Informatics in Medicine Unlocked

Early detection of suspicious moles remains the most effective means of reducing mortality from skin cancer, yet systematic screening is constrained by the time and expertise required for manual mole assessment. This paper presents an end-to-end computational pipeline that utilizes wide-angle skin photographs (including consumer-grade smartphone images) and produces quantitative ABCD (Asymmetry, Border irregularity, Color variegation, Diameter) feature scores for every detected mole. The pipeline operates in four stages: mole detection via adaptive thresholding and blob analysis, super-resolution enhancement using EDSR, false-positive filtering using a brightness-based statistical criterion, and lesion segmentation using the Boundary Attention Mapper (BAM). BAM generates high-resolution segmentation masks by fusing early-layer activations with GradCAM heatmaps from a trained EfficientNet-B7 classifier, achieving 90.45% accuracy on the ISIC2017 dataset, outperforming both conventional GradCAM (87.78%) and dedicated segmentation architectures, including DeepLabv3 and SAM v2 by more than 5 percentage points in Dice score. The EfficientNet-B7 backbone achieves a micro-average AUC of 0.97 across eight lesion classes, with a melanoma AUC of 0.99. Color quantification uses K-means clustering with a threshold calibrated on the PH2 dataset (MSE = 1.425). Applied to 87 wide-angle images, the mole detection module achieved an F1 score of 86%. The system outputs a structured CSV of per-lesion ABCD scores suitable for clinical triage and longitudinal tracking. A clinical validation study with dermatologists and surgeons is underway to assess concordance between automated and expert assessments.

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.

Cervical cancer represents a pressing global health challenge, emphasizing the critical need for accurate and timely diagnostic methods to facilitate effective treatment and improve survival rates. In response to this challenge, the study presents CerViX-Net, an innovative classification framework designed to advance cervical cancer detection through enhanced computational efficiency and diagnostic accuracy. The development of CerViX-Net is motivated by the limitations of traditional diagnostic models, particularly in handling the computational and memory demands of large-scale data, while ensuring precise feature extraction and classification. CerViX-Net employs a hybrid deep learning architecture that combines the capabilities of ResNet50, EfficientNet-B0, and a Modified Vision Transformer (ViT) module. The ResNet50 branch extracts hierarchical features through stacked convolutional and identity blocks. In another path, the modified ViT module transforms image patches via linear projection, augments them with positional and class embeddings, and processes them using Parallel Transformer Encoder layers to model contextual relationships. Concurrently, EfficientNet-B0 utilizes MBConv blocks to extract multi-scale representations. The feature outputs from all three branches are integrated and passed through a classification head consisting of dropout layers and dense layers to ensure robust and accurate predictions. The proposed framework is rigorously evaluated on the Mendeley LBC dataset, achieving exceptional performance metrics with an accuracy of 99.69%, precision of 99.28%, recall of 99.48%, and an F1-score of 99.52%. The robustness of CerViX-Net is further validated on the SIPaKMeD and Herlev Pap Smear datasets, where it demonstrates comparable excellence, underscoring its efficacy and adaptability across diverse cytology datasets. Statistical validation using Friedman's test further reinforces its superiority over competing methods.

Cerebral ischemia is a significant concern during high-risk surgeries, such as carotid endarterectomy (CEA). Continuous electroencephalography, monitored by neurophysiological experts, is used to detect cerebral ischemia during surgery; however, real-time visual interpretation is resource-intensive and error-prone. We evaluated machine learning (ML) models, including random forest (RF), eXtreme Gradient Boosting with a random forest base classifier (XGB), elastic-net logistic regression (LR), support vector classifier (SVC) with a radial basis function kernel, and naive Bayes (NB) classifier, for automated detection of cerebral ischemia during CEA using quantitative electroencephalographic (qEEG) features. RF achieved the highest sensitivity (0.79-0.83) and an area under the precision-recall curve (AUPRC) of 0.44, while XGB demonstrated the highest specificity (0.93-0.96) with an AUPRC of 0.36. Both models showed high negative predictive values and high area under the receiver operating characteristic (AUROC) scores. Feature-importance analysis identified alpha-band activity and hemispheric asymmetry as the most discriminative qEEG predictors of ischemia. These results highlight the potential of ML-assisted monitoring to support neurophysiology experts and enhance patient safety during high-risk surgical procedures.

