Searcharxiv⌕ Search

arXiv subjects

Venet Osmani

Publications and source records attributed to Venet Osmani.

17 recordsLinked to original sources
arXiv2025

Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension

Recent advancements in early assessment of pulmonary hypertension (PH) primarily focus on applying machine learning methods to centralized diagnostic modalities, such as 12-lead electrocardiogram (12L-ECG). Despite their potential, these approaches fall short in decentralized clinical settings, e.g., point-of-care and general practice, where handheld 6-lead ECG (6L-ECG) can offer an alternative but is limited by the scarcity of labeled data for developing reliable models. To address this, we propose a lead-specific electrocardiogram multimodal variational autoencoder (\textsc{LS-EMVAE}), which incorporates a hierarchical modality expert (HiME) fusion mechanism and a latent representation alignment loss. HiME combines mixture-of-experts and product-of-experts to enable flexible, adaptive latent fusion, while the alignment loss improves coherence among lead-specific and shared representations. To alleviate data scarcity and enhance representation learning, we adopt a transfer learning strategy: the model is first pre-trained on a large unlabeled 12L-ECG dataset and then fine-tuned on smaller task-specific labeled 6L-ECG datasets. We validate \textsc{LS-EMVAE} across two retrospective cohorts in a 6L-ECG setting: 892 subjects from the ASPIRE registry for (1) PH detection and (2) phenotyping pre-/post-capillary PH, and 16,416 subjects from UK Biobank for (3) predicting elevated pulmonary atrial wedge pressure, where it consistently outperforms unimodal and multimodal baseline methods and demonstrates strong generalizability and interpretability. The code is available at https://github.com/Shef-AIRE/LS-EMVAE.

eess.SP↗
arXiv2025

MeDSLIP: Medical Dual-Stream Language-Image Pre-training with Pathology-Anatomy Semantic Alignment

Pathology and anatomy are two essential groups of semantics in medical data. Pathology describes what the diseases are, while anatomy explains where the diseases occur. They describe diseases from different perspectives, providing complementary insights into diseases. Thus, properly understanding these semantics and their relationships can enhance medical vision-language models (VLMs). However, pathology and anatomy semantics are usually entangled in medical data, hindering VLMs from explicitly modeling these semantics and their relationships. To address this challenge, we propose MeDSLIP, a novel Medical Dual-Stream Language-Image Pre-training pipeline, to disentangle pathology and anatomy semantics and model the relationships between them. We introduce a dual-stream mechanism in MeDSLIP to explicitly disentangle medical semantics into pathology-relevant and anatomy-relevant streams and align visual and textual information within each stream. Furthermore, we propose an interaction modeling module with prototypical contrastive learning loss and intra-image contrastive learning loss to regularize the relationships between pathology and anatomy semantics. We apply MeDSLIP to chest X-ray analysis and conduct comprehensive evaluations with four benchmark datasets: NIH CXR14, RSNA Pneumonia, SIIM-ACR Pneumothorax, and COVIDx CXR-4. The results demonstrate MeDSLIP's superior generalizability and transferability across different scenarios. The code is available at https://github.com/Shef-AIRE/MeDSLIP, and the pre-trained model is released at https://huggingface.co/pykale/MeDSLIP.

cs.CV↗
arXiv2025

Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review

Generating synthetic tabular health data is challenging, and evaluating their quality is equally, if not more, complex. This systematic review highlights the critical importance of rigorous evaluation of synthetic health data to ensure reliability, clinical relevance, and appropriate use. From an initial identification of 2067 relevant papers published in the last ten years, 134 studies were selected for detailed analysis. Our review identifies key challenges, including lack of consensus on evaluation methods, inconsistent application of evaluation metrics, limited involvement of domain experts, inadequate reporting of dataset characteristics, and limited reproducibility of results. In response, we provide a structured consolidation of synthetic data generation and evaluation methods into taxonomies, alongside practical guidelines to support more robust and standardised evaluation practices. These findings aim to support the responsible development and use of synthetic health data, aligned with emerging expectations around transparency, reproducibility, and governance, ultimately enabling the community to fully harness its transformative potential and accelerate innovation.

