1
|
Sheu RK, Chen LC, Wu CL, Pardeshi MS, Pai KC, Huang CC, Chen CY, Chen WC. Multi-Modal Data Analysis for Pneumonia Status Prediction Using Deep Learning (MDA-PSP). Diagnostics (Basel) 2022; 12:diagnostics12071706. [PMID: 35885612 PMCID: PMC9317409 DOI: 10.3390/diagnostics12071706] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2022] [Revised: 06/27/2022] [Accepted: 07/09/2022] [Indexed: 11/30/2022] Open
Abstract
Evaluating several vital signs and chest X-ray (CXR) reports regularly to determine the recovery of the pneumonia patients at general wards is a challenge for doctors. A recent study shows the identification of pneumonia by the history of symptoms and signs including vital signs, CXR, and other clinical parameters, but they lack predicting the recovery status after starting treatment. The goal of this paper is to provide a pneumonia status prediction system for the early affected patient’s discharge from the hospital within 7 days or late discharge more than 7 days. This paper aims to design a multimodal data analysis for pneumonia status prediction using deep learning classification (MDA-PSP). We have developed a system that takes an input of vital signs and CXR images of the affected patient with pneumonia from admission day 1 to day 3. The deep learning then classifies the health status improvement or deterioration for predicting the possible discharge state. Therefore, the scope is to provide a highly accurate prediction of the pneumonia recovery on the 7th day after 3-day treatment by the SHAP (SHapley Additive exPlanation), imputation, adaptive imputation-based preprocessing of the vital signs, and CXR image feature extraction using deep learning based on dense layers-batch normalization (BN) with class weights for the first 7 days’ general ward patient in MDA-PSP. A total of 3972 patients with pneumonia were enrolled by de-identification with an adult age of 71 mean ± 17 sd and 64% of them were male. After analyzing the data behavior, appropriate improvement measures are taken by data preprocessing and feature vectorization algorithm. The deep learning method of Dense-BN with SHAP features has an accuracy of 0.77 for vital signs, 0.92 for CXR, and 0.75 for the combined model with class weights. The MDA-PSP hybrid method-based experiments are proven to demonstrate higher prediction accuracy of 0.75 for pneumonia patient status. Henceforth, the hybrid methods of machine and deep learning for pneumonia patient discharge are concluded to be a better approach.
Collapse
Affiliation(s)
- Ruey-Kai Sheu
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
| | - Lun-Chi Chen
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
- Correspondence: ; Tel.: +886-04-2359-0415
| | - Chieh-Liang Wu
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung 40705, Taiwan;
- Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung 407224, Taiwan
- Department of Automatic Control Engineering, Feng Chia University, Taichung 407102, Taiwan
| | | | - Kai-Chih Pai
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
| | - Chien-Chung Huang
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
- Department of Critical Care Medicine, Taichung Veterans General Hospital, Taichung 40705, Taiwan;
| | - Chia-Yu Chen
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
| | - Wei-Cheng Chen
- Department of Computer Science, Tunghai University, Taichung 407224, Taiwan; (R.-K.S.); (K.-C.P.); (C.-C.H.); (C.-Y.C.); (W.-C.C.)
| |
Collapse
|
2
|
Cao B, Huang Y, She DY, Cheng QJ, Fan H, Tian XL, Xu JF, Zhang J, Chen Y, Shen N, Wang H, Jiang M, Zhang XY, Shi Y, He B, He LX, Liu YN, Qu JM. Diagnosis and treatment of community-acquired pneumonia in adults: 2016 clinical practice guidelines by the Chinese Thoracic Society, Chinese Medical Association. CLINICAL RESPIRATORY JOURNAL 2017; 12:1320-1360. [PMID: 28756639 PMCID: PMC7162259 DOI: 10.1111/crj.12674] [Citation(s) in RCA: 166] [Impact Index Per Article: 20.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/12/2017] [Accepted: 07/25/2017] [Indexed: 02/05/2023]
Abstract
Community‐acquired pneumonia (CAP) in adults is an infectious disease with high morbidity in China and the rest of the world. With the changing pattern in the etiological profile of CAP and advances in medical techniques in diagnosis and treatment over time, Chinese Thoracic Society of Chinese Medical Association updated its CAP guideline in 2016 to address the standard management of CAP in Chinese adults. Extensive and comprehensive literature search was made to collect the data and evidence for experts to review and evaluate the level of evidence. Corresponding recommendations are provided appropriately based on the level of evidence. This updated guideline covers comprehensive topics on CAP, including aetiology, antimicrobial resistance profile, diagnosis, empirical and targeted treatments, adjunctive and supportive therapies, as well as prophylaxis. The recommendations may help clinicians manage CAP patients more effectively and efficiently. CAP in pediatric patients and immunocompromised adults is beyond the scope of this guideline. This guideline is only applicable for the immunocompetent CAP patients aged 18 years and older. The recommendations on selection of antimicrobial agents and the dosing regimens are not mandatory. The clinicians are recommended to prescribe and adjust antimicrobial therapies primarily based on their local etiological profile and results of susceptibility testing, with reference to this guideline.
