIgnose was developed on the eICU Collaborative Research Database and externally validated on the MIMIC-III adult database and a pediatric SafeICU cohort (AIIMS New Delhi), with additional prospective validation in the pediatric ICU. We benchmarked three representation strategies: (i) engineered physiologic variability and nonlinear time-series features, (ii) deep learning, and (iii) Llama-3.1-8B embeddings with low-rank adaptation. Physiologic variability features consistently demonstrated superior cross-cohort generalization. The final model used 3,970 features from five vital signs to predict abnormal SI up to 8 hours ahead, achieving AUROC 0.861 (95% CI 0.859-0.863) and AUPRC 0.927 (95% CI 0.925-0.929) on eICU. External validation yielded AUROC 0.870 (95% CI 0.863-0.876) and AUPRC 0.935 (95% CI 0.930-0.940) on MIMIC-III, and AUROC 0.875 (95% CI 0.863-0.888) and AUPRC 0.915 (95% CI 0.898-0.930) on SafeICU; prospective pediatric validation (n = 88) achieved AUROC 0.885 (95% CI 0.868-0.902) and AUPRC 0.911 (95% CI 0.882-0.936). SHAP interpretability analysis identified heart rate variability, respiratory trend dynamics, and multi-scale blood pressure variability as key early-warning signatures. These findings establish SIgnose as a reproducible, low-compute, early-warning framework and demonstrate that physiologic variability features provide robust, generalizable representations for early deterioration detection across adult and pediatric critical care.

Machine learning (ML) has emerged as a transformative technology across biomedical and life science sectors, with applications spanning drug discovery, medical imaging, genomics, and clinical decision support (Goecks et al., 2020; Patel et al., 2020). Despite exponential growth in ML-related publications, from fewer than 100 articles in 2003 to nearly 25,000 by 2021 (NCBI, 2022), adoption among industry professionals remains uneven and sector-dependent. Understanding what drives or inhibits this adoption is critical for organisations seeking to leverage ML capabilities in research and clinical practice. Technology adoption in organisational contexts has been extensively studied through the Technology Acceptance Model (TAM), originally proposed by Davis (1989) and subsequently extended to incorporate external variables influencing perceived usefulness (PU) and perceived ease of use (PEU) (Venkatesh & Davis, 1996). While TAM has been applied across multiple industries, its application within biomedical and life science contexts remains limited, and the industry-specific factors that shape ML acceptance in this sector have not been systematically examined. Two external variables are particularly relevant to life science professionals. First, the bibliometric journal impact factor (JIF) functions as a cognitive signal of scientific credibility, a sector where evidence-based decision-making is culturally embedded, and publication quality serves as a proxy for technological legitimacy (Garfield, 1996). Second, technology hype, operationalised through the Gartner Hype Cycle framework, represents a social influence variable that shapes organisational expectations and investment decisions around emerging technologies (Gartner Inc., 2018). Whether these variables influence ML acceptance among life science professionals, alongside individual knowledge and experience, has not been empirically tested. This study addresses that gap by investigating ML technology acceptance among 213 biomedical and life science professionals across EMEA, LATAM, and North America, using a cross-sectional quantitative survey and PLS-SEM analysis. The TAM model is extended with three external variables, JIF, technology hype, and prior knowledge and experience, to test their influence on PU and PEU in this specific professional context. Additionally, the study examines demographic and regional differences in ML acceptance, with particular attention to variation between academic researchers and healthcare professionals. The findings contribute a validated, sector-specific extension of TAM for life sciences, provide actionable insights for organisations seeking to accelerate ML implementation, and establish a framework for future subsector-specific research.

