Informatics in Medicine Unlocked最新文献

{"title":"Curated phytochemicals of Annona muricata modulate proteins linked to type II diabetes mellitus: Molecular docking studies, ADMET and DFT calculation","authors":"Benjamin Olusola Omiyale ,&nbsp;Babatunji Emmanuel Oyinloye ,&nbsp;Basiru Olaitan Ajiboye ,&nbsp;Chukwudi Sunday Ubah","doi":"10.1016/j.imu.2024.101511","DOIUrl":"https://doi.org/10.1016/j.imu.2024.101511","url":null,"abstract":"<div><p>One of the medicinal herbs utilized in treating diabetes traditionally is <em>Annona muricata</em>. This work investigates the effect of phytochemicals from <em>A. muricata</em> on the therapeutically important protein targets associated with type II diabetes mellitus (T2DM) using a computational approach. Compounds (Phytochemicals) previously identified in <em>A. muricata</em> were docked against proteins of interest to find therapeutic hit compounds. The stability of the ligand-protein complexes was examined after selecting proteins that bind well with the discovered hits, and ADMET properties of the ligands were also predicted to determine their toxicity and drug-likeness. In addition to studying the compounds' softness, hardness, electron affinity, and electrostatic potential, the Schrödinger material science Jaguar fast engine was used to study their frontier molecular orbital (FMO). The targets aldose reductase (ALR), 11beta-hydroxysteroid dehydrogenase type 1 (11-HSD1), and diacylglycerol O-acyltransferase 1 (DGAT1) exhibited the highest binding affinities from the early screening of compounds against fifteen (15) proteins linked with T2DM. While eight (8) phenolic compounds of the plants had comparatively high docking scores with 11β-HSD1 and ALR, seven (7) acetogenins had good binding affinities with DGAT1. These top-scoring compounds exhibited considerable ADMET profiles. Additionally, the phenolic compounds that are considered as hits adhered to the Lipinski rule of 5 and can be thought of as potential drug candidates. Genistein and kaempferol are the most reactive ligands in terms of quantum mechanics. The information from this study could be used to create an alternative anti-diabetic drug with better efficacy.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"47 ","pages":"Article 101511"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000674/pdfft?md5=3fc28f332ad6e10ef637868cae91bdc3&pid=1-s2.0-S2352914824000674-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140813812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Few-shot learning for skin lesion classification: A prototypical networks approach","authors":"Sireesha Chamarthi ,&nbsp;Katharina Fogelberg ,&nbsp;Jakob Gawlikowski ,&nbsp;Titus J. Brinker","doi":"10.1016/j.imu.2024.101520","DOIUrl":"10.1016/j.imu.2024.101520","url":null,"abstract":"<div><p>Prototypical networks (PN) have emerged as one of multiple effective approaches for few-shot learning (FSL), even in medical image classification. This study focuses on implementing a PN for skin lesion classification to assess its performance, generalizability, and robustness when applied across 11 dermoscopic image domains. Unlike conventional FSL scenarios, where the performance is evaluated for unseen classes in the test set, our analysis extends this to evaluate PNs on a complete hold-out dataset with the same classes from a different domain. Differences in a patient’s age, lesion localization, or image acquisition systems variations mimic real-world cross-domain conditions in a clinic. Given the scarcity of medical datasets, this assessment is crucial for potentially translating such systems into real-world clinical settings to support physicians with the diagnosis. Our primary focus is two-fold: investigating whether a PN performs on par with a baseline classifier, even using only a limited number of reference samples from the hold-out test set (in-domain) and whether a PN can generalize to the same classes of unseen domains (cross-domain). Our analysis uncovers that a PN can perform on par with the baseline classifier in an in-domain setting, even with only a few support samples. However, in cross-domain scenarios, a PN exhibits improved performance only on specific domains, while others demonstrate similar or even decreased performance when confronted with a smaller number of images. Our findings contribute to comprehending potential opportunities and limitations of FSL in dermatological practice.