Background: Precise localisation of intracranial electrode contacts is essential for the interpretation of stereoelectroencephalography recordings and planning epilepsy surgery. In current clinical practice, this is typically a manual process, which is time-consuming and prone to variability. Existing automated solutions are often fragmented across multiple tools requiring technical expertise, limiting their adoption in routine clinical workflows. This study presents an open-source extension for 3D Slicer that provides an integrated, user-friendly standalone solution for the direct automatic detection of electrode contacts within a widely used medical imaging platform. Results: The proposed method combines anchor bolt-based initialisation, probabilistic segmentation of electrode structures, and non-linear modelling to precisely track true electrode trajectories. The approach was evaluated on a dataset comprising 78 cases from 73 patients, including 1,078 electrodes with 14,480 contacts. The method achieved high localisation accuracy, with a median (interquartile range) deviation of 0.10 (0.06, 0.15) mm. Only 7/1078 (0.65%) electrodes required manual correction; these specific cases were handled using tools provided within the proposed extension. Conclusions: The presented extension enables fast, accurate, and reproducible electrode contact localisation within a single integrated environment. By combining automation with intuitive user interaction, it significantly reduces processing time while maintaining clinical reliability. The tool's free availability as an extension in 3D Slicer lowers the barrier to adoption and supports the standardisation of workflows across clinical and research centres.

Background: Free-text EEG reports typically lack structure, hindering scalable analysis. We evaluate a large language model (LLM) pipeline to extract structured diagnostic labels and confidence levels from these reports. Methods: We developed a hierarchical annotation schema to classify EEG reports for four specific abnormality types using a four-point confidence scale. To establish ground truth, two certified EEG technicians annotated a diverse dataset of reports authored by neurologists with distinct writing styles. We then implemented a grammar-constrained Mistral-7B pipeline, iteratively prompt-tuned on a development set to mirror these expert annotations. The pipeline's effectiveness was evaluated against the human expert benchmark using core agreement (diagnostic accuracy) and certainty-adjusted agreement (confidence alignment), with classical NLP models serving as a secondary baseline. Results: Mistral-7B significantly outperformed baselines, achieving 96% accuracy for overall abnormality detection, approaching the human benchmark of 98%. Crucially, the model successfully identified rare epileptiform abnormalities where traditional models failed and generalized robustly across distinct reporting styles. While diagnostic accuracy was high, a performance gap persisted in certainty-adjusted agreement, indicating that accurately modeling nuanced clinical confidence remains a challenge. Conclusion: LLMs can effectively automate the extraction of structured diagnostic information from EEG reports with near-human accuracy and strong generalization. While confidence calibration requires further refinement, the combination of accurate classification and explainability makes this pipeline a promising tool for standardizing clinical data at scale. Keywords: Routine Clinical Electroencephalography; Large Language Models; Clinical NLP; Confidence Assessment; Explainable AI; Neurophysiological Evaluation

Despite longitudinal and multidimensional collected data within registries, their routine exploitation for value-based care and outcome transparency remains limited by analytical complexity and heterogeneous expertise across centers. To address this gap, we developed an open-source and free web-based software which allows registry-based data analysis operational for evaluation of practices and quality system management applied to allogeneic hematopoietic cell transplant registry. It was built with Python and Dash framework to treat user formatted data. AlloGraph produces epidemiological summaries, survival analyses, and quality management indicators. Privacy protection is ensured by a Transport Layer Security protocol to a secure server where processing occurs in-memory, without data saving. AlloGraph was evaluated positively by 30 practitioners in 24 transplant centers, of whom 89% anticipated that AlloGraph would change their monitoring practice. AlloGraph represents a privacy-preserving and user-centered platform simplifying registry analysis for activity monitoring. This scalable model could be adapted to exploit real-world health databases.

Emerging as a significant global health challenge, Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that causes memory loss and cognitive decline. Despite the ever-increasing waiting time for a specialist diagnosis, the need for a cost-effective and fast diagnostic technique is evident. This study explores the development of an explainable deep learning model to diagnose AD using only routine and low-cost clinical data, including demographic information, patient history, and results of neuropsychological tests (limited to those that can be automatically acquired). The analysis was carried out using a dataset provided by the National Alzheimer's Coordinating Center, comprising 167,364 observations and 1,024 features. The findings demonstrate diagnostic performance comparable, and slightly superior, to that of clinicians when evaluated under similar informative constraints. This study introduces two classification models to discriminate whether the presumptive etiological cause of cognitive impairment is Alzheimer's disease. The deep neural network achieved an accuracy of 90\% with an area under the receiver operating characteristic curve (ROC-AUC) of 0.96, whereas the Light Gradient Boosting Machine reached the same accuracy with a ROC-AUC of 0.97.

