1
|
Wang H, Sheng L, Xu S, Jin Y, Jin X, Qiao S, Chen Q, Xing W, Zhao Z, Yan J, Mao G, Xu X. Develop a diagnostic tool for dementia using machine learning and non-imaging features. Front Aging Neurosci 2022; 14:945274. [PMID: 36092811 PMCID: PMC9461143 DOI: 10.3389/fnagi.2022.945274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2022] [Accepted: 08/08/2022] [Indexed: 11/13/2022] Open
Abstract
BackgroundEarly identification of Alzheimer’s disease or mild cognitive impairment can help guide direct prevention and supportive treatments, improve outcomes, and reduce medical costs. Existing advanced diagnostic tools are mostly based on neuroimaging and suffer from certain problems in cost, reliability, repeatability, accessibility, ease of use, and clinical integration. To address these problems, we developed, evaluated, and implemented an early diagnostic tool using machine learning and non-imaging factors.Methods and resultsA total of 654 participants aged 65 or older from the Nursing Home in Hangzhou, China were identified. Information collected from these patients includes dementia status and 70 demographic, cognitive, socioeconomic, and clinical features. Logistic regression, support vector machine (SVM), neural network, random forest, extreme gradient boosting (XGBoost), least absolute shrinkage and selection operator (LASSO), and best subset models were trained, tuned, and internally validated using a novel double cross validation algorithm and multiple evaluation metrics. The trained models were also compared and externally validated using a separate dataset with 1,100 participants from four communities in Zhejiang Province, China. The model with the best performance was then identified and implemented online with a friendly user interface. For the nursing dataset, the top three models are the neural network (AUROC = 0.9435), XGBoost (AUROC = 0.9398), and SVM with the polynomial kernel (AUROC = 0.9213). With the community dataset, the best three models are the random forest (AUROC = 0.9259), SVM with linear kernel (AUROC = 0.9282), and SVM with polynomial kernel (AUROC = 0.9213). The F1 scores and area under the precision-recall curve showed that the SVMs, neural network, and random forest were robust on the unbalanced community dataset. Overall the SVM with the polynomial kernel was found to be the best model. The LASSO and best subset models identified 17 features most relevant to dementia prediction, mostly from cognitive test results and socioeconomic characteristics.ConclusionOur non-imaging-based diagnostic tool can effectively predict dementia outcomes. The tool can be conveniently incorporated into clinical practice. Its online implementation allows zero barriers to its use, which enhances the disease’s diagnosis, improves the quality of care, and reduces costs.
Collapse
Affiliation(s)
- Huan Wang
- Department of Biostatistics, The George Washington University, Washington, DC, United States
| | - Li Sheng
- Department of Mathematics, Drexel University, Philadelphia, PA, United States
| | - Shanhu Xu
- Department of Neurology, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Yu Jin
- Department of Neurology, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Xiaoqing Jin
- Department of Neurology, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Song Qiao
- Department of Neurology, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Qingqing Chen
- Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Wenmin Xing
- Zhejiang Provincial Key Lab of Geriatrics & Geriatrics Institute of Zhejiang Province, Department of Geriatrics, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Zhenlei Zhao
- Zhejiang Provincial Key Lab of Geriatrics & Geriatrics Institute of Zhejiang Province, Department of Geriatrics, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
| | - Jing Yan
- Zhejiang Provincial Key Lab of Geriatrics & Geriatrics Institute of Zhejiang Province, Department of Geriatrics, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
- *Correspondence: Jing Yan,
| | - Genxiang Mao
- Zhejiang Provincial Key Lab of Geriatrics & Geriatrics Institute of Zhejiang Province, Department of Geriatrics, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
- Genxiang Mao,
| | - Xiaogang Xu
- Zhejiang Provincial Key Lab of Geriatrics & Geriatrics Institute of Zhejiang Province, Department of Geriatrics, Affiliated Zhejiang Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China
- Xiaogang Xu,
| |
Collapse
|
2
|
Bissig D, Kaye J, Erten‐Lyons D. Validation of SATURN, a free, electronic, self-administered cognitive screening test. ALZHEIMER'S & DEMENTIA (NEW YORK, N. Y.) 2020; 6:e12116. [PMID: 33392382 PMCID: PMC7771179 DOI: 10.1002/trc2.12116] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/14/2020] [Revised: 10/19/2020] [Accepted: 10/27/2020] [Indexed: 11/28/2022]
Abstract
BACKGROUND Cognitive screening is limited by clinician time and variability in administration and scoring. We therefore developed Self-Administered Tasks Uncovering Risk of Neurodegeneration (SATURN), a free, public-domain, self-administered, and automatically scored cognitive screening test, and validated it on inexpensive (<$100) computer tablets. METHODS SATURN is a 30-point test including orientation, word recall, and math items adapted from the Saint Louis University Mental Status test, modified versions of the Stroop and Trails tasks, and other assessments of visuospatial function and memory. English-speaking neurology clinic patients and their partners 50 to 89 years of age were given SATURN, the Montreal Cognitive Assessment (MoCA), and a brief survey about test preferences. For patients recruited from dementia clinics (n = 23), clinical status was quantified with the Clinical Dementia Rating (CDR) scale. Care partners (n = 37) were assigned CDR = 0. RESULTS SATURN and MoCA scores were highly correlated (P < .00001; r = 0.90). CDR sum-of-boxes scores were well-correlated with both tests (P < .00001) (r = -0.83 and -0.86, respectively). Statistically, neither test was superior. Most participants (83%) reported that SATURN was easy to use, and most either preferred SATURN over the MoCA (47%) or had no preference (32%). DISCUSSION Performance on SATURN-a fully self-administered and freely available (https://doi.org/10.5061/dryad.02v6wwpzr) cognitive screening test-is well-correlated with MoCA and CDR scores.
Collapse
Affiliation(s)
- David Bissig
- Department of NeurologyUniversity of California–DavisSacramentoCaliforniaUSA
| | - Jeffrey Kaye
- Department of NeurologyOregon Health and Science UniversityPortlandOregonUSA
| | - Deniz Erten‐Lyons
- Department of NeurologyVeterans Affairs Medical CenterPortlandOregonUSA
| |
Collapse
|