Indonesian Journal of Electrical Engineering and Computer Science Vol. 32, No. 3, December 2023, pp. 1569~1579 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v32.i3.pp1569-1579  1569 Journal homepage: http://ijeecs.iaescore.com Local post-hoc interpretable machine learning model for prediction of dementia in young adults Vandana Sharma 1,2 , Divya Midhunchakkaravarthy 1 1 Department of Computer Science and Multimedia, Lincoln University College, Petaling Jaya, Malaysia 2 Computer Science Department, CHRIST (Deemed to be University), Delhi-NCR Campus, India Article Info ABSTRACT Article history: Received Jan 20, 2023 Revised Jul 8, 2023 Accepted Sep 1, 2023 Dementia is still the prevailing brain disease with late diagnosis. There is a large increase in dementia disease among young adults. The major reason is over indulgence of young adults on social media resulting in denial of disease and delayed clinical diagnosis. Dementia is preventable and curable if diagnosed at an early stage, however, no attempts are being made to mitigate dementia in young adults. Today artificial intelligence (AI) based advanced technology with real-life consultations in clinical or remote setups are proved beneficial and is used to detect dementia. Most AI-based test is dependent on computer-aided diagnosis (CAD) tools and uses non-invasive imaging technology such as magnetic resonance imaging (MRI) data for disease diagnosis. In this paper, a local post-hoc interpretable machine learning (LPIML) model for prediction of dementia in young adults is proposed. The performance parameters are computed and compared based on accuracy, specificity, precision, F1 score and recall. The proposed work yields 98.87% training accuracy on original images and 99.31% training accuracy on morphologically enhanced images. The performance results are intrinsic and intuitive in learning the prediction results of individual case. The adoption of the proposed work will accelerate the diagnosis process in the era of digital healthcare. Keywords: Artificial intelligence Brain diseases Convolutional neural network Classification model first Image segmentation techniques U-net structure This is an open access article under the CC BY-SA license. Corresponding Author: Vandana Sharma Department of Computer Science and Multimedia, Lincoln University College Petaling Jaya, Selangor, Malaysia Email: vandana.juyal@gmail.com, vandana.sharma@christuniversity.in 1. INTRODUCTION Strategic Market Research LLP [1] ongoing brain research it is projected to have a market share of 8 billion by 2028 with an approximate growth rate of 7.20%. The amount of money invested in brain research is growing exponentially which is nearly 8 billion US dollars in 2028. There are various factors affecting the human brain and its related diseases. At present several use cases related to memory loss can be seen. According to the world health organisation more than 55 million people are diagnosed with dementia, with a projection of a 10 million increase every year. Dementia, one of the most prevalent disease, is such that it has the potential to drain out the psychological space, social well-being, emotional outbursts and economical strain on the immediate family of the diseased. Dementia is a disease leading to the slow death of brain cells, eventually leading to memory loss. In the absence of awareness for the diseased, its early measurement tools, regulated policies, and lack of knowledge, sensitivity and awareness of caretaker, the number of people affected from dementia is expected to rise exponentially. The quantum of patients to be affected by 2050 with dementia is nearly 131 million. The measurement tools to diagnose population subjected to dementia is yet to be regulated and validated [2]. Motor impairment is one of the early symptoms for the diagnoses of dementia. Mikuła [3]