Carotid endarterectomy carries the risk of intraoperative cerebral ischemia, which is monitored by expert neurophysiologists through continuous electroencephalography (cEEG). Because expert availability is limited, we developed a hybrid novice-artificial intelligence (AI) system that detects ischemia using novice monitors with limited cEEG training. The hybrid system dynamically weights novice and AI inputs to arrive at a final output. Using four novices, we compared hybrid systems against experts alone, novices alone, and AI alone. Hybrid systems were statistically non-inferior to experts in sensitivity and false-positive rate (FPR), whereas novices alone were not. At 80% sensitivity, hybrid systems reduced FPR by half compared with the AI-only system, with similar benefits at 90% sensitivity. Further, the area under the precision-recall curve improved from 0.546 to 0.610-0.726, the area under the receiver operating characteristic curve improved from 0.957 to 0.967-0.971, and calibration improved compared with AI alone. These results highlight the potential of a hybrid system to monitor intraoperative cerebral ischemia.

Background: Accurate REM identification is critical for diagnosing REM sleep behaviour disorder (RBD), yet many automated sleep staging systems, especially single-channel EEG models trained on healthy cohorts, do not generalise well to real-life polysomnography (PSG) performed in patients. Objective: To compare a feature-based Random Forest (RF) model tuned for RBD with a state-of-the-art single-EEG deep architecture (AttnSleep), and to assess the impact of cohort adaptation and multimodal inputs (EEG, EOG, EMG, ECG). Methods: Experiments used 89 multi-site in-clinic PSGs (SleepWearables Phase-1) plus 53 MASS healthy controls (mean age 63, std 5 years), with 10-fold cross-validation and out-of-fold evaluation. Model performance was assessed using Cohen's kappa, and attention-based modality analysis was performed to quantify signal contributions. Results: When applied out-of-the-box after training on open-source healthy datasets, both models achieved moderate agreement overall (Cohen's kappa = 0.46), but performance declined in RBD, particularly for REM sleep (AttnSleep Cohen's kappa = 0.19 vs RF Cohen's kappa = 0.44), highlighting limited cross-cohort generalisation. The multimodal model improved overall agreement (Cohen's kappa 0.59 - 0.60) and performance in RBD (Cohen's kappa 0.45 - 0.46), with gains most pronounced in REM (Cohen's kappa 0.45 - 0.49). Attention-based modality analysis identified EEG as the dominant signal, increased EOG contribution during REM, and elevated ECG importance during N3. In RBD subjects, EOG weighting increased relative to non-RBD controls (Delta = +0.081). Guided by these weights, a reduced four-channel EEG model matched full multimodal performance in non-RBD subjects, and adding EOG achieved the best overall configuration (Cohen's kappa = 0.61 overall; Cohen's kappa = 0.48 in RBD) with improved REM classification (53% vs 45% recall). Inclusion of EOG also reduced inter-dataset variability in REM staging. Nonetheless, staging performance in RBD remained lower than in controls, particularly for REM. Conclusions: These results highlight the limited generalisability of minimal-sensor models trained on healthy cohorts, the value of mixed cohort-specific training, and the benefit of multimodal integration and attention-guided channel selection, rather than minimal-sensor approaches alone, for robust clinical sleep staging in pathological populations such as RBD.

Background: Uveal melanoma (UM) and cutaneous melanoma (CM) both originate from the same cell line. This proposes the possibility of a shared mechanism between entities, requiring explicit investigation. Methods: Data from GWAS Catalog and DisGeNET were used to identify shared variation-disease associations (VDAs) between UM and CM. The results were validated using the Ensembl database. In the next step, the STRING database was used to identify the protein-protein interaction. Results: Subsequently, 109 unique VDAs were identified for UM and 880 for CM. However, only 2 VDAs were found to be shared among UM and CM in different ethnic groups. These shared VDAs were rs12203592 of the IRF4 gene, rs12913832 of the HECT and RLD domain-containing E3 ubiquitin protein ligase 2 (HERC2) gene. Notably, PPI network assessment through STRING showcased that OCA2 and IRF4 directly interacted with HERC2. Conclusion: While HERC2 acts as a poor prognostic factor in uveal melanoma, IRF4 status is a key prognostic indicator in both UM and CM. Identifying IRF4 allele contributions enables a better understanding of melanoma pathogenesis and fosters the development of disease-specific approaches.

