新冠肺炎預後的人工智慧模型與單一醫學中心的肺癌篩檢成效

簡易檢索 / 詳目顯示

回結果列表

研究生：	吳智偉 Chih-Wei Wu
論文名稱：	新冠肺炎預後的人工智慧模型與單一醫學中心的肺癌篩檢成效 An artificial intelligence-based prognostic model of COVID-19 and a single-center experience of lung cancer screening
指導教授：	許藝瓊 Yi-Chiung Hsu
口試委員:
學位類別：	博士 Doctor
系所名稱：	生醫理工學院 - 生醫科學與工程學系 Department of Biomedical Sciences and Engineering
論文出版年：	2024
畢業學年度：	112
語文別：	中文
論文頁數：	97
中文關鍵詞：	新冠肺炎、人工智慧、胸部X光檢查、預後、死亡率、加護病房
外文關鍵詞：	COVID-19, Artificial intelligence, Chest X-rays, Prognosis, Mortality, Intensive care unit
相關次數：	點閱：17 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

背景: 台灣缺乏關於第一波新冠肺炎疫情的研究。本篇研究新冠肺炎重症的死亡危險因子與建立胸部X光的人工智慧的判讀模型。
方法: 本篇回溯性分析在西元二零二一年五月十五日至七月十五日之間在台北慈濟醫院的病歷資料。所有個案皆為插管使用呼吸器的病患。每一位病患都收錄四張胸部X光片，分別為第一張，插管前，插管後以及最嚴重。我們以移動網路第三版的方法來訓練人工智慧判讀模型，並且以交叉驗證方法來評估模型的表現。
結果: 本篇總共收錄了六十四位病患。整體死亡率為百分之四十五。從症狀發生到插管平均為八日。使用升壓藥，嚴重的X光指標（BRIXIA評分系統）是死亡的危險因子。人工智慧模型有準確的死亡預測能力，其四類X光的預測準確度值分別為0.88，0.92，0.92，0.94。
結論：呼吸衰竭而插管的新冠肺炎病患有高死亡率。使用升壓藥，嚴重的X光指標是死亡的危險因子。人工智慧模型有準確的死亡預測能力。

Background: The data of the first episode of the COVID-19 pandemic in Taiwan is scarce. We researched the risk factors of death among mechanically-ventilated patients with COVID-19 in Taiwan during the first episode of COVID-19. In addition, we are inspired to create a new artificial-intelligence-based death prognostication model by utilization of chest X-ray.
Method: We retrospectively extracted the medical data of patients with COVID-19 at Taipei Tzu Chi Hospital from May 15th to July 15th in 2021. We recruited patients who received invasive mechanical ventilation. The chest X-ray images of each recruited patient were assigned into four groups (first, before-intubation, post-intubation, and worst). The BRIXIA and percent opacification scores were reviewed by two pulmonologists. To set up a prognostication model, we used the MobilenetV3-Small model with “ImageNet” pretrained weights, followed by high Dropout regularization layers. We practiced the model with Five-Fold Cross-Validation to assess model efficacy.
Result: We finally recruited sixty-four patients. The overall death rate was forty-five percent. The median days since symptom commencement to endotracheal intubation was eight. Age, inferior academic degree, occurrence of COVID-19 complications, and a more severe achievement of the worst chest X-ray were linked to a higher death risk. The accuracy of the first, pre-intubation, post-intubation, and worst chest X-ray by the artificial-intelligence model were 0.88, 0.92, 0.92, and 0.94 respectively.

第ㄧ部分: 新冠肺炎預後的人工智慧模型                     頁次
中文提要..............................................i
英文提要..............................................ii
目錄.................................................iv
圖目錄................................................v
表目錄...............................................vi
一、        緒論......................................1
二、        研究內容與方法..............................8
   2-1      收案條件與資料搜集..........................8
   2-2      胸部X光影像分類............................9
   2-3      藥物治療準則...............................9
三、        資料統計分析的方法..........................11
   3-1      生物統計分析..............................11
   3-2      人工智慧方法..............................11
   3-3      人工智慧的數據準備.........................12
   3-4      倫理道德聲明..............................13
四、        研究結果..................................14
五、        討論.....................................16
六、        結論.....................................20
七、        參考文獻..................................21
八、        圖片.....................................25
九、        表格.....................................28
附錄一      BRIXIA score的範例........................37
附錄二      人工智能運算的數據準備.......................42
附錄三      新冠肺炎重症患者的其他疾病自然史..............44
附錄四      新冠台灣人工智慧預測死亡模型的其他效能指標......45

第二部分: 單一醫學中心的肺癌篩檢成效                     頁次
中文提要..............................................i 
英文提要.............................................ii
目錄.................................................iv
圖目錄................................................v
表目錄...............................................vi
一、        緒論......................................1
二、        研究內容與方法..............................7
   2-1      收案條件與資料搜集..........................7
   2-2      電腦斷層影像追蹤流程........................8
   2-3      影像判讀與處理.............................8
三、        資料統計分析的方法...........................10
   3-1      生物統計分析...............................10
   3-2      倫理道德聲明...............................10
四、        研究結果...................................11
五、        討論......................................14
六、        結論......................................20
七、        參考文獻...................................21
八、        圖片......................................24
九、        表格......................................28
                                