OBJECTIVE: Bladder cancer (BC) is predominantly a disease of older, comorbid adults, and radical cystectomy (RC), which is the gold standard treatment, carries considerable morbidity. We sought to determine the impact of baseline dementia and frailty on the care trajectory beyond the immediate postoperative period. We hypothesized that frail patients and those with dementia undergoing RC for BC will have poorer care trajectories. METHODS AND MATERIALS: We identified Medicare beneficiaries [≥] 66 years old who underwent RC for BC in 2017 with 12 months of pre- and post-RC enrollment. Frailty and dementia were characterized using validated, claims-based measures. Associations between baseline frailty and dementia with postoperative care trajectory outcomes were determined using Fine-Gray competing risk models. RESULTS: We identified 3,600 beneficiaries of whom 11.6% were frail and 3.4% met criteria for dementia. Patients with dementia were more likely to be frail, comorbid, and not receive standard-of-care neoadjuvant chemotherapy. Frailty was independently associated with [≥] 2 transitions in care level after index discharge from RC and skilled nursing facility (SNF) admissions within 1 year of RC, exposure to intensive post-RC interventions, including dialysis and feeding tube placement, and poorer survival. Dementia remained associated with SNF admissions regardless of frailty level. CONCLUSIONS: Among a contemporary cohort of older adults undergoing RC for BC, preoperative dementia and frailty were independently associated with poorer care trajectory beyond the immediate postoperative period after RC. Our work highlights a role for preoperative geriatric assessment in identifying and optimizing patients at greatest risk.

Background Slow walking in older adults with mild parkinsonian signs (MPS) is a complex, multifactorial phenomenon arising from the cumulative burden of subclinical age-associated pathologies. This decline reflects age-associated neuronal loss in the dopaminergic system. A recent study suggests that levodopa treatment may enhance gait parameters. The goal of this small pilot study is to explore the effect of levodopa treatment on slow walking gait in older adults with MPS. Method This study was a randomized, placebo-controlled clinical pilot trial. Slow walking older adults without clinical evidence of PD were recruited and randomized into 2 groups (active treatment group or placebo control group). Participants in the active group were pre-treated with carbidopa for three days, followed by carbidopa-levodopa for seven days. Spatiotemporal gait parameters were evaluated at baseline and post-intervention. Results Gait factor analysis identified three main factors explaining gait characteristics at baseline, which included gait efficiency, gait rhythmicity, and gait turning.No effect of treatment was observed in the placebo group (p=0.111, p=0.616), no group difference was observed between the placebo and active group at baseline ({beta}=0.310, p=0.547), but a strong trend for a treatment-related increase was observed in the active treatment group ({beta}=0.506, p=0.076). Conclusion Our preliminary data suggest that sustained levodopa treatment (one week) in conjunction with carbidopa pre-treatment and concomitant carbidopa supplementation is feasible in slow walking older adults with MPS. Moreover, the data indicate potential efficacy, showing improvements in cadence, and step durations.

**Abstract** **Background:** Transcatheter edge-to-edge repair (TEER) is an established treatment for mitral regurgitation but remains highly dependent on operator experience and complex transesophageal echocardiography (TEE)-guided intraprocedural imaging. Artificial intelligence (AI)-based semantic segmentation may improve procedural reproducibility and intraprocedural guidance; however, no TEER-specific segmentation framework has been reported. **Objectives:** To develop and evaluate AutoClip, a clinician-driven AI-guided TEE semantic segmentation model designed for simultaneous delineation of mitral valve anatomy and in-vivo TEER device components. **Methods:** A retrospective proof-of-concept study was conducted using 987 intraprocedural TEE frames derived from 10 video clips in 3 patients undergoing MitraClip G4 implantation. Seven semantic labels, including mitral leaflets and device components, were manually annotated using ITK-SNAP. Following standardized preprocessing and region-of-interest extraction, an Attention U-Net architecture was trained frame-wise on bicommissural and corresponding X-plane TEE views. Model performance was assessed using mean intersection-over-union (IoU) and Dice coefficient on an independent test set. **Results:** The Attention U-Net demonstrated improved sensitivity to small device structures compared with conventional U-Net architectures. Preliminary training performance achieved a mean IoU of approximately 0.93, while independent test performance reached a mean IoU of 0.46 across foreground classes. Qualitative assessment demonstrated feasible simultaneous segmentation of mitral leaflets, clip arms, grippers, and delivery shaft during TEER procedures. **Conclusions:** AutoClip represents a proof-of-concept TEER-specific TEE semantic segmentation framework initiated through a clinician-oriented workflow without formal computer science expertise. Although preliminary accuracy remains modest due to limited sample size, this study establishes a reproducible pathway for future AI-assisted intraprocedural guidance systems and larger multicenter development efforts in structural heart interventions.