AO_SCPLOWBSTRACTC_SCPLOWElectroencephalography (EEG) is a promising tool for automated detection of mild cognitive impairment (MCI) and dementia, but comparisons across studies are limited by inconsistent datasets and evaluation protocols. This study benchmarks ten deep learning models across four resting-state EEG datasets and eight binary classification tasks using a unified preprocessing pipeline and five-fold subject-wise cross-validation. Each experiment was repeated ten times. SCCNet obtained the highest mean subject-level accuracy, sensitivity, and F1 score, while ShallowConvNet achieved the highest mean segment-level accuracy, specificity, and precision. Subject-level aggregation improved mean accuracy for all evaluated models, and performance varied substantially across datasets and diagnostic tasks. Higher computational cost did not consistently correspond to better classification performance, with several compact architectures remaining competitive with substantially larger models. The results provide a reproducible reference for comparing EEG-based dementia classification models under consistent subject-independent evaluation conditions.

In this work, we present a machine learning model for identifying pathogenic DNA variants. The model was learned from the analysis of normal and pathogenic sequences extracted from the ClinVar database (supported by NCBI). This analysis was based on a conceptual semantic model of DNA sequences converted to peptide sequences (amino acid sequences) governed by a well-defined grammar, which allowed us to apply NLP techniques, specifically Part of Speech tagging (POS tagging). Our predictive model was built by combining two techniques: CRF (from the Markov model family), which performs the sequencing, and BiLSTM (a deep learning model) which captures the past and future content of the sequences. The training space was created with the sequences of 105 genes associated with approximately 27,000 pathogenic variants. The model was evaluated using the metrics precision, P-R and ROC curves, AUC, and confusion matrices. Its performance was also compared against five known methods for predicting pathogenic variants. The results show exceptional performance that exceeds expectations and places this new method at the state of the art for predicting pathogenic DNA sequences.

Background: Automatic sleep staging algorithms are increasingly applied in clinical and home-based recordings. However, their performance may degrade when transferred to new montages and clinical populations. This is particularly relevant in reduced-channel portable PSG and in disorders such as REM sleep behaviour disorder (RBD), where altered sleep architecture may challenge pretrained models. Objective: To evaluate and compare multiple open-source sleep staging algorithms on a minimal portable PSG setup in controls and patients with and without RBD, and to assess the impact of fine-tuning on clinic-ascertained data. Methods: Six open-source models were applied to 76 subjects recruited from three clinical sleep medicine sites. Performance was assessed using accuracy, F1 scores, and Cohen's kappa, both overall and per sleep stage. Each model was evaluated out-of-the-box and after fine-tuning on clinical data. Results: Out-of-the-box performance varied substantially across models (Cohen's kappa 0.21-0.54). Fine-tuning consistently improved agreement, with the best-performing model (GSSC) reaching Cohen's kappa = 0.58 indicating moderate to good agreement. Performance was highest in controls and lower in patient groups. N3 was the most reliably classified stage across models, whereas N1 remained consistently challenging. REM classification improved after fine-tuning in several architectures but remained model, and subgroup-dependent, particularly in RBD subjects. Conclusion: Fine-tuning substantially mitigates domain shift, updating model parameters to align with new data distributions, when applying automatic sleep staging algorithms to portable clinical recordings. Model architecture influences robustness, with feature-learning approaches demonstrating greater adaptability than fixed-feature models. Despite moderate agreement after adaptation, performance, especially for REM and N1 remains insufficient for fully automated diagnostic use in clinical populations.