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"48 ","pages":"Article 101520"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000765/pdfft?md5=fc2b86c841307a0c99065159261be4f6&pid=1-s2.0-S2352914824000765-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141053149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging mobile NER for real-time capture of symptoms, diagnoses, and treatments from clinical dialogues","authors":"Rafik Rhouma ,&nbsp;Christopher McMahon ,&nbsp;Donald Mcgillivray ,&nbsp;Hassan Massood ,&nbsp;Safia Kanwal ,&nbsp;Meraj Khan ,&nbsp;Thomas Lo ,&nbsp;Jean-Paul Lam ,&nbsp;Christopher Smith","doi":"10.1016/j.imu.2024.101519","DOIUrl":"10.1016/j.imu.2024.101519","url":null,"abstract":"<div><p>In the dynamic world of healthcare technology, efficiently and accurately extracting medical data from physician–patient conversations is vital. This paper presents a new approach in healthcare technology, employing Natural Language Processing (NLP) to identify and extract critical information from doctor–patient conversations on mobile devices. Unlike traditional methods that rely on Electronic Health Records, our novel application enables the extraction of symptoms, diagnoses, and treatments directly on a mobile device during medical consultations, significantly enhancing patient privacy. We managed to integrate both Bidirectional Encoder Representations from Transformers (BERT) models and optimized Large Language Models (LLMs) on a mobile device without compromising performance significantly. Our findings reveal that the BERT model attained an F1-score of 85.1%, while FLERT and its compressed variant DistilFLERT showed superior performance. The FLAN-T5 model outperformed all models we tested with scores up to 92.7%. These results highlight the efficacy of leveraging advanced NLP and LLM technologies in healthcare environments on a mobile device, offering a promising direction for accessible and efficient patient care.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"48 ","pages":"Article 101519"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000753/pdfft?md5=dcf02a1406246b404d5d886e23c7d375&pid=1-s2.0-S2352914824000753-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141023645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of the feasibility of digital health applications based on best practice guidelines for diabetes management: A scoping review","authors":"Andi Sulfikar,&nbsp;M. Alfian Rajab","doi":"10.1016/j.imu.2024.101601","DOIUrl":"10.1016/j.imu.2024.101601","url":null,"abstract":"<div><h3>Introduction</h3><div>The prevalence of type 1 and type 2 diabetes mellitus has increased significantly and has become a major challenge for global healthcare systems. Digital health applications have emerged as potential solutions to improve diabetes management. However, many of these applications do not adhere to best practice standards, which can lead to patient rejection and application wastage.</div></div><div><h3>Objective</h3><div>This study aims to evaluate the feasibility of digital health applications based on best practice guidelines for diabetes management.</div></div><div><h3>Methods</h3><div>This study used the scoping review method to evaluate the feasibility of digital health applications based on best practice guidelines for diabetes management. The search strategy involved keywords relevant to diabetes mellitus and digital health applications, and searches were conducted in databases such as PubMed, Cochrane Library, EMBASE, and others. The collected data were analyzed descriptively to identify patterns, trends, and differences in application effectiveness.</div></div><div><h3>Results</h3><div>The results of this review indicate that some applications, such as mySugr PRO and Vitadio, adhere to best practice guidelines and have a significant positive impact on clinical parameters such as HbA1c levels. However, many other applications still fail to meet these standards, often due to a lack of relevant biomarker data and adherence to established guidelines.</div></div><div><h3>Conclusion</h3><div>The study concludes that while some digital health applications show promise in managing diabetes effectively, there is a need for improvement in many others to comply with best practice guidelines, which is crucial for maximizing their benefits and ensuring patient acceptance.