{"id":2458,"date":"2023-04-10T10:25:38","date_gmt":"2023-04-10T02:25:38","guid":{"rendered":"https:\/\/www.bebi.ntu.edu.tw\/?p=2458"},"modified":"2023-04-10T10:25:38","modified_gmt":"2023-04-10T02:25:38","slug":"%e7%94%9f%e9%86%ab%e9%9b%bb%e8%b3%87%e6%89%80%e6%95%99%e5%b8%ab%e7%a0%94%e7%a9%b6%e4%ba%ae%e9%bb%9e-112%e5%b9%b44%e6%9c%88%e4%bb%bd%e3%80%8c%e9%82%b1%e9%8a%98%e7%ab%a0%e6%95%99%e6%8e%88%e3%80%8d","status":"publish","type":"post","link":"https:\/\/www.bebi.ntu.edu.tw\/?p=2458","title":{"rendered":"\u751f\u91ab\u96fb\u8cc7\u6240\u6559\u5e2b\u7814\u7a76\u4eae\u9ede-112\u5e744\u6708\u4efd\u300c\u90b1\u9298\u7ae0\u6559\u6388\u300d"},"content":{"rendered":"<p>\u7814\u7a76\u4e3b\u984c\uff1a\u900f\u904e\u6a5f\u5668\u5b78\u7fd2\u5efa\u7acb\u963f\u8332\u6d77\u9ed8\u75c7\u81e8\u5e8a\u5206\u985e\u6a21\u578b<br \/>\n\u64b0\u5beb\uff1a\u5b78\u751f\u66fe\u5b50\u6d0b<\/p>\n<p>\u96a8\u8457\u5168\u7403\u4eba\u53e3\u7d50\u69cb\u6539\u8b8a\uff0c\u9ad8\u9f61\u5316\u5df2\u6210\u70ba\u7576\u4eca\u5168\u7403\u5df2\u958b\u767c\u570b\u5bb6\u9762\u81e8\u7684\u4e00\u5927\u6311\u6230\uff0c\u5c0d\u65bc\u5065\u5eb7\u4fdd\u96aa\u3001\u793e\u6703\u798f\u5229\u653f\u7b56\u4e43\u81f3\u65bc\u7d93\u6fdf\u6578\u64da\u8207\u6587\u5316\u50f9\u503c\u7b49\u65b9\u9762\u7686\u7522\u751f\u91cd\u5927\u5f71\u97ff\u3002\u5176\u4e2d\u96a8\u5e74\u9f61\u589e\u9577\uff0c\u4eba\u9ad4\u7684\u5668\u5b98\u8207\u7d44\u7e54\u4e5f\u6703\u96a8\u4e4b\u8001\u5316\u3002\u4ee5\u795e\u7d93\u7cfb\u7d71\u70ba\u4f8b\uff0c\u53ef\u80fd\u6703\u5c0e\u81f4\u795e\u7d93\u5143\u7684\u8870\u9000\u8207\u840e\u7e2e\uff0c\u795e\u7d93\u50b3\u5c0e\u901f\u5ea6\u6e1b\u6162\uff0c\u795e\u7d93\u7d30\u80de\u518d\u751f\u80fd\u529b\u4e0b\u964d\u7b49\u554f\u984c\uff0c\u5f9e\u800c\u589e\u52a0\u795e\u7d93\u75be\u75c5\u767c\u751f\u7684\u98a8\u96aa\uff0c\u5982\u5e15\u91d1\u68ee\u6c0f\u75c7\u8207\u963f\u8332\u6d77\u9ed8\u75c7\uff08Alzheimer\u2019s disease, AD\uff09\u7b49\u3002\u70ba\u56e0\u61c9\u9ad8\u9f61\u5316\u793e\u6703\u5c0e\u81f4\u4e4b\u795e\u7d93\u75be\u75c5\u76f8\u95dc\u6311\u6230\uff0c\u53ca\u65e9\u767c\u73fe\u795e\u7d93\u75be\u75c5\u4e26\u4e14\u9032\u884c\u5c0d\u61c9\u7684\u6cbb\u7642\u4ee5\u63a7\u5236\u75c7\u72c0\u4e43\u5341\u5206\u91cd\u8981\u3002\u800c\u90b1\u6559\u6388\u4f5c\u70ba\u795e\u7d93\u79d1\u91ab\u5e2b\uff0c\u540c\u6642\u4e5f\u81f4\u529b\u65bc\u5931\u667a\u75c7\u7684\u76f8\u95dc\u7814\u7a76\uff0c\u4ed6\u4e5f\u5e36\u9818\u7814\u7a76\u5718\u968a\u6536\u96c6\u81e8\u5e8a\u8cc7\u6599\u4e26\u65bc\u53bb\u5e74\u91dd\u5c0d\u963f\u8332\u6d77\u9ed8\u75c7\u7684\u5206\u985e\u767c\u8868\u76f8\u95dc\u7814\u7a76\u6210\u679c [1]\u3002<\/p>\n<p>\u963f\u8332\u6d77\u9ed8\u75c7\u662f\u4e00\u7a2e\u6162\u6027\u795e\u7d93\u9000\u5316\u6027\u75be\u75c5\uff0c\u662f\u5931\u667a\u75c7\u4e2d\u5e38\u898b\u7684\u4e00\u7a2e\uff0c\u73fe\u4ecd\u7121\u6839\u6cbb\u7684\u65b9\u6cd5\u3002\u5176\u7279\u5fb5\u70ba\u5927\u8166\u4e2d\u90e8\u5206\u795e\u7d93\u7d30\u80de\u8207\u795e\u7d93\u5143\u4e4b\u9593\u7684\u9023\u7d50\u7570\u5e38\u5f9e\u800c\u5f71\u97ff\u5927\u8166\u8a18\u61b6\u529f\u80fd\u3002\u75c7\u72c0\u5305\u542b\u8f15\u5fae\u77ed\u671f\u8a18\u61b6\u55aa\u5931\uff0c\u8a8d\u77e5\u969c\u7919\uff0c\u751a\u81f3\u53ef\u80fd\u5931\u53bb\u65e5\u5e38\u751f\u6d3b\u81ea\u7406\u80fd\u529b\u3002\u963f\u8332\u6d77\u9ed8\u75c7\u76f8\u95dc\u7684\u795e\u7d93\u75be\u75c5\u5305\u542b\u81ea\u89ba\u8a8d\u77e5\u8870\u9000\uff08subjective