{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:35:27Z","timestamp":1792600527537,"version":"4.5.0"},"reference-count":52,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Parkinson\u2019s disease (PD) is a progressive neurological disorder that affects millions globally, posing significant challenges in early and accurate diagnosis. Recent advancements in machine learning (ML) offer promising approaches for addressing these challenges by enabling more precise and efficient PD predictions. This paper proposes an enhanced ML framework for PD prediction, integrating data balancing, feature selection, and explainable AI techniques. We evaluate nine different ML algorithms using a dataset of clinical and voice features. To address the class imbalance, we employ the Synthetic Minority Oversampling Technique (SMOTE) and NearMiss, comparing results to an imbalanced baseline. Feature engineering approaches, including Featurewiz, Tree based Feature Importance and the chi-square test, are utilized to identify key predictive features such as Pitch Period Entropy (PPE), Noise-to-Harmonic Ratio (NHR), and other voice biomarkers. Explainable AI (XAI) techniques (SHAP and LIME) interpret model decision-making and highlight influential features. The best-performing model, KNN with SMOTE, achieved 92% accuracy, F1-score 0.94, and a G-Mean of 0.95\u2014demonstrating balanced, reliable PD detection. While some models achieved higher accuracy on imbalanced data (up to 97%), their performance lacked sensitivity and balance. Our findings suggest that combining SMOTE with feature engineering and XAI substantially enhances model fairness, performance, and interpretability. This research advances PD prediction by providing an accurate and interpretable ML-based diagnostic tool to support early diagnosis and better patient management.<\/jats:p>","DOI":"10.1371\/journal.pone.0333418","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:52:56Z","timestamp":1761933176000},"page":"e0333418","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["An interpretable and balanced machine learning framework for Parkinson\u2019s disease prediction using feature engineering and explainable AI"],"prefix":"10.1371","volume":"20","author":[{"given":"Nasim Mahmud","family":"Nayan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Al Mamun","family":"Rana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Monirul","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tahmina","family":"Yasmin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-9038","authenticated-orcid":true,"given":"Jasim","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"pone.0333418.ref001","doi-asserted-by":"crossref","first-page":"109678","DOI":"10.1016\/j.mehy.2020.109678","article-title":"Parkinson disease classification using one against all based data sampling with the acoustic features from the speech signals","volume":"140","author":"K Polat","year":"2020","journal-title":"Med Hypotheses."},{"key":"pone.0333418.ref002","unstructured":"WHO. Launch of WHO\u2019s Parkinson disease technical brief; 2022."},{"key":"pone.0333418.ref003","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1016\/j.procs.2015.04.021","article-title":"A survey of big data analytics in healthcare and government","volume":"50","author":"J Archenaa","year":"2015","journal-title":"Proc Comput Sci."},{"issue":"2","key":"pone.0333418.ref004","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1007\/s10796-016-9641-2","article-title":"Big data and analytics in healthcare: Introduction to the special section","volume":"18","author":"A Kankanhalli","year":"2016","journal-title":"Inf Syst Front."},{"key":"pone.0333418.ref005","doi-asserted-by":"crossref","first-page":"37718","DOI":"10.1109\/ACCESS.2019.2906350","article-title":"Feature selection based on L1-norm support vector machine and effective recognition system for Parkinson\u2019s disease using voice recordings","volume":"7","author":"AU Haq","year":"2019","journal-title":"IEEE Access."},{"issue":"2","key":"pone.0333418.ref006","doi-asserted-by":"crossref","first-page":"329","DOI":"10.3390\/biom12020329","article-title":"Update on CSF biomarkers in Parkinson\u2019s disease","volume":"12","author":"EH Kwon","year":"2022","journal-title":"Biomolecules."},{"issue":"2","key":"pone.0333418.ref007","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1080\/0013791X.2017.1294718","article-title":"Evaluating the cost-effectiveness of an early detection of Parkinson\u2019s Disease through innovative technology","volume":"62","author":"DA Munoz","year":"2017","journal-title":"Eng Econ."},{"issue":"3","key":"pone.0333418.ref008","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1002\/ana.22311","article-title":"Cerebrospinal fluid biomarkers for Parkinson disease diagnosis and progression","volume":"69","author":"M Shi","year":"2011","journal-title":"Ann Neurol."