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"51 ","pages":"Article 101601"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review of ulcer detection methods in wireless capsule endoscopy","authors":"Ahmmad Musha ,&nbsp;Rehnuma Hasnat ,&nbsp;Abdullah Al Mamun ,&nbsp;Md Sohag Hossain ,&nbsp;Md Jakir Hossen ,&nbsp;Tonmoy Ghosh","doi":"10.1016/j.imu.2024.101600","DOIUrl":"10.1016/j.imu.2024.101600","url":null,"abstract":"<div><h3>Background</h3><div>Ulcers are one of the most prevalent disorders in the gastrointestinal (GI) tract, affecting many people worldwide. Wireless capsule endoscopy (WCE) emerges as the most non-invasive way to diagnose ulcers in the GI tract. However, manually reviewing images captured by WCE is a tedious and time-consuming process. Implementing a computer-aided ulcer detection system can facilitate the automatic evaluation of these images.</div></div><div><h3>Methods</h3><div>Many researchers have proposed various models to develop automatic ulcer detection methods. This research aims to conduct a systematic review by scouring four repositories (Scopus, PubMed, IEEE Xplore, and ScienceDirect) for all original publications on computer-aided ulcer detection published between 2011 and 2024. The review follows the the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines.</div></div><div><h3>Results</h3><div>The full texts of 89 scientific articles were reviewed. The contributions of this paper are two-fold: I) it reports and summarizes the current state-of-the-art ulcer detection algorithms; and II) it finds the most appropriate and preferable method in terms of color space, region of interest selection, feature extraction, and classifier.</div></div><div><h3>Conclusion</h3><div>The paper concludes with a discussion of the challenges and futuredirections for ulcer detection.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"51 ","pages":"Article 101600"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142700653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated multi-class high-grade glioma segmentation based on T1Gd and FLAIR images","authors":"Areen K. Al-Bashir ,&nbsp;Abeer N. Al Obeid ,&nbsp;Mohammad A. Al-Abed ,&nbsp;Imad S. Athamneh ,&nbsp;Maysoon A-R. Banihani ,&nbsp;Rabah M. Al Abdi","doi":"10.1016/j.imu.2024.101570","DOIUrl":"10.1016/j.imu.2024.101570","url":null,"abstract":"<div><p>Glioma is the most prevalent primary malignant brain tumor. Segmentation of glioma regions using magnetic resonance imaging (MRI) is essential for treatment planning. However, segmentation of glioma regions is usually based on four MRI modalities, which are T1, T2, T1Gd, and FLAIR. Acquiring these four modalities will increase patients' time inside the scanner and drive up the segmentation process's processing time. Nevertheless, not all these modalities are acquired in some cases due to the limited available time on the MRI scanner or uncooperative patients. Therefore, U-Net-based fully convolutional neural networks were employed for automated segmentation to answer the urgent question: does a smaller number of MRI modalities limit the segmentation accuracy? The proposed approach was trained, validated, and tested on 100 high-grade glioma (HGG) cases twice, once with all MRI sequences and second with only FLAIR and T1Gd. The results on the test set showed that the baseline U-Net model gave a mean Dice score of 0.9166 and 0.9190 on all MRI sequences using FLAIR and T1Gd, respectively. To check for possible performance improvement of the U-Net on FLAIR and T1Gd modalities, an ensemble of pre-trained VGG16, VGG19, and ResNet50 as modified U-Net encoders were employed for automated glioma segmentation based on T1Gd and FLAIR modalities only and compared with the baseline U-Net. The proposed models were trained, validated, and tested on 259 high-grade gliomas (HGG) cases. The results showed that the proposed baseline U-Net model and the ensemble of pre-trained VGG16, VGG19, or ResNet50 as modified U-Net encoders have a mean Dice score of 0.9395, 0.9360, 0.9359, and 0.9356, respectively. The results were also compared to other studies based on four MRI modalities. The work indicates that FLAIR and T1Gd are the most prominent contributors to the segmentation process. The proposed baseline U-Net is robust enough for segmenting HGG sub-tumoral structures and competitive with other state-of-the-art works.