Advanced International Journal for Research

E-ISSN: 3048-7641   •   Impact Factor: 9.11

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 3 (May-June 2026) Submit your research before last 3 days of June to publish your research paper in the issue of May-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 3
May-June 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar Wiki for Call for Papers WorldCat Zenodo

Random-forest Based Prediction of Cognitive Impairment in Age Related Hearing Loss using Integrated Audiological and Neurocognitive Features

Author(s) vishaldeep kaur
Country India
Abstract Abstract
Background: Age related hearing loss (ARHL) is a major risk factor for dementia and it is a modifiable factor. However, there are few studies based on artificial intelligence to jointly model audiological and cognitive data for early risk prediction.
Objective: To develop and validate a machine learning model that predicts cognitive impairment and dementia risk in older adults with ARHL using combined audiological and neuropsychological features.
Methods: In a cross-sectional study of 93 adults aged ≥45 years with mild, moderate, or severe sensorineural ARHL, pure-tone and speech audiometry are combined with performance on the MMSE, MoCA, PGI Memory Scale, and Buschke Selective Reminding Test to construct a 54-feature dataset. Median imputation addresses missing values, and the data are split into stratified training, validation, and test sets in a 70:15:15 ratio. A Random Forest classifier with RandomizedSearchCV and three-fold stratified cross-validation is trained, with SMOTE applied to manage class imbalance. Model performance is evaluated using accuracy, precision, recall, macro- and weighted-F1 scores, and class-wise ROC AUC, while calibration and prediction confidence are examined across severity levels.
Results: The final model achieved 95–98% training accuracy, 88–92% validation accuracy, and 85–90% test accuracy across severity based tasks, with particularly strong F1 scores for severe cognitive impairment (0.88–0.95). ROC AUC values ranged from 0.93 to 1.00 across classes, indicating excellent discrimination. Among 54 features, speech discrimination score (SDS) showed the highest importance, followed by 1000 Hz pure tone thresholds and global cognitive scores (MMSE, MoCA), with MoCA delayed recall among the top predictors. Model outputs included probability based prediction confidence and per patient top feature explanations, supporting clinical interpretability.
Conclusions: A Random Forest model integrating routine audiological and cognitive tests can accurately stratify dementia risk and cognitive impairment severity in ARHL, with SDS and specific memory domains emerging as key predictors. These findings support embedding explainable AI models into audiology and geriatric workflows for early identification and triage of cognitively vulnerable, hearing impaired adults.
Keywords Age related hearing loss (ARHL) ,dementia, cognitive impairment, MMSE, MoCA, PGI Memory Scale, and Buschke Selective Reminding Test,Random Forest model, Artificial Intelligence
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 3, May-June 2026
Published On 2026-06-13
DOI https://doi.org/10.63363/aijfr.2026.v07i03.6372
View / Download PDF File

Share this



E-ISSN 3048-7641
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 4Cover Page Vol 7 Isu 3Cover Page Vol 7 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AIJFR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9898-79-39-59 editor@aijfr.com