Objective: Tumor-infiltrating lymphocytes (TILs) in breast cancer are one of the most important indicators of the immune response within the tumor microenvironment. They play a particularly significant prognostic and predictive role in triple-negative and HER2-positive subtypes. However, substantial inter-observer variability has been reported in TIL scoring among pathologists, which limits its reliability in clinical practice. The aim of this study was to evaluate the agreement between artificial intelligence (AI) models and pathologists in TIL scoring and to compare this agreement using different statistical approaches, thereby assessing the potential of AI integration into pathology practice. Materials and Methods: Digitized histopathological images of breast cancer cases were included in the study. Tumor regions annotated by pathologists were evaluated for both stromal TIL percentage and the proportion of stromal tumor area within each ROI, with assessments performed independently by three pathologists and two AI models. Agreement was assessed among pathologists, between pathologists and AI, and between AI models. Statistical analyses included intraclass correlation coefficient (ICC), Cohen and Fleiss kappa, correlation tests, and Bland-Altman analysis. In addition, categorical agreement was examined using different cut-off values. Results: Inter-pathologist agreement was high, with an ICC of 0.81. In contrast, the global agreement between pathologists and AI models was lower (ICC 0.41). Pairwise comparisons of pathologist-AI agreement yielded substantially lower ICC values (0.12-0.21), although this improved to 0.53 when three pathologists were assessed jointly with a single AI model. The strongest categorical agreement was observed with dichotomized TIL scores ([≤]10% vs. >10%), whereas multi-category classifications were associated with a marked reduction in kappa values. Spearman correlation coefficients between pathologists and AI models ranged from moderate to good ({rho} = 0.48-0.81). Agreement between the two AI models themselves was moderate, with an ICC of 0.64

Background. Fairness-aware machine learning increasingly targets demographic performance disparities in clinical prediction, yet whether standard bias mitigation strategies genuinely improve equity in physiological signal analysis remains unclear. Age-based disparities in photoplethysmography (PPG)-based heart rate prediction present a particular challenge, as age-related performance differences may reflect context-dependent physiological structure rather than correctable artifacts. Methods. We evaluated three fairness interventions, inverse-frequency weighting (IF), Group Distributionally Robust Optimization (GroupDRO), and adversarial debiasing (ADV), applied via fine-tuning of a PPG foundation model across three clinical datasets spanning intensive care unit, laboratory, and consumer wearable contexts. Outcomes were assessed using a 2x2 framework classifying each intervention-dataset combination by the joint direction of change in mean absolute error (MAE) and fairness gap (FG) across age groups, yielding four outcome types: genuine improvement (G), leveling down (L), selective benefit (S), and both worse (W). Results. Across nine intra-domain conditions, no intervention simultaneously improved both MAE and FG (0/9 genuine improvement). The dominant pattern was leveling down (5/9): FG decreased but was accompanied by MAE degradation, indicating that apparent fairness gains were achieved at the cost of overall predictive performance. Age-group difficulty ordering varied across clinical contexts at baseline and was not preserved under intervention. In 18 cross-domain transfer conditions, genuine improvement was rare (4/18) and observed exclusively in non-MIMIC source configurations; models fine-tuned on MIMIC-sourced data yielded no genuine improvements (0/6). Embedding-level representation changes following fine-tuning did not reliably predict fairness outcomes. Conclusions. Age-based fairness interventions in PPG heart rate prediction indicate a leveling-down pattern rather than genuine equity improvement, suggesting that age-related performance gaps reflect context-dependent physiological structure not fully addressable through standard bias mitigation. Cross-domain transfer further amplifies this instability. These findings suggest that fairness evaluation frameworks for age-stratified physiological prediction should account for context-dependent performance structure rather than treating observed gaps as correctable bias.