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"50 ","pages":"Article 101570"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824001266/pdfft?md5=11ba24b47b85eb2088a7bca0c079845f&pid=1-s2.0-S2352914824001266-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142011667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic literature review of time series methods applied to epidemic prediction","authors":"Apollinaire Batoure Bamana ,&nbsp;Mahdi Shafiee Kamalabad ,&nbsp;Daniel L. Oberski","doi":"10.1016/j.imu.2024.101571","DOIUrl":"10.1016/j.imu.2024.101571","url":null,"abstract":"<div><p>While time series are extensively utilized in economics, finance and meteorology, their application in epidemics has been comparatively limited. To facilitate a comprehensive research endeavor on this matter, we deemed it necessary to commence with a systematic literature review (SLR). This Systematic Literature Review aims to assess, based on a sample of relevant papers, the use of Time Series Methods (TSM) in epidemic prediction, with a special focus on African issues and the impact of COVID-19. The SLR was conducted using databases such as ACM, IEEE, PubMed and Science Direct. Open access published papers in English, in a pear reviewed Journals, from 2014 to 2023, containing keywords such as Time Series, Epidemic and Prediction were selected. The findings were summarized in an adapted PRISMA flow diagram. We end up with a sample of 36 papers. As conclusion, TSM are not so used in epidemic prediction as in some other domains, even though epidemic data are collected as time series. Just very few works address African issues regarding diseases and countries. COVID-19 is the pandemic that revealed and enhanced the used of TSM to forecast epidemics. This work paves ways for R&amp;D on epidemiology, based on TSM.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"50 ","pages":"Article 101571"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824001278/pdfft?md5=85971cb7cf5e63c60e9c1e0138eb216e&pid=1-s2.0-S2352914824001278-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142006748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CTD-Global (CTD-G): A novel composition, transition, and distribution based peptide sequence encoder for hormone peptide prediction","authors":"Hina Ghafoor ,&nbsp;Ahtisham Fazeel Abbasi ,&nbsp;Muhammad Nabeel Asim ,&nbsp;Andreas Dengel","doi":"10.1016/j.imu.2024.101578","DOIUrl":"10.1016/j.imu.2024.101578","url":null,"abstract":"<div><p>Hormone peptides are small signaling molecules that regulate key cellular processes such as cell growth, and differentiation. Hormone peptide identification is important for understanding their potential associations with certain diseases such as attention deficit hyperactivity disorder, diabetes, and psychiatric disorders. A comprehensive understanding of hormone peptides’ roles in cellular signaling, and immune regulation can provide insights into their therapeutic potential. Hormone peptides are identified through wet-lab approaches which are restricted by resource-intensive processes, limited scalability, and cost ineffectiveness. In an effort to substitute experimental approaches with computational predictors, researchers leveraged the capabilities of machine learning (ML) classifiers. These classifiers have inherent dependency over statistical vectors that are generated by extracting amino acids’ distinctive patterns from peptide sequences. Classifiers utilize these vectors for discriminating peptides into hormone and non-hormone classes. However, the performance of current predictors is constrained due to their inability to effectively extract discriminative amino acids patterns from peptide sequences. Following the need for a powerful predictor, the paper in hand presents a novel sequence encoder namely, CTD-G that transforms peptide sequences into statistical vectors by extracting 3 different types of amino acids patterns namely composition, transition, and distribution. Across public benchmark dataset, the proposed CTD-G encoder potential is compared with 56 existing encoders under two different evaluation strategies namely intrinsic and extrinsic. In Intrinsic evaluation, TSNE-based visualization demonstrates reduced overlap between clusters of hormone and non-hormone peptides with the proposed encoder’s statistical vectors compared to existing encoders. Extrinsic evaluation demonstrates the superiority of the proposed encoder, as 7 out of 11 ML classifiers achieve better performance with its statistical vectors compared to those from existing encoders. Furthermore, the proposed predictor outperforms existing hormone peptide classification predictors by 1.5% in accuracy, 5.36% in sensitivity, 1.80% in specificity, and 2.62% in MCC. To facilitate the scientific community, a web application is available at <span><span>https://sds_genetic_analysis.opendfki.de/</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"50 ","pages":"Article 