},{"issue":"7","key":"pone.0333418.ref009","doi-asserted-by":"crossref","first-page":"209","DOI":"10.14704\/nq.2021.19.7.NQ21104","article-title":"A multiple feature selection based Parkinson\u2019s disease diagnostic system using deep learning neural network classifier","volume":"19","author":"DrN Suresh Kumar","year":"2021","journal-title":"nq."},{"issue":"10","key":"pone.0333418.ref010","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1038\/s41591-022-01932-x","article-title":"Artificial intelligence-enabled detection and assessment of Parkinson\u2019s disease using nocturnal breathing signals","volume":"28","author":"Y Yang","year":"2022","journal-title":"Nat Med."},{"issue":"1","key":"pone.0333418.ref011","first-page":"19","article-title":"Classification and clustering of Parkinson\u2019s and healthy control gait dynamics using LDA and K-means","volume":"21","author":"AK Bhoi","year":"2017","journal-title":"Int J Bioautom."},{"issue":"5","key":"pone.0333418.ref012","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1007\/s10916-016-0477-6","article-title":"A decision support system to improve medical diagnosis using a combination of k-medoids clustering based attribute weighting and SVM","volume":"40","author":"M Peker","year":"2016","journal-title":"J Med Syst."},{"issue":"1","key":"pone.0333418.ref013","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1038\/s41531-022-00431-7","article-title":"A meta-analysis of the diagnostic utility of biomarkers in cerebrospinal fluid in Parkinson\u2019s disease","volume":"8","author":"C Xiang","year":"2022","journal-title":"NPJ Parkinsons Dis."},{"issue":"1","key":"pone.0333418.ref014","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1186\/s12880-024-01335-z","article-title":"An improved method for diagnosis of Parkinson\u2019s disease using deep learning models enhanced with metaheuristic algorithm","volume":"24","author":"B Majhi","year":"2024","journal-title":"BMC Med Imaging."},{"issue":"1","key":"pone.0333418.ref015","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1212\/WNL.0000000000001098","article-title":"CSF biomarkers and clinical progression of Parkinson disease","volume":"84","author":"S Hall","year":"2015","journal-title":"Neurology."},{"issue":"1","key":"pone.0333418.ref016","first-page":"1","article-title":"Comparison analysis of GLCM and PCA on Parkinson\u2019s disease using structural MRI","volume":"12","author":"S Tomer","year":"2021","journal-title":"Int J Inform Retriev Res."},{"issue":"23","key":"pone.0333418.ref017","doi-asserted-by":"crossref","first-page":"2615","DOI":"10.3390\/diagnostics14232615","article-title":"Early detection of Parkinson\u2019s disease using AI techniques and image analysis","volume":"14","author":"M Ianculescu","year":"2024","journal-title":"Diagnostics (Basel)."},{"key":"pone.0333418.ref018","article-title":"Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection","author":"M Little","year":"2007","journal-title":"Nat Prec."},{"issue":"3","key":"pone.0333418.ref019","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/TITB.2011.2107916","article-title":"Feature selection for accelerometer-based posture analysis in Parkinson\u2019s disease","volume":"15","author":"L Palmerini","year":"2011","journal-title":"IEEE Trans Inf Technol Biomed."},{"key":"pone.0333418.ref020","doi-asserted-by":"crossref","first-page":"102452","DOI":"10.1016\/j.bspc.2021.102452","article-title":"An efficient dimensionality reduction method using filter-based feature selection and variational autoencoders on Parkinson\u2019s disease classification","volume":"66","author":"H Gunduz","year":"2021","journal-title":"Biomed Signal Process Control."},{"issue":"22","key":"pone.0333418.ref021","doi-asserted-by":"crossref","first-page":"15997","DOI":"10.1007\/s00521-022-07046-2","article-title":"A novel sample and feature dependent ensemble approach for Parkinson\u2019s disease detection","volume":"35","author":"L Ali","year":"2022","journal-title":"Neural Comput Applic."},{"issue":"1","key":"pone.0333418.ref022","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s13755-020-00104-w","article-title":"Bio-inspired dimensionality reduction for Parkinson\u2019s disease (PD) classification","volume":"8","author":"A Pasha","year":"2020","journal-title":"Health Inf Sci Syst."},{"issue":"17","key":"pone.0333418.ref023","doi-asserted-by":"crossref","first-page":"2816","DOI":"10.3390\/diagnostics13172816","article-title":"Parkinson\u2019s disease detection using filter feature selection and a genetic algorithm with ensemble learning","volume":"13","author":"AM Ali","year":"2023","journal-title":"Diagnostics (Basel)."