Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline

Zhengxiao Yang, Hao Zhou, Sudesh Srivastav, Jeffrey G. Shaffer, Kuukua E. Abraham, Samuel M. Naandam and Samuel Kakraba ()
Additional contact information
Zhengxiao Yang: Biostatistics and Data Science Graduate Program, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, 1440 Canal St., New Orleans, LA 70112, USA
Hao Zhou: Biostatistics and Data Science Graduate Program, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, 1440 Canal St., New Orleans, LA 70112, USA
Sudesh Srivastav: Department of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USA
Jeffrey G. Shaffer: Department of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USA
Kuukua E. Abraham: Department of Mathematics and Statistics, Minnesota State University, Mankato, MN 60001, USA
Samuel M. Naandam: Department of Mathematics, University of Cape Coast, Cape Coast 00233, Ghana
Samuel Kakraba: Department of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USA

Data, 2025, vol. 10, issue 1, 1-20

Abstract: Patient-level grouped data are prevalent in public health and medical fields, and multiple instance learning (MIL) offers a framework to address the challenges associated with this type of data structure. This study compares four data aggregation methods designed to tackle the grouped structure in classification tasks: post-mean, post-max, post-min, and pre-mean aggregation. We developed a customized AI pipeline that incorporates twelve machine learning algorithms along with the four aggregation methods to detect Parkinson’s disease (PD) using multiple voice recordings from individuals available in the UCI Machine Learning Repository, which includes 756 voice recordings from 188 PD patients and 64 healthy individuals. Seven performance metrics—accuracy, precision, sensitivity, specificity, F1 score, AUC, and MCC—were utilized for model evaluation. Various techniques, such as Bag Over-Sampling (BOS), cross-validation, and grid search, were implemented to enhance classification performance. Among the four aggregation methods, post-mean aggregation combined with XGBoost achieved the highest accuracy (0.880), F1 score (0.922), and MCC (0.672). Furthermore, we identified potential trends in selecting aggregation methods that are suitable for imbalanced data, particularly based on their differences in sensitivity and specificity. These findings provide meaningful implications for the further exploration of grouped imbalanced data.

Keywords: Parkinson’s disease (PD); machine learning (ML); artificial intelligence (AI); multiple instance learning (MIL); data aggregation; classification; supervised learning; comparative study (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/10/1/4/pdf (application/pdf)
https://www.mdpi.com/2306-5729/10/1/4/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:10:y:2025:i:1:p:4-:d:1558930

Access Statistics for this article

Data is currently edited by Ms. Cecilia Yang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().