Compliance-Aware and Explainable GA-Optimized Neural Network for Cost Estimation in Safety-Critical Medical Software

Compliance-Aware and Explainable GA-Optimized Neural Network for Cost Estimation in Safety-Critical Medical Software | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Compliance-Aware and Explainable GA-Optimized Neural Network for Cost Estimation in Safety-Critical Medical Software Liangyu Li, Zulkefli Mansor, Fatin Filzahti Ismail, Xiaoyan Zhao, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7593580/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Accurate cost estimation is vital for medical software projects due to their safety-critical nature and strict compliance requirements. Traditional algorithmic models fail to capture nonlinear cost-driver interactions, while black-box machine learning approaches lack interpretability, limiting adoption in regulated contexts. To address this, we propose GA-BP-XAI, an explainable backpropagation neural network framework with genetic algorithm–based hyperparameter optimization. The framework integrates SHAP-and LIME-based interpretability to deliver transparent, auditable predictions. Using a dataset of 1,200 anonymized medical software projects, GA-BP-XAI reduces MAE by 11.6% and improves R 2 from 0.902 to 0.927 compared with standard BP, outperforming strong baselines such as Linear Regression, Random Forest, and XGBoost. Explainability results highlight domain-relevant drivers including FunctionPoints, ComplianceLevel, and IntegrationComplexity, consistent with expert knowledge. These results demonstrate that GA-BP-XAI achieves both state-of-the-art predictive accuracy and regulatory-aligned transparency, supporting trustworthy decision-making in compliance-driven, high-stakes environments. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Medical Software Engineering Cost Estimation Genetic Algorithm Backpropagation Neural Network Explainable AI Full Text Additional Declarations No competing interests reported. Supplementary Files file.zip DataAvailabilityStatement.doc Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7593580","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":521685335,"identity":"b9192763-e756-4d30-a6a2-edd63cd31685","order_by":0,"name":"Liangyu Li","email":"data:image/png;base64,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","orcid":"","institution":"Universiti Kebangsaan Malaysia","correspondingAuthor":true,"prefix":"","firstName":"Liangyu","middleName":"","lastName":"Li","suffix":""},{"id":521685336,"identity":"53303baa-c4aa-47f1-aa90-7d577274d722","order_by":1,"name":"Zulkefli Mansor","email":"","orcid":"","institution":"Universiti Kebangsaan Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Zulkefli","middleName":"","lastName":"Mansor","suffix":""},{"id":521685337,"identity":"0193752f-8b96-4d67-9639-efd47ddd0750","order_by":2,"name":"Fatin Filzahti Ismail","email":"","orcid":"","institution":"Universiti Kebangsaan Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Fatin","middleName":"Filzahti","lastName":"Ismail","suffix":""},{"id":521685338,"identity":"92ee4d8d-537c-4185-b736-05ea171ef1c1","order_by":3,"name":"Xiaoyan Zhao","email":"","orcid":"","institution":"Universiti Kebangsaan Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyan","middleName":"","lastName":"Zhao","suffix":""},{"id":521685339,"identity":"1ceb7aa3-28a1-463f-9909-7930dc2d9be4","order_by":4,"name":"Xuwei Guo","email":"","orcid":"","institution":"Universiti Kebangsaan Malaysia","correspondingAuthor":false,"prefix":"","firstName":"Xuwei","middleName":"","lastName":"Guo","suffix":""},{"id":521685340,"identity":"cbe41480-6fed-4e1b-bd3e-fdfad1b165ae","order_by":5,"name":"Hao Sun","email":"","orcid":"","institution":"University College London","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Sun","suffix":""},{"id":521685341,"identity":"23abfb04-e0d1-4f5b-89c8-421fb06bb6ee","order_by":6,"name":"Yuzhe Jing","email":"","orcid":"","institution":"Kyungil University","correspondingAuthor":false,"prefix":"","firstName":"Yuzhe","middleName":"","lastName":"Jing","suffix":""},{"id":521685342,"identity":"5a651028-d61b-46dd-b99a-cb6946ca7080","order_by":7,"name":"Yanhui Xu","email":"","orcid":"","institution":"Peoples’ Friendship University of Russia","correspondingAuthor":false,"prefix":"","firstName":"Yanhui","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2025-09-11 15:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7593580/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7593580/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92381871,"identity":"73b2bac2-79da-4e08-86e2-9ae465fbf88e","added_by":"auto","created_at":"2025-09-29 06:23:57","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":298110,"visible":true,"origin":"","legend":"","description":"","filename":"main2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7593580/v1/0d5f4e3723d85849982e49bb.pdf"},{"id":92381838,"identity":"bd81bd44-33c2-4c12-ab0d-4d9b474546d7","added_by":"auto","created_at":"2025-09-29 06:23:56","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10811,"visible":true,"origin":"","legend":"","description":"","filename":"6b184e7e4f674129af4df01d3b76211f.json","url":"https://assets-eu.researchsquare.com/files/rs-7593580/v1/96860b0316490625453782b8.json"},{"id":101490511,"identity":"d4539f96-f30a-44c2-b35e-217bda466c48","added_by":"auto","created_at":"2026-01-30 09:58:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":357316,"visible":true,"origin":"","legend":"","description":"","filename":"main2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7593580/v1_covered_abecb1b7-9b38-4b00-aa7a-81d96d30602a.pdf"},{"id":92381839,"identity":"08815716-f785-4d2f-aec0-42451350af62","added_by":"auto","created_at":"2025-09-29 06:23:56","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2250580,"visible":true,"origin":"","legend":"","description":"","filename":"file.zip","url":"https://assets-eu.researchsquare.com/files/rs-7593580/v1/fc8b779031b1aa686c81985f.zip"},{"id":92382314,"identity":"b71fff5d-ab5b-4f99-9068-392f858b77c1","added_by":"auto","created_at":"2025-09-29 06:31:56","extension":"doc","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":11264,"visible":true,"origin":"","legend":"","description":"","filename":"DataAvailabilityStatement.doc","url":"https://assets-eu.researchsquare.com/files/rs-7593580/v1/466d3819483f4b30ef852198.doc"}],"financialInterests":"No competing interests reported.","formattedTitle":"Compliance-Aware and Explainable GA-Optimized Neural Network for Cost Estimation in Safety-Critical Medical Software","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Medical Software Engineering, Cost Estimation, Genetic Algorithm, Backpropagation Neural Network, Explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-7593580/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7593580/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate cost estimation is vital for medical software projects due to their safety-critical nature and strict compliance requirements. Traditional algorithmic models fail to capture nonlinear cost-driver interactions, while black-box machine learning approaches lack interpretability, limiting adoption in regulated contexts. To address this, we propose GA-BP-XAI, an explainable backpropagation neural network framework with genetic algorithm–based hyperparameter optimization. The framework integrates SHAP-and LIME-based interpretability to deliver transparent, auditable predictions. Using a dataset of 1,200 anonymized medical software projects, GA-BP-XAI reduces MAE by 11.6% and improves R 2 from 0.902 to 0.927 compared with standard BP, outperforming strong baselines such as Linear Regression, Random Forest, and XGBoost. Explainability results highlight domain-relevant drivers including FunctionPoints, ComplianceLevel, and IntegrationComplexity, consistent with expert knowledge. These results demonstrate that GA-BP-XAI achieves both state-of-the-art predictive accuracy and regulatory-aligned transparency, supporting trustworthy decision-making in compliance-driven, high-stakes environments.","manuscriptTitle":"Compliance-Aware and Explainable GA-Optimized Neural Network for Cost Estimation in Safety-Critical Medical Software","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-29 06:23:50","doi":"10.21203/rs.3.rs-7593580/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f8155104-557d-4a51-9665-b46279e16889","owner":[],"postedDate":"September 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55449415,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":55449416,"name":"Physical sciences/Engineering"},{"id":55449417,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-01-30T09:55:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-29 06:23:50","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7593580","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7593580","identity":"rs-7593580","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}