Collapse
Affiliation(s)
- Bin Cao
- National Clinical Research Center of Respiratory Diseases, Center for Respiratory Diseases, China-Japan Friendship Hospital, Capital Medical University, Beijing 100029, China
| | - Yi Huang
- Department of Respiratory and Critical Care Medicine, Changhai Hospital, the Second Military Medical University, Shanghai 200433, China
| | - Dan-Yang She
- Department of Respiratory and Critical Care Medicine, Chinese PLA General Hospital, Beijing 100853, China
| | - Qi-Jian Cheng
- Department of Respiratory and Critical Care Medicine, Ruijin Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200025, China
| | - Hong Fan
- Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Sichuan 610041, China
| | - Xin-Lun Tian
- Department of Pulmonary Medicine, Peking Union Medical College Hospital, Beijing 100730, China
| | - Jin-Fu Xu
- Department of Respiratory and Critical Care Medicine, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai 200433, China
| | - Jing Zhang
- Department of Respiratory and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai 200032, China
| | - Yu Chen
- Department of Respiratory and Critical Care Medicine, Shengjing Hospital, China Medical University, Shenyang 110004, China
| | - Ning Shen
- Department of Respiratory Medicine, Peking University Third Hospital, Beijing 100191, China
| | - Hui Wang
- Department of Laboratory Medicine, Peking University People's Hospital, Beijing 100044, China
| | - Mei Jiang
- State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Diseases, the First Affiliated Hospital of Guangzhou Medical University, Guangzhou 510120, China
| | - Xiang-Yan Zhang
- Department of Respiratory and Critical Care Medicine, Guizhou Provincial People's Hospital, Guizhou 550002, China
| | - Yi Shi
- Department of Respiratory and Critical Care Medicine, Jinling Hospital, Nanjing 210002, China
| | - Bei He
- Department of Respiratory Medicine, Peking University Third Hospital, Beijing 100191, China
| | - Li-Xian He
- Department of Respiratory and Critical Care Medicine, Zhongshan Hospital, Fudan University, Shanghai 200032, China
| | - You-Ning Liu
- Department of Respiratory and Critical Care Medicine, Chinese PLA General Hospital, Beijing 100853, China
| | - Jie-Ming Qu
- Department of Respiratory and Critical Care Medicine, Ruijin Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200025, China
| |
Collapse
|
3
|
Sirvent J, Carmen de la Torre M, Lorencio C, Taché A, Ferri C, Garcia-Gil J, Torres A. Predictive factors of mortality in severe community-acquired pneumonia: A model with data on the first 24h of ICU admission. Med Intensiva 2013; 37:308-15. [DOI: 10.1016/j.medin.2013.03.003] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2012] [Revised: 01/31/2013] [Accepted: 03/08/2013] [Indexed: 01/20/2023]
|
4
|
Woodhead M, Blasi F, Ewig S, Garau J, Huchon G, Ieven M, Ortqvist A, Schaberg T, Torres A, van der Heijden G, Read R, Verheij TJM. Guidelines for the management of adult lower respiratory tract infections--summary. Clin Microbiol Infect 2012; 17 Suppl 6:1-24. [PMID: 21951384 DOI: 10.1111/j.1469-0691.2011.03602.x] [Citation(s) in RCA: 196] [Impact Index Per Article: 15.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
This document is an update of Guidelines published in 2005 and now includes scientific publications through to May 2010. It provides evidence-based recommendations for the most common management questions occurring in routine clinical practice in the management of adult patients with LRTI. Topics include management outside hospital, management inside hospital (including community-acquired pneumonia (CAP), acute exacerbations of COPD (AECOPD), acute exacerbations of bronchiectasis) and prevention. The target audience for the Guideline is thus all those whose routine practice includes the management of adult LRTI.
Collapse
Affiliation(s)
- M Woodhead
- Department of Respiratory Medicine, Manchester Royal Infirmary, Oxford Road, Manchester, UK.
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
5
|
Woodhead M, Blasi F, Ewig S, Garau J, Huchon G, Ieven M, Ortqvist A, Schaberg T, Torres A, van der Heijden G, Read R, Verheij TJM. Guidelines for the management of adult lower respiratory tract infections--full version. Clin Microbiol Infect 2011; 17 Suppl 6:E1-59. [PMID: 21951385 PMCID: PMC7128977 DOI: 10.1111/j.1469-0691.2011.03672.x] [Citation(s) in RCA: 611] [Impact Index Per Article: 43.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
This document is an update of Guidelines published in 2005 and now includes scientific publications through to May 2010. It provides evidence-based recommendations for the most common management questions occurring in routine clinical practice in the management of adult patients with LRTI. Topics include management outside hospital, management inside hospital (including community-acquired pneumonia (CAP), acute exacerbations of COPD (AECOPD), acute exacerbations of bronchiectasis) and prevention. Background sections and graded evidence tables are also included. The target audience for the Guideline is thus all those whose routine practice includes the management of adult LRTI.
Collapse
Affiliation(s)
- M Woodhead
- Department of Respiratory Medicine, Manchester Royal Infirmary, Oxford Road, Manchester, UK.
| | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|