},{"key":"pone.0333418.ref024","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang C, Jia Y, Wang P, Zhang X, Xie T. Simultaneous learning of speech feature and segment for classification of Parkinson disease. In: 2017 IEEE 19th international conference on e-health networking, applications and services (Healthcom), 2017. 1\u20136. http:\/\/dx.doi.org\/10.1109\/healthcom.2017.8210820 https:\/\/doi.org\/10.1109\/healthcom.2017.8210820","DOI":"10.1109\/HealthCom.2017.8210820"},{"key":"pone.0333418.ref025","doi-asserted-by":"crossref","first-page":"11","DOI":"10.52783\/jns.v14.1725","article-title":"Parkinsons disease prediction with spiral drawings and wave frequency using deep conformal neural networks","volume":"14","author":"S SasiRekha","year":"2025","journal-title":"J Neonatal Surg."},{"key":"pone.0333418.ref026","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1016\/j.procs.2018.05.154","article-title":"Predicting Severity Of Parkinson\u2019s Disease Using Deep Learning","volume":"132","author":"S Grover","year":"2018","journal-title":"Procedia Computer Science."},{"issue":"3","key":"pone.0333418.ref027","first-page":"2278","article-title":"Automatic recognition of Parkinson\u2019s Disease via artificial neural network and support vector machine","volume":"4","author":"A Sharma","year":"2014","journal-title":"Int J Innov Technol Explor Eng (IJITEE)."},{"issue":"8","key":"pone.0333418.ref028","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1109\/TNSRE.2018.2851787","article-title":"Smartphone allows capture of speech abnormalities associated with high risk of developing Parkinson\u2019s disease","volume":"26","author":"J Rusz","year":"2018","journal-title":"IEEE Trans Neural Syst Rehabil Eng."},{"issue":"7","key":"pone.0333418.ref029","doi-asserted-by":"crossref","first-page":"2566","DOI":"10.3390\/s22072566","article-title":"Long-term polygraphic monitoring through MEMS and charge transfer for low-power wearable applications","volume":"22","author":"A Manoni","year":"2022","journal-title":"Sensors (Basel)."},{"issue":"1","key":"pone.0333418.ref030","doi-asserted-by":"crossref","first-page":"4","DOI":"10.3390\/diagnostics15010004","article-title":"Parkinson\u2019s disease prediction: An attention-based multimodal fusion framework using handwriting and clinical data","volume":"15","author":"S Benredjem","year":"2024","journal-title":"Diagnostics."},{"key":"pone.0333418.ref031","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.eswa.2018.06.003","article-title":"Feature-driven machine learning to improve early diagnosis of Parkinson\u2019s disease","volume":"110","author":"L Parisi","year":"2018","journal-title":"Expert Syst Applic."},{"issue":"1","key":"pone.0333418.ref032","doi-asserted-by":"crossref","first-page":"13813","DOI":"10.1038\/s41598-024-64004-9","article-title":"Detection of Parkinson disease using multiclass machine learning approach","volume":"14","author":"S Srinivasan","year":"2024","journal-title":"Sci Rep."},{"issue":"10","key":"pone.0333418.ref033","doi-asserted-by":"crossref","first-page":"4849","DOI":"10.1007\/s00521-020-05233-7","article-title":"Multi-variate vocal data analysis for detection of Parkinson disease using deep learning","volume":"33","author":"G Nagasubramanian","year":"2020","journal-title":"Neural Comput Applic."},{"key":"pone.0333418.ref034","doi-asserted-by":"crossref","unstructured":"Karan B, Sahu SS, Mahto K. Stacked auto-encoder based time-frequency features of speech signal for Parkinson disease prediction. In: 2020 International conference on artificial intelligence and signal processing (AISP), 2020. 1\u20134. http:\/\/dx.doi.org\/10.1109\/aisp48273.2020.9073595 https:\/\/doi.org\/10.1109\/aisp48273.2020.9073595","DOI":"10.1109\/AISP48273.2020.9073595"},{"key":"pone.0333418.ref035","doi-asserted-by":"crossref","first-page":"107495","DOI":"10.1016\/j.cmpb.2023.107495","article-title":"Explainable machine learning models based on multimodal time-series data for the early detection of Parkinson\u2019s disease","volume":"234","author":"M Junaid","year":"2023","journal-title":"Comput Methods Programs Biomed."},{"issue":"5","key":"pone.0333418.ref036","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1615\/CritRevBiomedEng.2022044813","article-title":"Stack Ensemble Oriented Parkinson Disease Prediction Using Machine Learning Approaches Utilizing GridSearchCV-Based Hyper Parameter Tuning","volume":"50","author":"N Suroor","year":"2022","journal-title":"Crit Rev Biomed Eng."},{"issue":"50","key":"pone.0333418.ref037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5120\/ijca2023922617","article-title":"Date fruit classification with machine learning and explainable artificial intelligence","volume":"184","author":"Md Sahidullah","year":"2023","journal-title":"IJCA."},{"key":"pone.0333418.ref038","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkv468","article-title":"ClustVis: A web tool for visualizing clustering of multivariate data using principal component analysis and heatmap","volume":"43","author":"T Metsalu","year":"2015","journal-title":"Nucleic Acids Res."