cs.LG↗
arXiv2025

Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling

Class-bias, that is class-wise performance disparities, is typically attributed to data imbalance and addressed through frequency-based resampling. However, we demonstrate that substantial bias persists even in perfectly balanced datasets, proving that class frequency alone cannot explain unequal model performance. We investigate these disparities through the lens of class-level learning difficulty and propose Hardness-Based Resampling (HBR), a strategy that leverages hardness estimates to guide data selection. To better capture these effects, we introduce an evaluation protocol that complements global metrics with gap- and dispersion-based measures. Our experiments show that HBR significantly reduces recall gaps, by up to 32% on CIFAR-10 and 16% on CIFAR-100, outperforming standard frequency-based resampling. We further show that we can improve fairness outcomes by selectively using the hardest samples from a state-of-the-art diffusion model, rather than randomly selecting them. These findings demonstrate that data balance alone is insufficient to mitigate class bias, necessitating a shift toward hardness-aware approaches.

cs.LG↗
arXiv2024

Multimodal Variational Autoencoder for Low-cost Cardiac Hemodynamics Instability Detection

Recent advancements in non-invasive detection of cardiac hemodynamic instability (CHDI) primarily focus on applying machine learning techniques to a single data modality, e.g. cardiac magnetic resonance imaging (MRI). Despite their potential, these approaches often fall short especially when the size of labeled patient data is limited, a common challenge in the medical domain. Furthermore, only a few studies have explored multimodal methods to study CHDI, which mostly rely on costly modalities such as cardiac MRI and echocardiogram. In response to these limitations, we propose a novel multimodal variational autoencoder ($\text{CardioVAE}_\text{X,G}$) to integrate low-cost chest X-ray (CXR) and electrocardiogram (ECG) modalities with pre-training on a large unlabeled dataset. Specifically, $\text{CardioVAE}_\text{X,G}$ introduces a novel tri-stream pre-training strategy to learn both shared and modality-specific features, thus enabling fine-tuning with both unimodal and multimodal datasets. We pre-train $\text{CardioVAE}_\text{X,G}$ on a large, unlabeled dataset of $50,982$ subjects from a subset of MIMIC database and then fine-tune the pre-trained model on a labeled dataset of $795$ subjects from the ASPIRE registry. Comprehensive evaluations against existing methods show that $\text{CardioVAE}_\text{X,G}$ offers promising performance (AUROC $=0.79$ and Accuracy $=0.77$), representing a significant step forward in non-invasive prediction of CHDI. Our model also excels in producing fine interpretations of predictions directly associated with clinical features, thereby supporting clinical decision-making.

cs.LG↗
arXiv2022

Mitigating Health Data Poverty: Generative Approaches versus Resampling for Time-series Clinical Data

Several approaches have been developed to mitigate algorithmic bias stemming from health data poverty, where minority groups are underrepresented in training datasets. Augmenting the minority class using resampling (such as SMOTE) is a widely used approach due to the simplicity of the algorithms. However, these algorithms decrease data variability and may introduce correlations between samples, giving rise to the use of generative approaches based on GAN. Generation of high-dimensional, time-series, authentic data that provides a wide distribution coverage of the real data, remains a challenging task for both resampling and GAN-based approaches. In this work we propose CA-GAN architecture that addresses some of the shortcomings of the current approaches, where we provide a detailed comparison with both SMOTE and WGAN-GP*, using a high-dimensional, time-series, real dataset of 3343 hypotensive Caucasian and Black patients. We show that our approach is better at both generating authentic data of the minority class and remaining within the original distribution of the real data.

cs.LG↗
arXiv2021

Benchmarking machine learning models on multi-centre eICU critical care dataset

Progress of machine learning in critical care has been difficult to track, in part due to absence of public benchmarks. Other fields of research (such as computer vision and natural language processing) have established various competitions and public benchmarks. Recent availability of large clinical datasets has enabled the possibility of establishing public benchmarks. Taking advantage of this opportunity, we propose a public benchmark suite to address four areas of critical care, namely mortality prediction, estimation of length of stay, patient phenotyping and risk of decompensation. We define each task and compare the performance of both clinical models as well as baseline and deep learning models using eICU critical care dataset of around 73,000 patients. This is the first public benchmark on a multi-centre critical care dataset, comparing the performance of clinical gold standard with our predictive model. We also investigate the impact of numerical variables as well as handling of categorical variables on each of the defined tasks. The source code, detailing our methods and experiments is publicly available such that anyone can replicate our results and build upon our work.