Background: Electrolyte replacement is ubiquitous in the acute care setting, but its familiarity cannot belie that even small dosing errors with potassium can cause lethal cardiac arrhythmias. Recently, MedAgentBench offered a benchmark for agentic artificial intelligence (AI) including the ability to correctly dose potassium based on a single rule; however, this does not adequately reflect the clinical complexity or safety concerns of an agent that has been used as the lethal injection. The purpose of this analysis was to a probe leaderboard large language model (LLM) capabilities to follow basic dosing rules to safely replace potassium in a series of clinician-annotated cases. Methods: Using a clinician panel, we developed a series of dosing principles and 20 clinical cases reflective of the complexity of potassium replacement. External clinicians were surveyed to assess practice variability and agreement to clinician panel answers. We tested GPT-5-chat with each case in triplicate, with and without the clinician curated dosing principles, and prompted the model to answer six questions involving potassium goals, dosing, route, lab frequency, concurrent interventions, and the model's perceived level of confidence for the output and complexity of the case. The primary outcome was the rate of appropriate recommendations in comparison to clinician answers. Results: A total of 54 clinicians reviewed the 20 hypokalemia cases and hypokalemia dosing guideline. Clinicians expressed "highly agree" or "somewhat agree" for 66.8% of the cases evaluated when asked if they agree with the guideline-recommended management. When given the potassium dosing guideline, total errors dropped from 165 to 104, and average accuracy improved from 45% to 65% with GPT-5-Chat. GPT-5-Chat conveyed a high level of confidence for 100% of responses, while labeling 80% and 76% of cases as highly complex with and without the criteria, respectively. Potential harm scores were considerable in both groups, however, a notable reduction in severity scores occurred with the dosing guidance document. Recommendations on concurrent interventions and dosing had the highest rate of errors in both groups. Conclusions: Benchmarks must appropriately reflect clinical complexity to be considered valuable for the deployment of agentic artificial intelligence tools in the healthcare domain. GPT-5-Chat assessment on a comprehensive medication management task for potassium replacement showed improvement with dosing guidance, yet unfit benchmarking performance.

Background: Circulating tumour DNA (ctDNA) liquid biopsy is now established across oncology for early cancer detection, minimal residual disease surveillance, and treatment monitoring. Detection thresholds for all current ctDNA assays are derived empirically through receiver operating characteristic analysis on training cohorts - a statistically valid but theoretically uninformed approach that does not specify the minimum detectable tumour fraction given assay technical characteristics, nor identify when increasing sequencing depth ceases to provide additional clinical information. Methods: We model ctDNA detection as a binary hypothesis testing problem with Binomial-distributed mutant allele counts against a sequencing error noise floor. The Neyman-Pearson lemma is applied to derive the uniformly most powerful detector and the minimum detectable tumour fraction in closed form. The sequencing assay is modelled as a binary symmetric channel and Shannon channel capacity is calculated. Empirical validation uses n=61 data points extracted from five published peer-reviewed analytical validation studies across five independent institutions in the US and EU (2018 - 2025): Yu et al. 2022, Stetson et al. 2018, Frydendahl et al. 2023, Northcott et al. 2024, and Cheng et al. 2025. Results: The minimum detectable tumour fraction is derived in closed form as f_min approximately equal to (z_alpha + z_beta) multiplied by the square root of (epsilon divided by N), where N is sequencing depth, epsilon is the platform error rate, and z_alpha, z_beta are standard normal quantiles at the specified false positive and false negative rates. Shannon channel capacity is C = 1 minus H(epsilon) bits per read, where H(epsilon) is binary entropy. Empirical validation yields 84.3% agreement for single-locus assays. Discordance for multi-locus tumour-informed assays (NeXT Personal, duplex WGS) is consistent with the single-locus model scope and identifies the principal theoretical extension required. Conclusions: This framework provides the first formal Neyman-Pearson optimality proof for ctDNA detection, a closed-form detection limit, and a platform-independent efficiency metric for NHS and regulatory standardisation. Keywords: circulating tumour DNA; liquid biopsy; Neyman-Pearson detection; Shannon channel capacity; sequencing depth; limit of detection; minimal residual disease; signal detection theory