},{"issue":"5","key":"pone.0333418.ref039","article-title":"Exploratory big data statistical analysis the impact of people life\u2019s characteristics on their educational level","volume":"100","author":"SZ ABD Elhady","year":"2022","journal-title":"J Theor Appl Inform Technol."},{"issue":"1","key":"pone.0333418.ref040","article-title":"Comparison of four ML predictive models predictive analysis of BIG data","volume":"101","author":"SZ ABD Elhady","year":"2023","journal-title":"J Theor Appl Inform Technol."},{"key":"pone.0333418.ref041","doi-asserted-by":"crossref","unstructured":"Nayan NM, Islam A, Islam MU, Ahmed E, Hossain MM, Alam MZ. SMOTE oversampling and near miss undersampling based diabetes diagnosis from imbalanced dataset with XAI visualization. In: 2023 IEEE symposium on computers and communications (ISCC); 2023. p. 1\u20136. https:\/\/doi.org\/10.1109\/iscc58397.2023.10218281","DOI":"10.1109\/ISCC58397.2023.10218281"},{"key":"pone.0333418.ref042","doi-asserted-by":"crossref","unstructured":"Mustary S, Kashem MA, Khan MNI, Jewel FA, Islam MM, Islam S. LEACH based WSN classification using supervised machine learning algorithm. In: 2021 International conference on computer communication and informatics (ICCCI). IEEE; 2021. p. 1\u20135.","DOI":"10.1109\/ICCCI50826.2021.9457001"},{"issue":"3","key":"pone.0333418.ref043","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1016\/j.bbe.2022.07.002","article-title":"Enhanced decision tree induction using evolutionary techniques for Parkinson\u2019s disease classification","volume":"42","author":"M Ghane","year":"2022","journal-title":"Biocybern Biomed Eng."},{"issue":"2","key":"pone.0333418.ref044","first-page":"130","article-title":"Decision tree methods: Applications for classification and prediction","volume":"27","author":"Y-Y Song","year":"2015","journal-title":"Shanghai Arch Psychiatry."},{"key":"pone.0333418.ref045","doi-asserted-by":"crossref","first-page":"109126","DOI":"10.1016\/j.ress.2023.109126","article-title":"Support vector machine in structural reliability analysis: A review","volume":"233","author":"A Roy","year":"2023","journal-title":"Reliab Eng Syst Safety."},{"issue":"1","key":"pone.0333418.ref046","doi-asserted-by":"crossref","DOI":"10.1007\/s13721-023-00420-7","article-title":"A modified kNN algorithm to detect Parkinson\u2019s disease","volume":"12","author":"R Indu","year":"2023","journal-title":"Netw Model Anal Health Inform Bioinform."},{"key":"pone.0333418.ref047","doi-asserted-by":"crossref","unstructured":"Yadav D, Jain I. Comparative analysis of machine learning algorithms for Parkinson\u2019s disease prediction. In: 2022 6th international conference on intelligent computing and control systems (ICICCS); 2022. p. 1334\u20139. https:\/\/doi.org\/10.1109\/iciccs53718.2022.9788354","DOI":"10.1109\/ICICCS53718.2022.9788354"},{"key":"pone.0333418.ref048","doi-asserted-by":"crossref","first-page":"100285","DOI":"10.1016\/j.health.2023.100285","article-title":"A medical cyber-physical system for predicting maternal health in developing countries using machine learning","volume":"5","author":"MM Hossain","year":"2024","journal-title":"Healthcare Analytics."},{"key":"pone.0333418.ref049","first-page":"8938","article-title":"Fish survival prediction in an aquatic environment using random forest model","volume":"2252","author":"MM Islam","year":"2021","journal-title":"Int J Artif Intell."},{"issue":"4","key":"pone.0333418.ref050","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-023-10652-8","article-title":"Cost-sensitive learning for imbalanced medical data: A review","volume":"57","author":"I Araf","year":"2024","journal-title":"Artif Intell Rev."},{"key":"pone.0333418.ref051","doi-asserted-by":"crossref","first-page":"109511","DOI":"10.1016\/j.sigpro.2024.109511","article-title":"Pearson\u2013Matthews correlation coefficients for binary and multinary classification","volume":"222","author":"P Stoica","year":"2024","journal-title":"Signal Process."},{"key":"pone.0333418.ref052","doi-asserted-by":"crossref","unstructured":"Hosaain MM, Kashem MA, Nayan NM. Artificial intelligence-driven approach for predicting maternal health risk factors. In: 2024 9th South-East Europe design automation, computer engineering, computer networks and social media conference (SEEDA-CECNSM); 2024. p. 153\u20138.","DOI":"10.1109\/SEEDA-CECNSM63478.2024.00035"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:53:04Z","timestamp":1761933184000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0333418"}},"subtitle":[],"editor":[{"given":"Syed Nisar Hussain","family":"Bukhari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":52,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0333418","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,31]]}}}