cognitive decline, SCD\uff09\u8207\u8f15\u5ea6\u8a8d\u77e5\u969c\u7919\uff08mild cognitive impairment, MCI\uff09\u3002SCD\u662f\u6307\u6c92\u6709\u5ba2\u89c0\u8a8d\u77e5\u969c\u7919\u7684\u524d\u63d0\u4e0b\uff0c\u60a3\u8005\u81ea\u89ba\u8a18\u61b6\u529b\u6216\u8a8d\u77e5\u80fd\u529b\u4e0b\u964d\u3002\u800cMCI \u5247\u662f\u4e00\u7a2e\u4ecb\u65bc\u6b63\u5e38\u8001\u5316\u8207\u963f\u8332\u6d77\u9ed8\u75c7\u9593\u7684\u72c0\u614b\uff0c\u5e38\u88ab\u8996\u70ba\u963f\u8332\u6d77\u9ed8\u75c7\u7684\u81e8\u5e8a\u524d\u671f\u3002\u6b64\u5916\u76f8\u95dc\u7814\u7a76\u8868\u660e\uff0c\u60a3\u6709SCD\u8207MCI\u7684\u75c5\u4eba\u6709\u8f03\u9ad8\u7f79\u60a3\u963f\u8332\u6d77\u9ed8\u75c7\u7684\u98a8\u96aa [2]\u3002\u70ba\u4e86\u65e9\u671f\u767c\u73fe\u4e26\u63d0\u4f9b\u963f\u8332\u6d77\u9ed8\u75c7\u7684\u6cbb\u7642\uff0c\u90b1\u6559\u6388\u8207\u5176\u7814\u7a76\u5718\u968a\u958b\u767c\u4e00\u6a5f\u5668\u5b78\u7fd2\u6a21\u578b\u4ee5\u5c0d\u6f5b\u5728\u75c5\u60a3\u9032\u884c\u5206\u985e\uff0c\u5224\u65b7\u5176\u5c6c\u4e3b\u89c0\u8a8d\u77e5\u8870\u9000\u3001\u8f15\u5ea6\u8a8d\u77e5\u969c\u7919\u6216\u963f\u8332\u6d77\u9ed8\u75c7\u3002<\/p>\n<p>\u90b1\u6559\u6388\u6536\u96c6\u5404\u5f0f\u81e8\u5e8a\u6578\u64da\u5305\u542b\u8840\u6db2\u6a23\u672c\u8207\u8166\u90e8\u5f71\u50cf\uff0c\u4e26\u7be9\u9078\u5341\u4e8c\u7a2e\u7279\u5fb5\uff0c\u4f5c\u70ba\u5f8c\u7e8c\u6a5f\u5668\u5b78\u7fd2\u6a21\u578b\u7684\u8f38\u5165\u3002\u5341\u4e8c\u7a2e\u7279\u5fb5\u5305\u62ecMMSE\uff08Mini-mental state examination\uff09\u8a55\u5206\u3001\u5e74\u9f61\u3001\u5de6\u53f3\u524d\u8449\u76ae\u8cea\u539a\u5ea6\u3001\u8840\u6f3f\u4e2d\u985e\u6fb1\u7c89\u86cb\u767d\uff08Amyloid \u03b2, A\u03b2\uff09\u3001tau \u86cb\u767d\u542b\u91cf\u8207\u6d77\u99ac\u8ff4\u9ad4\u7a4d\u7b49\u3002\u4e26\u4f7f\u7528\u96a8\u6a5f\u68ee\u6797\uff08Random forest, RF\uff09\u8207\u652f\u6301\u5411\u91cf\u6a5f\uff08Support vector machine, SVM\uff09\u5169\u7a2e\u6a5f\u5668\u5b78\u7fd2\u6a21\u578b\u3002\u900f\u904e\u8a08\u7b97\u63a5\u6536\u8005\u64cd\u4f5c\u7279\u5fb5\u66f2\u7dda\u4e0b\u9762\u7a4d\uff08Area under receiver operating characteristics curve, AUROC\uff09\u53ef\u767c\u73fe\u8a72\u6a21\u578b\u4e0d\u8ad6\u662f\u5728\u5206\u5225\u662f\u5426\u7f79\u60a3\u76f8\u95dc\u75be\u75c5\uff08MCI\u8207AD vs. \u63a7\u5236\u7d44\uff09\uff0c\u6291\u6216\u662f\u4e0d\u540c\u75c7\u72c0\u5169\u5169\u5206\u985e\uff08SCD\u3001MCI\u8207AD\uff09\u7684\u8868\u73fe\uff0c\u5169\u6a21\u578b\u5728\u4f7f\u7528\u6240\u9078\u4e4b\u5341\u4e8c\u7a2e\u7279\u5fb5\u7684\u5206\u985e\u8868\u73fe\u7686\u76f8\u7576\u826f\u597d\uff0c\u5176AUROC\u5206\u6578\u7686\u9ad8\u65bc0.85\u4e14\u6700\u9ad8\u6709\u9054\u52300.9\u7684\u5206\u985e\u6548\u679c\uff0c\u8aaa\u660e\u4f7f\u7528\u81e8\u5e8a\u4e0a\u6613\u65bc\u7372\u5f97\u7684\u5341\u4e8c\u7a2e\u7279\u5fb5\uff0c\u4e26\u7d50\u5408\u6a5f\u5668\u5b78\u7fd2\u6a21\u578b\u53ef\u4ee5\u6709\u6548\u7684\u5340\u5206\u963f\u8332\u6d77\u9ed8\u75c7\u8207\u5176\u4ed6\u76f8\u95dc\u75c7\u72c0\u5982MCI \u8207SCD\u3002\u7d9c\u5408\u4ee5\u4e0a\uff0c\u90b1\u6559\u6388\u8207\u5176\u7814\u7a76\u5718\u968a\u900f\u904e\u81e8\u5e8a\u6578\u64da\u7684\u641c\u96c6\u8207\u7be9\u9078\uff0c\u4e26\u7d50\u5408\u6a5f\u5668\u5b78\u7fd2\u7684\u6cd5\uff0c\u63d0\u51fa\u4e00\u826f\u597d\u7684\u5206\u985e\u6a21\u578b\uff0c\u4ee5\u5354\u52a9\u81e8\u5e8a\u4e0a\u7684\u8a3a\u65b7\uff0c\u4f7f\u60a3\u8005\u53ef\u4ee5\u65e9\u671f\u63a5\u53d7\u9810\u9632\u6027\u6cbb\u7642\u4ee5\u5ef6\u7de9\u75be\u75c5\u75c7\u72c0\u7684\u60e1\u5316\u3002<\/p>\n<p>Research Topic: Developing a machine learning model for Alzheimer\u2019s disease classification<\/p>\n<p>Due to the change of global population structure, aging society has become a major challenge of developed countries around the world nowadays. It has brought significant impact on not only health insurance and social welfare policies but economic growth and cultural values. With age, organs and tissues also age accordingly. Take nervous system as example, this will lead to neuronal decline and atrophy, slowed nerve conduction velocity, decreased neural regeneration ability, and increased risk of neurodegenerative diseases such as Parkinson\u2019s disease and Alzheimer\u2019s disease(AD). To address the challenges of neurodegenerative diseases caused by an aging society, it is important to detect and treat them early to control symptoms. Professor Chiu, as a neurologist who is also dedicated to research on dementia, leads a research team to collect clinical data and published relevant research results on the classification of Alzheimer\u2019s disease last year [1].<\/p>\n<p>Alzheimer\u2019s disease is a chronic neurodegenerative disorder, one of the common types of dementia and there is still no cure for it currently. The characteristics of AD is abnormal connections<br \/>\nbetween some nerve cells and neurons in the brain, which affects the memory function. Symptoms of AD include mild short-term memory loss, cognitive impairment and even loss of the ability to<br \/>\nperform daily activities. There are two neurological diseases, subjective cognitive decline (SCD) and mild cognitive impairment (MCI), related to Alzheimer\u2019s disease. SCD refers to a decline in memory of cognitive abilities in patients without objective cognitive impairment. On the other hand, MCI is a state between normal aging and Alzheimer\u2019s disease and is often considered as a<br \/>\npreclinical stage of Alzheimer\u2019s disease. Additionally, previous studies have shown that patients with SCD and MCI have a higher risk of developing Alzheimer\u2019s disease [2]. To detect and provide early treatment for Alzheimer\u2019s disease, Prof. Chiu and his research team developed a machine learning model to classify patients into normal, SCD, MCI or Alzheimer\u2019s disease.