〔1〕M. Cascella, M. Rajnik, A. Aleem, S. C. Dulebohn, R.D. Napoli, Features, Evaluation, and Treatment of Coronavirus (COVID-19)., StatPearls Publishing, Last Update: August 18, 2023.
〔2〕台灣疾病管制中心。https://www.cdc.gov.tw/ at.
〔3〕Z.J. Lim and A. Subramaniam, “Case fatality rates for patients with COVID-19 requiring invasive mechanical ventilation. A meta-analysis.” American Journal of Respiratory and Critical Care Medicine, Vol 54, AMER THORACIC SOC, January 2021, pp. 54-66.
〔4〕A.Y. I and Y. Higashi, “Chest radiograph scoring alone or combined with other risk scores for predicting outcomes in COVID-19.” Radiology, Vol 302, No 2, RADIOLOGICAL SOC NORTH AMERICA (RSNA), February 2022, pp. 460-469.
〔5〕M. Balbi and A. Caroli, “Chest X-ray for predicting mortality and the need for ventilatory support in COVID-19 patients presenting to the emergency department.” European Radiology, Vol 31, SPRINGER, April 2021, pp. 1999-2012.
〔6〕A. Borghesi and R. Maroldi, “COVID-19 outbreak in Italy: experimental chest X-ray scoring system for quantifying and monitoring disease progression.” Radiologia Medica, Vol 125, No 5, SPRINGER-VERLAG ITALIA SRL, May 2020, pp. 509-513.
〔7〕C.J. Nicholson and L. Wooster, “Estimating risk of mechanical ventilation and in-hospital mortality among adult COVID-19 patients admitted to Mass General Brigham: the VICE and DICE scores.” EClinicalMedicine, Vol 33, ELSEVIER, March 2021, pp. 100765.
〔8〕S.R. Knight and A. Ho, “Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score.” British Medical Journal, Vol 370, BMJ PUBLISHING GROUP, September 2020, pp. m3339.
〔9〕P. Horby and W.S. Lim, “Dexamethasone in hospitalized patients with covid-19.” New England Journal of Medicine, Vol 384, No 8, MASSACHUSETTS MEDICAL SOC, February 2021, pp. 693-704.
〔10〕P. Horby and M. Campbell, “Tocilizumab in patients admitted to hospital with COVID-19 (RECOVERY): a randomised, controlled, open-label, platform trial.” Lancet, Vol 397, No 10285, ELSEVIER SCIENCE INC, May 2021, pp. 1637-1645.
〔11〕Y. Gu and D. Wang, “PaO2/FiO2 and IL-6 are risk factors of mortality for intensive care COVID-19 patients.” Scientific Reports, Vol 11, NATURE PORTFOLIO, April 2021, pp. 7334.
〔12〕E.C. Somers and G.A. Eschenauer, “Tocilizumab for treatment of mechanically ventilated patients with COVID-19.” Clinical Infectious Diseases, Vol 73, OXFORD UNIV PRESS INC, July 2020, pp. e445-e454.
〔13〕M.T.U. Schuijt and M.J. Schultz, “PRoVENT–COVID Collaborative Group Association of intensity of ventilation with 28-day mortality in COVID-19 patients with acute respiratory failure: insights from the PRoVENT-COVID study.” Critical Care, Vol 25, BMC, August 2021, pp. 283.
〔14〕SGLH. Nijbroek and L. Hol, “Low tidal volume ventilation is associated with mortality in COVID-19 patients—insights from the PRoVENT-COVID study.” Journal of Critical Care, Vol 70, W B SAUNDERS CO-ELSEVIER INC, August 2022, pp. 154047.
〔15〕M.C. Shelhamer and P.D. Wesson, “Prone positioning in moderate to severe acute respiratory distress syndrome due to COVID-19: a cohort study and analysis of physiology.” Journal of Intensive Care Medicine, Vol 36, SAGE PUBLICATIONS INC, February 2021, pp. 241-252.
〔16〕S.C. Auld and C.S. Mark, “ICU and ventilator mortality among critically ill adults with coronavirus disease 2019.” Critical Care Medicine, Vol 48, LIPPINCOTT WILLIAMS & WILKINS, September 2020, pp. e799-e804.
〔17〕A.A. Mutair and A.A. Mutairi, “Clinical predictors of COVID-19 mortality among patients in intensive care units: a retrospective study.” International Journal of General Medicine, Vol 14, DOVE MEDICAL PRESS LTD, July 2021, pp. 3719-3728.
〔18〕Z. Jiao and J.W. Choi, “Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study.” Lancet Digital Health, Vol 3, ELSEVIER, May 2021, pp. e286-e294.
〔19〕P. Soda and N.C. D'Amico, “AIforCOVID: predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study.” Medical Image Analysis, Vol 74, ELSEVIER, December 2021, pp. 102216.
〔20〕I. Dayan and H.R. Roth, “Federated learning for predicting clinical outcomes in patients with COVID-19.” Nature Medicine, Vol 27, NATURE PORTFOLIO, October 2021, pp. 1735-1743.
〔21〕B.H.S. van der Velden and H.J. Kuijf, “Explainable artificial intelligence (XAI) in deep learning-based medical image analysis.” Medical Image Analysis, Vol 79, ELSEVIER, July 2022, pp. 102470.

簡易檢索 / 詳目顯示

相關論文