101578"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824001345/pdfft?md5=213fc4dace189dd6ba5c4b98542fe484&pid=1-s2.0-S2352914824001345-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142148881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Binding modes of the metabolites docosahexaenoic acid, eicosapentaenoic acid, and eicosapentaenoic acid ethyl ester from Caulerpa racemosa as COX-2 inhibitors revealed via metabolomics and molecular dynamics","authors":"Turmidzi Fath ,&nbsp;Citra Fragrantia Theodorea ,&nbsp;Erik Idrus ,&nbsp;Izumi Mashima ,&nbsp;Dewi Fatma Suniarti ,&nbsp;Sri Angky Soekanto","doi":"10.1016/j.imu.2024.101539","DOIUrl":"https://doi.org/10.1016/j.imu.2024.101539","url":null,"abstract":"<div><p>A total of 116 metabolites of <em>Caulerpa racemosa</em> were identified. However, only three (DHA, EPA, and EPAS) were found to have high anti-inflammatory potential, with Pa scores ranging from 0.764 to 0,827. The inhibition constant (Ki) and binding energy interactions with COX-2 revealed by DHA (−8.83 kcal/mol: 0.338 μM), EPA (−8.35 kcal/mol: 0.763 μM), EPAS (−8.05 kcal/mol: 1.25 μM). They were used to bind to the fundamental residues of COX-2 (TYR 348, VAL 349, LEU 384, TYR 385, and TRP 387). The result of molecular dynamics showed that DHA, EPA, and EPAS had high stability while interacting with COX-2 in 310 K. The stabilities were 1.8 Å for DHA from 60 Ns to 200 Ns, 2.0 Å for EPA from 75 Ns to 200 Ns, and 2.2 Å for EPAS from 100 Ns to 200 Ns. Additionally, the potential energy of DHA (−1.069.250 eV) was higher compared with that of EPA (−1.069.247 eV) and EPAS (−1.069.220 eV). This data shows that DHA, EPA, and EPAS could stably inhibit COX-2 by blocking the transcriptional regulation of COX-2 via TYR348, VAL349, LEU384, TYR385, and TRP387.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"49 ","pages":"Article 101539"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000959/pdfft?md5=193620962fc821d638c5d23edf739b9b&pid=1-s2.0-S2352914824000959-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141481218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A one-dimensional convolutional neural network-based deep learning approach for predicting cardiovascular diseases","authors":"Dhafer G. Honi,&nbsp;Laszlo Szathmary","doi":"10.1016/j.imu.2024.101535","DOIUrl":"https://doi.org/10.1016/j.imu.2024.101535","url":null,"abstract":"<div><p>Early detection of cardiovascular diseases (CVDs) is crucial for managing cardiovascular diseases and improving patient outcomes. Deep neural networks have the potential to reduce the reliance on costly and time-consuming clinical tests, leading to cost savings for patients and healthcare systems. This study proposes the development of specialized convolutional neural networks for the automated selection of essential variables, employing various preprocessing procedures. It evaluates the approach using the UCI repository heart disease dataset, focusing on early-stage heart disease identification to enhance early prediction and intervention for CVD. To address the challenge of achieving higher accuracy, we introduce an approach using one-dimensional convolutional neural networks, incorporating extensive testing to optimize the network architecture and enhance predictive performance. Additionally, recognizing the impact of features on accuracy, a comprehensive data analysis was performed. Through a meticulous selection process, we identified and utilized key features that significantly influenced the accuracy of our model, contributing to more reliable predictions. Finally, cross-validation techniques were implemented to precisely evaluate the efficacy of our work. Numerous experiments were conducted to demonstrate the relevance of our research. The prediction accuracy was found to be 99.95% when employing a train–test approach, while it was approximately 98.53% when employing K-Fold cross-validation. In comparison to existing literature, our approach outperforms a recent best study that proposed a Catboost model, achieving an F1-score of about 92.3% and an average accuracy of 90.94%. This signifies a substantial improvement in predictive performance, with a percentage improvement of approximately 9.90% compared to the Catboost model.</p></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"49 ","pages":"Article 101535"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2352914824000911/pdfft?md5=c038dd79fdd8c5c503fbc451fc6301c6&pid=1-s2.0-S2352914824000911-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141483833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}