Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline
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 c...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Data |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5729/10/1/4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588681477619712 |
|---|---|
| author | Zhengxiao Yang Hao Zhou Sudesh Srivastav Jeffrey G. Shaffer Kuukua E. Abraham Samuel M. Naandam Samuel Kakraba |
| author_facet | Zhengxiao Yang Hao Zhou Sudesh Srivastav Jeffrey G. Shaffer Kuukua E. Abraham Samuel M. Naandam Samuel Kakraba |
| author_sort | Zhengxiao Yang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-2ba3eedcc72047959873f236a3698182 |
| institution | Kabale University |
| issn | 2306-5729 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Data |
| spelling | doaj-art-2ba3eedcc72047959873f236a36981822025-01-24T13:28:32ZengMDPI AGData2306-57292025-01-01101410.3390/data10010004Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence PipelineZhengxiao Yang0Hao Zhou1Sudesh Srivastav2Jeffrey G. Shaffer3Kuukua E. Abraham4Samuel M. Naandam5Samuel Kakraba6Biostatistics and Data Science Graduate Program, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, 1440 Canal St., New Orleans, LA 70112, USABiostatistics and Data Science Graduate Program, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, 1440 Canal St., New Orleans, LA 70112, USADepartment of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USADepartment of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USADepartment of Mathematics and Statistics, Minnesota State University, Mankato, MN 60001, USADepartment of Mathematics, University of Cape Coast, Cape Coast 00233, GhanaDepartment of Biostatistics and Data Science, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA 70112, USAPatient-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.https://www.mdpi.com/2306-5729/10/1/4Parkinson’s disease (PD)machine learning (ML)artificial intelligence (AI)multiple instance learning (MIL)data aggregationclassification |
| spellingShingle | Zhengxiao Yang Hao Zhou Sudesh Srivastav Jeffrey G. Shaffer Kuukua E. Abraham Samuel M. Naandam Samuel Kakraba Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline Data Parkinson’s disease (PD) machine learning (ML) artificial intelligence (AI) multiple instance learning (MIL) data aggregation classification |
| title | Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline |
| title_full | Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline |
| title_fullStr | Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline |
| title_full_unstemmed | Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline |
| title_short | Optimizing Parkinson’s Disease Prediction: A Comparative Analysis of Data Aggregation Methods Using Multiple Voice Recordings via an Automated Artificial Intelligence Pipeline |
| title_sort | optimizing parkinson s disease prediction a comparative analysis of data aggregation methods using multiple voice recordings via an automated artificial intelligence pipeline |
| topic | Parkinson’s disease (PD) machine learning (ML) artificial intelligence (AI) multiple instance learning (MIL) data aggregation classification |
| url | https://www.mdpi.com/2306-5729/10/1/4 |
| work_keys_str_mv | AT zhengxiaoyang optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT haozhou optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT sudeshsrivastav optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT jeffreygshaffer optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT kuukuaeabraham optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT samuelmnaandam optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline AT samuelkakraba optimizingparkinsonsdiseasepredictionacomparativeanalysisofdataaggregationmethodsusingmultiplevoicerecordingsviaanautomatedartificialintelligencepipeline |