Background: Wheeled walkers can improve safety during walking, but improper use may increase fall risk among frail older adults. No suitable tool exists to assess safe indoor wheeled walker use in this population. This study aimed to develop and validate a video-based expert assessment tool. Methods: Based on the literature and expert consensus, seven problematic indoor situations were identified, and an assessment tool with five safety criteria per situation was developed (maximum score = 35). Fifty participants (mean age 83.9 years, 64% women) from a geriatric rehabilitation clinic and a nursing home were video-recorded while using a rollator. Expert ratings were compared with nursing staff ratings, self-ratings, and the Timed Up and Go test to evaluate validity. Intra- and inter-rater reliability were determined from independent ratings by two physiotherapists and a repeated expert rating after seven days. Sensitivity to change was assessed after two weeks of rehabilitation, and feasibility by the time required for assessment. Results: The expert score of rater 1 at baseline was 28.5 points, and assessment required a mean of 17.5 minutes. Intra-rater reliability was excellent (ICC = 0.98) and inter-rater reliability was good (ICC = 0.80). Validity analyses showed the strongest association with nursing staff assessments (r = 0.74) and a moderate association with the Timed Up and Go test (r = -0.45). After two weeks, patients improved by an average of 2.38 points (8.4% of baseline score). Conclusions: The new instrument demonstrated high reliability, acceptable validity, sensitivity to change, and good feasibility for assessing safe wheeled walker use in frail older adults. Trial registration number and date of registration: DRKS00038358, 07/11/2025

Introduction: Synthetic oligopeptides provide a rapid and cost-efficient approach to developing antibodies and diagnostics for emerging viral variants. Methods: This study computationally and experimentally characterized a synthetic peptide analog of the SARS-CoV-2 spike subdomain 2 major disulfide loop (SD2MDL), designated S621 (CPVAIHADQLTPTWRVYSTC). Binding affinity was computationally estimated using the Heuristic Affinity Prediction Tool for Immune Complexes (HAPTIC), while experimental validation was performed using enzyme-linked immunosorbent assay (ELISA) with rabbit-derived antipeptide antibodies. Clinical diagnostic accuracy testing was done using plasma samples from RT-PCR-confirmed COVID-19 patients and pre-COVID-19 controls. Results: S621 demonstrated nanomolar binding affinity (Kdapp = 1.14 nM) and high avidity (3.67 nM), closely matching HAPTIC predictions (3.54 nM). Diagnostic evaluation yielded a sensitivity of 89.92% and specificity of 27.79%, corresponding to an overall accuracy of 71.79%. Discussion: These findings demonstrate that a single synthetic peptide derived from a conserved spike subdomain can function as a high-affinity surrogate for full-length antigens, supporting its potential application in rapid peptide-based immunodiagnostics.

Abstract Background: Kaposi sarcoma (KS) is the most common cancer among men in several Eastern African countries, yet treatment monitoring relies on imprecise, time-consuming ruler-based measurements defined by the AIDS Clinical Trial Group (ACTG). This method suffers from inter-observer variability, fails to capture lesion height or true geometric area, and performs poorly on dark skin. SkinScan3D (SS3D) is a portable, low-cost, AI-enabled 3D imaging device that provides objective measurements of KS skin lesion area, height, volume, and color. The Precision Imaging to Evaluate Kaposi Sarcoma (PRIME-KS) study evaluates whether SS3D provides more reproducible and accurate lesion measurements than the standard method, and validates its integration into routine clinical workflows in Kenya and Uganda. Methods: PRIME-KS is a multicountry prospective mixed-methods study with two clinical objectives. Objective 1 is a cross-sectional diagnostic accuracy study comparing SS3D with ruler-based measurement in 50 adults with KS (150 lesions) across sites in Kenya and Uganda. Two clinicians independently measure three lesions per participant using both methods. The primary outcomes are concordance correlation coefficient (CCC) for inter-rater reproducibility, and co-efficient of determination for accuracy. Objective 2 is a non-randomized before-and-after pilot study in 100 patients at three sites, evaluating device usability, acceptability, appropriateness, and feasibility using validated instruments, along with time-and-motion studies and activity-based micro-costing. Prior to these clinical objectives, a formative study used focus group discussions, discrete choice experiments, and human-centered design workshops to refine the SS3D device and protocols with end-user input. Discussion: PRIME-KS will provide the first rigorous evaluation of a 3D imaging device for monitoring KS treatment response in routine clinical settings. If SS3D demonstrates superior reproducibility and clinical utility, it could reduce unnecessary chemotherapy exposure and associated toxicities by enabling earlier, more objective assessment of treatment response. Trial registration: ClinicalTrials.gov NCT06898203, registered 27 March 2025. Pan African Clinical Trials Registry PACTR202603523439856. Keywords Kaposi sarcoma, SkinScan3D, 3D imaging, treatment monitoring, diagnostic accuracy, implementation science, usability, human-centered design, Kenya, Uganda

