An interpretable machine learning model for diagnosis of Alzheimer's disease
We present an interpretable machine learning model for medical diagnosis called sparse high-order interaction model with rejection option (SHIMR). A decision tree explains to a patient the diagnosis with a long rule (i.e., conjunction of many intervals), while SHIMR employs a weighted sum of short r...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2019-03-01
|
Series: | PeerJ |
Subjects: | |
Online Access: | https://peerj.com/articles/6543.pdf |
id |
doaj-981e5ae1ea324b7bbddd345b53e4789e |
---|---|
record_format |
Article |
spelling |
doaj-981e5ae1ea324b7bbddd345b53e4789e2020-11-25T01:02:20ZengPeerJ Inc.PeerJ2167-83592019-03-017e654310.7717/peerj.6543An interpretable machine learning model for diagnosis of Alzheimer's diseaseDiptesh Das0Junichi Ito1Tadashi Kadowaki2Koji Tsuda3Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, JapanData Science Laboratory, hhc Data Creation Center, Eisai Co. Ltd., Tsukuba, JapanData Science Laboratory, hhc Data Creation Center, Eisai Co. Ltd., Tsukuba, JapanDepartment of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, JapanWe present an interpretable machine learning model for medical diagnosis called sparse high-order interaction model with rejection option (SHIMR). A decision tree explains to a patient the diagnosis with a long rule (i.e., conjunction of many intervals), while SHIMR employs a weighted sum of short rules. Using proteomics data of 151 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, SHIMR is shown to be as accurate as other non-interpretable methods (Sensitivity, SN = 0.84 ± 0.1, Specificity, SP = 0.69 ± 0.15 and Area Under the Curve, AUC = 0.86 ± 0.09). For clinical usage, SHIMR has a function to abstain from making any diagnosis when it is not confident enough, so that a medical doctor can choose more accurate but invasive and/or more costly pathologies. The incorporation of a rejection option complements SHIMR in designing a multistage cost-effective diagnosis framework. Using a baseline concentration of cerebrospinal fluid (CSF) and plasma proteins from a common cohort of 141 subjects, SHIMR is shown to be effective in designing a patient-specific cost-effective Alzheimer’s disease (AD) pathology. Thus, interpretability, reliability and having the potential to design a patient-specific multistage cost-effective diagnosis framework can make SHIMR serve as an indispensable tool in the era of precision medicine that can cater to the demand of both doctors and patients, and reduce the overwhelming financial burden of medical diagnosis.https://peerj.com/articles/6543.pdfDementiaInterpretable modelSparse high-order interactionAlzheimer’s disease (AD)Computer-aided diagnosis (CAD) modelSHIMR |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Diptesh Das Junichi Ito Tadashi Kadowaki Koji Tsuda |
spellingShingle |
Diptesh Das Junichi Ito Tadashi Kadowaki Koji Tsuda An interpretable machine learning model for diagnosis of Alzheimer's disease PeerJ Dementia Interpretable model Sparse high-order interaction Alzheimer’s disease (AD) Computer-aided diagnosis (CAD) model SHIMR |
author_facet |
Diptesh Das Junichi Ito Tadashi Kadowaki Koji Tsuda |
author_sort |
Diptesh Das |
title |
An interpretable machine learning model for diagnosis of Alzheimer's disease |
title_short |
An interpretable machine learning model for diagnosis of Alzheimer's disease |
title_full |
An interpretable machine learning model for diagnosis of Alzheimer's disease |
title_fullStr |
An interpretable machine learning model for diagnosis of Alzheimer's disease |
title_full_unstemmed |
An interpretable machine learning model for diagnosis of Alzheimer's disease |
title_sort |
interpretable machine learning model for diagnosis of alzheimer's disease |
publisher |
PeerJ Inc. |
series |
PeerJ |
issn |
2167-8359 |
publishDate |
2019-03-01 |
description |
We present an interpretable machine learning model for medical diagnosis called sparse high-order interaction model with rejection option (SHIMR). A decision tree explains to a patient the diagnosis with a long rule (i.e., conjunction of many intervals), while SHIMR employs a weighted sum of short rules. Using proteomics data of 151 subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, SHIMR is shown to be as accurate as other non-interpretable methods (Sensitivity, SN = 0.84 ± 0.1, Specificity, SP = 0.69 ± 0.15 and Area Under the Curve, AUC = 0.86 ± 0.09). For clinical usage, SHIMR has a function to abstain from making any diagnosis when it is not confident enough, so that a medical doctor can choose more accurate but invasive and/or more costly pathologies. The incorporation of a rejection option complements SHIMR in designing a multistage cost-effective diagnosis framework. Using a baseline concentration of cerebrospinal fluid (CSF) and plasma proteins from a common cohort of 141 subjects, SHIMR is shown to be effective in designing a patient-specific cost-effective Alzheimer’s disease (AD) pathology. Thus, interpretability, reliability and having the potential to design a patient-specific multistage cost-effective diagnosis framework can make SHIMR serve as an indispensable tool in the era of precision medicine that can cater to the demand of both doctors and patients, and reduce the overwhelming financial burden of medical diagnosis. |
topic |
Dementia Interpretable model Sparse high-order interaction Alzheimer’s disease (AD) Computer-aided diagnosis (CAD) model SHIMR |
url |
https://peerj.com/articles/6543.pdf |
work_keys_str_mv |
AT dipteshdas aninterpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT junichiito aninterpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT tadashikadowaki aninterpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT kojitsuda aninterpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT dipteshdas interpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT junichiito interpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT tadashikadowaki interpretablemachinelearningmodelfordiagnosisofalzheimersdisease AT kojitsuda interpretablemachinelearningmodelfordiagnosisofalzheimersdisease |
_version_ |
1725205472354500608 |