cs.LG↗
arXiv2021

Prediction of Blood Lactate Values in Critically Ill Patients: A Retrospective Multi-center Cohort Study

Purpose. Elevations in initially obtained serum lactate levels are strong predictors of mortality in critically ill patients. Identifying patients whose serum lactate levels are more likely to increase can alert physicians to intensify care and guide them in the frequency of tending the blood test. We investigate whether machine learning models can predict subsequent serum lactate changes. Methods. We investigated serum lactate change prediction using the MIMIC-III and eICU-CRD datasets in internal as well as external validation of the eICU cohort on the MIMIC-III cohort. Three subgroups were defined based on the initial lactate levels: i) normal group (<2 mmol/L), ii) mild group (2-4 mmol/L), and iii) severe group (>4 mmol/L). Outcomes were defined based on increase or decrease of serum lactate levels between the groups. We also performed sensitivity analysis by defining the outcome as lactate change of >10% and furthermore investigated the influence of the time interval between subsequent lactate measurements on predictive performance. Results. The LSTM models were able to predict deterioration of serum lactate values of MIMIC-III patients with an AUC of 0.77 (95% CI 0.762-0.771) for the normal group, 0.77 (95% CI 0.768-0.772) for the mild group, and 0.85 (95% CI 0.840-0.851) for the severe group, with a slightly lower performance in the external validation. Conclusion. The LSTM demonstrated good discrimination of patients who had deterioration in serum lactate levels. Clinical studies are needed to evaluate whether utilization of a clinical decision support tool based on these results could positively impact decision-making and patient outcomes.

q-bio.QM↗
arXiv2021

Deep ROC Analysis and AUC as Balanced Average Accuracy to Improve Model Selection, Understanding and Interpretation

Optimal performance is critical for decision-making tasks from medicine to autonomous driving, however common performance measures may be too general or too specific. For binary classifiers, diagnostic tests or prognosis at a timepoint, measures such as the area under the receiver operating characteristic curve, or the area under the precision recall curve, are too general because they include unrealistic decision thresholds. On the other hand, measures such as accuracy, sensitivity or the F1 score are measures at a single threshold that reflect an individual single probability or predicted risk, rather than a range of individuals or risk. We propose a method in between, deep ROC analysis, that examines groups of probabilities or predicted risks for more insightful analysis. We translate esoteric measures into familiar terms: AUC and the normalized concordant partial AUC are balanced average accuracy (a new finding); the normalized partial AUC is average sensitivity; and the normalized horizontal partial AUC is average specificity. Along with post-test measures, we provide a method that can improve model selection in some cases and provide interpretation and assurance for patients in each risk group. We demonstrate deep ROC analysis in two case studies and provide a toolkit in Python.

stat.ME↗
arXiv2019

Blood lactate concentration prediction in critical care patients: handling missing values

Blood lactate concentration is a strong indicator of mortality risk in critically ill patients. While frequent lactate measurements are necessary to assess patient's health state, the measurement is an invasive procedure that can increase risk of hospital-acquired infections. For this reason we formally define the problem of lactate prediction as a clinically relevant benchmark problem for machine learning community so as to assist clinical decision making in blood lactate testing. Accordingly, we demonstrate the relevant challenges of the problem and its data in addition to the adopted solutions. Also, we evaluate the performance of different prediction algorithms on a large dataset of ICU patients from the multi-centre eICU database. More specifically, we focus on investigating the impact of missing value imputation methods in lactate prediction for each algorithm. The experimental analysis shows promising prediction results that encourages further investigation of this problem.

cs.LG↗
arXiv2019

Natural Language Processing of Clinical Notes on Chronic Diseases: Systematic Review

Of the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using ICD-10. The majority of studies focused on diseases of the circulatory system (n=38) while endocrine and metabolic diseases were fewest (n=14). This was due to the structure of clinical records related to metabolic diseases, which typically contain much more structured data, compared with medical records for diseases of the circulatory system, which focus more on unstructured data and consequently have seen a stronger focus of NLP. The review has shown that there is a significant increase in the use of machine learning methods compared to rule-based approaches; however, deep learning methods remain emergent (n=3). Consequently, the majority of works focus on classification of disease phenotype with only a handful of papers addressing extraction of comorbidities from the free text or integration of clinical notes with structured data. There is a notable use of relatively simple methods, such as shallow classifiers (or combination with rule-based methods), due to the interpretability of predictions, which still represents a significant issue for more complex methods. Finally, scarcity of publicly available data may also have contributed to insufficient development of more advanced methods, such as extraction of word embeddings from clinical notes. Further efforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and (5) availability of large-scale, de-identified clinical corpora.