Background The European Association for the Study of the Liver (ESAL) - Steatotic Liver Disease (SLD) screening algorithm involves two steps; initial screening with FIB-4 followed by referral for vibration-controlled transient elastography (VCTE) in patients likely to have significant fibrosis (SF). However, VCTE is not widely available in resource-limited settings. Aim To optimise the EASL SLD screening algorithm for resource-poor settings using machine learning (ML). Methods We analysed data from 964 adults aged [≥]35 years who underwent VCTE at a tertiary referral centre in Sri Lanka between November 2024 and 2025. Multiple ML models using different methods and variable combinations were trained on 80% of the dataset and tested on the remaining 20%. Best models were selected based on performance and externally validated using data from 430 patients who underwent VCTE before November 2024. Model performance was compared with the FIB-4 using confusion matrices. Results A Random Forest model incorporating age, AST, ALT, and platelet count separately, rather than using FIB-4, outperformed. The all-variable ML model showed the best predictive performance for SF, with accuracy of 77.2%, recall of 0.762, precision of 0.778, and AUC-ROC of 0.818. The variables used in the model, in descending order of feature importance, were AST, platelet count, BMI, ALT, age, diabetes mellitus, hypertension, dyslipidaemia, sex, family history, hypothyroidism, diabetes complication and smoking. External validation demonstrated 75.1% accuracy and an AUC of 0.779. When used as the first step of the SLD screening algorithm, the all-variable ML model identified 37 (17.1%) additional true positives and reduced false-negative diagnoses by 50% compared with FIB-4. Conclusions ML-based models were more effective than the FIB-4 score as the first-line screening tool for VCTE referral, substantially improving the identification of patients with significant fibrosis in this South Asian cohort.

Background Chronic pain is common in adults aged 85 years and older (85+) and is associated with detrimental outcomes. Chronic pain guidelines advise first line management with non-pharmacological measures; paracetamol and non-steroidal anti-inflammatory drugs are the preferred analgesics. Challenges in accessing non-pharmacological therapies for adults aged 85+, and the presence of multimorbidity and polypharmacy, mean that opioid medication is often prescribed for chronic pain despite the potential for opioid-related adverse effects and guidance identifying long-term opioids for chronic pain as a potentially inappropriate prescription. Aim This study aims to explore patient, caregiver, and healthcare professional perspectives on the prescription of opioid medications for pain management for chronic pain in adults aged 85+ to support development of resources for optimising opioid prescribing. Design and Setting In this qualitative study, participants were recruited through primary care, in the community or in care home settings. Method 36 semi-structured interviews were conducted with care home residents and community dwellers aged 85+ (n=12), caregivers (informal and care home staff) (n=12), and healthcare professionals (n=12). Interviews were transcribed and analysed using reflexive thematic analysis. Results Four themes were developed: contextual complexity, satellite influences, balancing act, and pragmatic prescribing. Using opioids in adults aged 85+ is a balancing act to support patients best possible quality of life within their unique circumstances whilst using the pain management tools available. Conclusion Opioids continue to have an important role in pain management in adults aged 85+ largely due to paucity of alternatives and the drive to support quality of life.