The natural variation that distinguishes living organisms within a single species is currently being studied intensively, primarily at the genetic level. Unfortunately, studies of natural variants at the level of protein gene products are not very common, mainly due to the lack of appropriate databases and bioinformatics tools. The main research technique used to study proteomes/peptidomes is mass spectrometry (MS). A classic method for interpreting raw mass spectrometry data in proteomic/peptidomic studies involves the use of databases containing representative (canonical) sequences that define the proteome of the organism under study. In this paper, we present the AliceDB database, which contains information on over 7 million natural variants of protein sequences described in the scientific literature for Homo sapiens. The data contained in the AliceDB database can be utilized using widely available and commonly used software for interpreting proteomic data. Test results regarding the use of the AliceDB database for the interpretation of proteomic data indicate that accounting for the presence of natural variants increases both the number and quality of identified proteins. Furthermore, it is easy to identify protein sequence variants that may, for example, be of significance in medicine.

Background Continuous health monitoring enables early detection of diseases and improves therapeutic outcomes. Non-intrusive biosignal sensors, such as capacitive ECG (cECG), offer a practical solution for daily monitoring in private environments, such as smart homes and vehicles. However, artifacts reduce signal quality and compromise reliability. Methods Following a registered report protocol (Warnecke JM et al. Plos One. 2021; 16(7):e0254780), we record data of 44 subjects and develop an artifact index for cECG. We use three signal quality indices (SQIs): the correlation of QRS complexes (corSQI), the R-peak detection consistency (bSQI) and the absolute amplitude ratio (aSQI). Our index classifies overlapping 10s segments with a step-width of 2s into clean or artifact segments. We label a 2s interval as artifacts if all five overlapping segments indicate artifacts. We record cECGs using an armchair with integrated electrodes in a single-arm study involving 44 subjects performing two activities -- reading and watching television (TV); for 11 minutes each. We record a time-synchronized reference ECG with skin electrodes on the chest. To evaluate the artifact index, we compare it with manually generated ground truth. Moreover, we evaluate the clothing materials cotton, linen, jeans, and polyester in 5 subjects. Results Watching TV results in longer, continuously clean signal durations than reading. On average, 88.3% of the signal has a minimum continuous clean duration of 10s, versus 79.8% during reading. All clothing configurations achieve a clean signal duration exceeding 10s. Among the SQI metrics, bSQI performs best, achieving an accuracy of 90.7% and an F1 score of 79.9%. Combining the three SQI metrics in a voting approach improves accuracy to 92.0% and F1 score to 82.1%. Discussion Our artifact index automatically distinguishes clean from artifact cECG segments, promoting health monitoring in unsupervised real-world settings, earlier disease detection, and preventive health management. A limitation is the investigation of only two scenarios (reading and watching TV).

Existing supervised and self-supervised EEG models mainly learn discriminative or reconstructive representations within individual segments, while the transition information between adjacent EEG segments remains underexplored. In this study, we propose a Multimodal self-supervised EEG World Model for wearable seizure detection. Inspired by Le World Model, the proposed method encodes consecutive EEG segments into a shared latent space and predicts the next-segment latent representation from the current-segment representation conditioned on synchronized physiological information from ECG, EMG, and movement (MOV) signals. A learnable query-based fusion module aggregates the auxiliary multimodal representations into a compact physiological condition, while Sketched Isotropic Gaussian Regularization (SIGReg) is applied to stabilize the latent space and prevent representation collapse. After pretraining, only the pretrained EEG encoder is retained and frozen for linear binary probing, enabling EEG-only downstream seizure detection. We evaluated the proposed model on the SeizeIT2 wearable focal epilepsy dataset using a strict patient-wise training, validation, and test split. The proposed Multimodal EEG World Model achieved an AUPRC of 0.3748 , ROC-AUC of 0.8025 , and balanced accuracy of 0.7308 , ranking first on these three metrics among the ablation studies. It also achieved the highest AUPRC, ROC-AUC, balanced accuracy, and F1-score among the evaluated external baselines. These findings demonstrate that synchronized multimodal physiological information can provide useful contextual information for latent EEG transition learning and improve wearable EEG representation learning.