cs.CY↗
arXiv2018

Processing of Electronic Health Records using Deep Learning: A review

Availability of large amount of clinical data is opening up new research avenues in a number of fields. An exciting field in this respect is healthcare, where secondary use of healthcare data is beginning to revolutionize healthcare. Except for availability of Big Data, both medical data from healthcare institutions (such as EMR data) and data generated from health and wellbeing devices (such as personal trackers), a significant contribution to this trend is also being made by recent advances on machine learning, specifically deep learning algorithms.

cs.CY↗
arXiv2018

Smartphone apps usage patterns as a predictor of perceived stress levels at workplace

Explosion of number of smartphone apps and their diversity has created a fertile ground to study behaviour of smartphone users. Patterns of app usage, specifically types of apps and their duration are influenced by the state of the user and this information can be correlated with the self-reported state of the users. The work in this paper is along the line of understanding patterns of app usage and investigating relationship of these patterns with the perceived stress level within the workplace context. Our results show that using a subject-centric behaviour model we can predict stress levels based on smartphone app usage. The results we have achieved, of average accuracy of 75% and precision of 85.7%, can be used as an indicator of overall stress levels in work environments and in turn inform stress reduction organisational policies, especially when considering interrelation between stress and productivity of workers.

cs.CY↗
arXiv2017

Enabling Prescription-based Health Apps

We describe an innovative framework for prescription of personalised health apps by integrating Personal Health Records (PHR) with disease-specific mobile applications for managing medical conditions and the communication with clinical professionals. The prescribed apps record multiple variables including medical history enriched with innovative features such as integration with medical monitoring devices and wellbeing trackers to provide patients and clinicians with a personalised support on disease management. Our framework is based on an existing PHR ecosystem called TreC, uniquely positioned between healthcare provider and the patients, which is being used by over 70.000 patients in Trentino region in Northern Italy. We also describe three important aspects of health app prescription and how medical information is automatically encoded through the TreC framework and is prescribed as a personalised app, ready to be installed in the patients' smartphone.

cs.CY↗
arXiv2015

Automatic Stress Detection in Working Environments from Smartphones' Accelerometer Data: A First Step

Increase in workload across many organisations and consequent increase in occupational stress is negatively affecting the health of the workforce. Measuring stress and other human psychological dynamics is difficult due to subjective nature of self- reporting and variability between and within individuals. With the advent of smartphones it is now possible to monitor diverse aspects of human behaviour, including objectively measured behaviour related to psychological state and consequently stress. We have used data from the smartphone's built-in accelerometer to detect behaviour that correlates with subjects stress levels. Accelerometer sensor was chosen because it raises fewer privacy concerns (in comparison to location, video or audio recording, for example) and because its low power consumption makes it suitable to be embedded in smaller wearable devices, such as fitness trackers. 30 subjects from two different organizations were provided with smartphones. The study lasted for 8 weeks and was conducted in real working environments, with no constraints whatsoever placed upon smartphone usage. The subjects reported their perceived stress levels three times during their working hours. Using combination of statistical models to classify self reported stress levels, we achieved a maximum overall accuracy of 71% for user-specific models and an accuracy of 60% for the use of similar-users models, relying solely on data from a single accelerometer.

cs.HC↗
arXiv2013

Investigation of indoor localization with ambient FM radio stations

Localization plays an essential role in many ubiquitous computing applications. While the outdoor location-aware services based on GPS are becoming increasingly popular, their proliferation to indoor environments is limited due to the lack of widely available indoor localization systems. The de-facto standard for indoor positioning is based on Wi-Fi and while other localization alternatives exist, they either require expensive hardware or provide a low accuracy. This paper presents an investigation into localization system that leverages signals of broadcasting FM radio stations. The FM stations provide a worldwide coverage, while FM tuners are readily available in many mobile devices. The experimental results show that FM radio can be used for indoor localization, while providing longer battery life than Wi-Fi, making FM an alternative to consider for positioning.

cs.NI↗