Childhood diarrheal disease remains a leading cause of morbidity and mortality among children under five years in sub-Saharan Africa, particularly in settings affected by inadequate sanitation, climate variability, malnutrition, and limited healthcare access. Conventional forecasting approaches are often constrained by sparse surveillance data, weak spatial representation, and limited incorporation of mechanistic disease dynamics. This study presents a Physics-Informed Multimodal Artificial Intelligence Digital Twin framework that integrates Physics-Informed Neural Networks, Graph Neural Networks, diffusion-reaction epidemiological modeling, multimodal fusion learning, and Digital Twin simulation to estimate and predict childhood diarrheal disease burden in Kenya, Somaliland, and Zimbabwe. Using public epidemiological, environmental, climate, sanitation, and synthetic proof-of-concept datasets, the framework modeled temporal disease dynamics, spatial transmission, pathogen-attributed burden, and outbreak trajectories while enforcing epidemiological consistency through physics-informed optimization. Results demonstrated robust forecasting performance, enhanced spatial transmission modeling, uncertainty-aware predictions, and realistic outbreak simulations across the three countries. Rotavirus, Shigella, and Cryptosporidium were identified as major contributors to modeled mortality burden, while unsafe water exposure, poor sanitation, malnutrition, and climate-sensitive transmission substantially increased disease risk. Compared with a Bayesian baseline model, the multimodal framework achieved superior nonlinear risk characterization, geospatial learning, and temporal prediction. These findings highlight the potential of scientific machine learning and digital twin systems for infectious disease surveillance, outbreak forecasting, climate-health analytics, and evidence-based public health decision-making in low-resource African settings. Keywords: Physics-Informed Neural Networks, Graph Neural Networks, Digital Twin, Childhood Diarrheal Disease, Epidemiology, Kenya, Somaliland, Zimbabwe, Scientific Machine Learning, Spatial Epidemiology, Multimodal Fusion

End-of-rotation handoffs are critical for patient safety but add to documentation burden for hospitalists. Generative artificial intelligence (AI) may help automate handoff creation using electronic health record data, but its impact on quality and safety is unclear. Methods: We developed an AI handoff tool with a large language model using clinical notes as input and conducted a retrospective evaluation comparing AI-generated and clinician-authored handoffs. Handoffs were assessed across domains of quality and safety through a structured review. Results: Quality ratings were similar between AI and human handoffs (3.7 vs. 3.5, p=0.57). AI-generated handoffs were rated higher for organization (4.4 vs. 4.1, p=0.05) and completeness (4.1 vs. 3.6, p=0.01), but lower for conciseness (3.7 vs. 4.1, p=0.03) and accuracy (4.1 vs. 4.4, p=0.03). Error rates were comparable (0.3/handoff in both groups); however, AI-generated handoffs included inaccuracies (9% of AI errors) and hallucinations (1% of AI errors), while clinician-authored handoffs contained only omissions. Conclusion: Human and AI handoffs have differing error profiles and tradeoffs between completeness and conciseness. Prospective evaluation in clinical workflows is underway.

Background Coeliac disease (CD) diagnosis on duodenal biopsies is limited by interobserver variability. We have previously demonstrated pathologist-level performance with our artificial intelligence (AI) model for the histopathological diagnosis of adult CD, but not in paediatric practice. As paediatric CD screening programmes expand internationally, accurate and scalable diagnostic tools are needed. We investigated whether an AI model trained exclusively on adult whole-slide images (WSIs) can generalise to paediatric CD diagnosis across independent centres. Methods A training and validation dataset of 9,958 WSIs from 8,421 adult patients (961 CD) from five centres was used to develop an ensemble of multiple-instance learning models using features from a foundation model. Testing was performed on 708 consecutive paediatric patients (86 CD) from two centres (Edinburgh and Southampton) not included in training. Model calibration was assessed, and probability outputs were grouped into clinically interpretable categories. Findings In adult cross-validation, the AI model achieved an area under the receiver operating characteristic curve (AUC) of 98.7%, sensitivity of 84.9%, specificity of 99.0%, and negative predictive value (NPV) of 98.1%. On testing (paediatric) datasets, performance remained high (AUC 98.8%, sensitivity 80.2%, specificity 98.4%, NPV 97.3%). Restricting analysis to predictions outside the intermediate-probability range (predicted CD probability <10% or [&ge;]65%; 85.3% of cases) improved sensitivity to 100% and specificity to 98.7%. No misclassifications were observed among high-confidence predictions (<2% or [&ge;]85%; 66.0% of cases). The expected calibration error was 0.03. Performance improved significantly when biopsies from both duodenal sites (bulb [D1] and descending [D2/3]) were considered. Interpretation Our AI model, trained on adult biopsies, generalises to paediatric CD diagnosis across centres and scanner platforms. Well-calibrated probability outputs provide clinically interpretable measures of diagnostic confidence and could support safe identification of CD-negative biopsies within defined thresholds. These findings demonstrate the feasibility of applying adult-derived AI models in paediatric populations and reinforce the importance of multi-site (D1 & D2) biopsy sampling.