<\/p>\n<p>Professor Chiu collected various clinical data including blood samples and brain imaging. Twelve features are selected as inputs for the subsequent machine learning model including MMSE (Minimental state examination) score, age, cortical thickness of the left and right frontal lobes, plasma amyloid \u03b2 (\u0391\u03b2), tau protein content, and hippocampal volume. Two machine learning models, random forest (RF) and support vector machine (SVM), were used in this study to classify the patients. By calculating the area under receiver operating characteristics curve (AUROC), it was found that both models performed well in classifying whether there was related disease (MCI and AD vs. control group) and in two-class classification of different symptoms (SCD, MCI, and AD) using the selected twelve features. The AUROC scores were all higher than 0.85, and the highest classification effect reached 0.9, indicating that using the twelve clinically easily obtainable features combined with machine learning models can effectively distinguish Alzheimer\u2019s disease from other related symptoms such as MCI and SCD. In summary, Professor Chiu and his research team proposed a good machine learning classification model by collecting and selecting data to assist clinical diagnosis. Additionally, using the model to distinguish patients state can let patients receive preventive treatment earlier to delay the deterioration of disease symptoms.<\/p>\n[1] Chiu, S. I., Fan, L. Y., Lin, C. H., Chen, T. F., Lim, W. S., Jang, J. R., &#038; Chiu, M. J. (2022). Machine Learning-Based Classification of Subjective Cognitive Decline, Mild Cognitive<br \/>\nImpairment, and Alzheimer&#8217;s Dementia Using Neuroimage and Plasma Biomarkers. ACS chemical neuroscience, 13(23), 3263\u20133270. https:\/\/doi.org\/10.1021\/acschemneuro.2c00255<br \/>\n[2] Abner, E. L., Kryscio, R. J., Caban-Holt, A. M., &#038; Schmitt, F. A. (2015). Baseline subjective memory complaints associate with increased risk of incident dementia: the PREADVISE trial. The<br \/>\njournal of prevention of Alzheimer&#8217;s disease, 2(1), 11\u201316. https:\/\/doi.org\/10.14283\/jpad.2015.37<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7814\u7a76\u4e3b\u984c\uff1a\u900f\u904e\u6a5f\u5668\u5b78\u7fd2\u5efa\u7acb\u963f\u8332\u6d77\u9ed8\u75c7\u81e8\u5e8a\u5206\u985e\u6a21\u578b \u64b0\u5beb\uff1a\u5b78\u751f\u66fe\u5b50\u6d0b \u96a8\u8457\u5168\u7403\u4eba\u53e3\u7d50\u69cb\u6539\u8b8a\uff0c\u9ad8\u9f61\u5316\u5df2\u6210\u70ba\u7576\u4eca\u5168\u7403 [&#8230;]\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[19],"tags":[],"class_list":["post-2458","post","type-post","status-publish","format-standard","hentry","category-award"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/posts\/2458","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2458"}],"version-history":[{"count":1,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/posts\/2458\/revisions"}],"predecessor-version":[{"id":2459,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=\/wp\/v2\/posts\/2458\/revisions\/2459"}],"wp:attachment":[{"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2458"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2458"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bebi.ntu.edu.tw\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2458"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}