Huntington's disease (HD) presents a heterogeneous neurodegenerative course, with motor, cognitive, and functional symptoms progressing differently across individuals. This atypical progression complicates the definition of discrete disease stages, hindering understanding of disease trajectories, timely pa- tient care, and therapy development. Consequently, current clinical staging systems rely heavily on clinician-defined, domain-specific criteria and fixed clinical measurement boundaries for stage assignment, reducing objectivity and often leading to overlapping clinical measurements across stages. While machine learning methods can help, existing approaches cannot fully capture complex temporal relationships within and across patients. We propose URL- STFN, a dynamic graph-based representation learning model that encodes both inter- and intra-patient temporal patterns from longitudinal clinical measures. We then evaluate disease stages formed through clustering and stability analysis of URL-STFN latent representations, and compare them with representations obtained from conventional embedding approaches. We further benchmark these clustering-based stages against states derived from conventional temporal models, including DHMM. We hypothesize that clustering URL-STFN latent representations enables identification of HD stages with reduced overlap in clinical measurements. The proposed framework is evaluated using 1,477 clinical visits from the Enroll-HD dataset, a large lon- gitudinal cohort with repeated clinical assessments. For staging, we used 44 clinical measurements spanning motor, cognitive, and functional domains. URL-STFN identifies clinically meaningful HD stages consistent with estab- lished disease progression while reducing overlap in clinical feature values compared with DHMM-derived and clinical staging approaches. These find- ings highlight the potential of a dynamic graph-based representation learning and clustering framework to support more objective, data-driven, and precise HD staging.

Accurate diagnosis of Parkinson's disease (PD) remains challenging due to substantial inter-subject variability and the absence of widely accessible, objective multimodal biomarkers. Although speech and magnetoencephalography (MEG) biomarkers have individually demonstrated strong discriminative potential, their joint utilization is constrained by the absence of subject-level paired datasets - a fundamental gap that has prevented cross-modal validation at the individual level. We argue that this makes cross-cohort representation learning not merely a pragmatic workaround, but the most realistic and clinically transferable framework for multimodal PD assessment. In real-world deployment, acoustic screening and neuroimaging biomarkers are acquired through separate clinical pathways and must be integrated across heterogeneous patient populations. To address this, we propose MIRA-Net (Modality-Invariant Residual Adversarial Network). This cross-cohort representation learning framework integrates acoustic speech features from four established UCI datasets (n = 193) with beta-band MEG biomarkers from the NatMEG-PD dataset (n = 127) for PD classification. MIRA-Net employs RF-SHAP feature selection, gradient-reversal-based domain adaptation, and supervised contrastive alignment to learn participant-independent, modality-invariant embeddings. The framework is evaluated under Rest, Go, and Passive task conditions against Early Fusion, Vanilla DANN, and Supervised Contrastive Learning baselines. MIRA-Net achieves a peak accuracy of 86.23% (Go condition, Stacking classifier) with AUC values exceeding 0.88 under repeated cross-validation, alongside a sensitivity of 89.4% and specificity of 83.1%. Friedman tests confirm statistically significant performance differences among fusion strategies (p < 0.003 across all conditions). These results demonstrate that cross-cohort representation learning can extract robust disease-discriminative signatures without synchronized multimodal recordings, offering a practical pathway toward AI-assisted PD assessment in resource-constrained clinical settings.

Purpose In idiopathic normal pressure hydrocephalus (iNPH), longitudinal monitoring of ventricular size is important for diagnosis and treatment follow-up. This study aimed to validate a fully automated AI model for CT ventricular volumetry with subcompartments and to compare AI-derived volume changes with routine radiology assessments. Methods This retrospective, single-center study included 88 patients with iNPH and 456 non-contrast-enhanced head CT examinations. The model was trained on 38 manually labeled CT scans with 12 ventricular subcompartments. Outcomes included segmentation accuracy, correspondence between AI-derived longitudinal ventricular volume changes and radiology report categories (decreased, unchanged, increased), radiologist detection thresholds for ventricular change, and paired pre- and postoperative volume changes in 22 patients with ventriculoperitoneal shunt. Results Mean segmentation accuracy was high (Dice, 0.83). 91% of 100 segmentations were rated as excellent by an expert neuroradiologist. AI-derived ventricular volume changes corresponded well to radiology report categories (median total ventricular volume changes of -17% in cases reported as decreased, 0% in unchanged cases, and +22% in increased cases; all p < 0.001). Radiologists reported ventricular volume change in 50% of cases at an AI-measured relative volume change of +/-6%, and in 90% of cases at +21% for enlargement and -18% for decrease. After shunt placement, ventricular volume decreased by -8% (median), with the largest relative reductions observed in the right temporal and occipital horns. Conclusions Automated AI-based ventricular segmentation on CT enables accurate and reproducible assessment of ventricular volume changes in iNPH and complements routine radiological evaluation for longitudinal and postoperative monitoring.