1
|
Zubair M. Clinical applications of artificial intelligence in identification and management of bacterial infection: Systematic review and meta-analysis. Saudi J Biol Sci 2024; 31:103934. [PMID: 38304541 PMCID: PMC10831261 DOI: 10.1016/j.sjbs.2024.103934] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Revised: 12/28/2023] [Accepted: 01/11/2024] [Indexed: 02/03/2024] Open
Abstract
Pneumonia is declared a global emergency public health crisis in children less than five age and the geriatric population. Recent advancements in deep learning models could be utilized effectively for the timely and early diagnosis of pneumonia in immune-compromised patients to avoid complications. This systematic review and meta-analysis utilized PRISMA guidelines for the selection of ten articles included in this study. The literature search was done through electronic databases including PubMed, Scopus, and Google Scholar from 1st January 2016 till 1 July 2023. Overall studies included a total of 126,610 images and 1706 patients in this meta-analysis. At a 95% confidence interval, for pooled sensitivity was 0.90 (0.85-0.94) and I2 statistics 90.20 (88.56 - 91.92). The pooled specificity for deep learning models' diagnostic accuracy was 0.89 (0.86---0.92) and I2 statistics 92.72 (91.50 - 94.83). I2 statistics showed low heterogeneity across studies highlighting consistent and reliable estimates, and instilling confidence in these findings for researchers and healthcare practitioners. The study highlighted the recent deep learning models single or in combination with high accuracy, sensitivity, and specificity to ensure reliable use for bacterial pneumonia identification and differentiate from other viral, fungal pneumonia in children and adults through chest x-rays and radiographs.
Collapse
Affiliation(s)
- Mohammad Zubair
- Department of Medical Microbiology, Faculty of Medicine, University of Tabuk, Tabuk 71491, Kingdom of Saudi Arabia
| |
Collapse
|
2
|
Liu CW, Wu FH, Hu YL, Pan RH, Lin CH, Chen YF, Tseng GS, Chan YK, Wang CL. Left ventricular hypertrophy detection using electrocardiographic signal. Sci Rep 2023; 13:2556. [PMID: 36781924 PMCID: PMC9924839 DOI: 10.1038/s41598-023-28325-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2022] [Accepted: 01/17/2023] [Indexed: 02/15/2023] Open
Abstract
Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From the medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that is often used as a preliminary diagnosis for the detection of heart disease. Nowadays, there are many criteria for assessing LVH by ECG. These criteria usually include that voltage combination of RS peaks in multi-lead ECG must be greater than one or more thresholds for diagnosis. We developed a system for detecting LVH using ECG signals by two steps: firstly, the R-peak and S-valley amplitudes of the 12-lead ECG were extracted to automatically obtain a total of 24 features and ECG beats of each case (LVH or non-LVH) were segmented; secondly, a back propagation neural network (BPN) was trained using a dataset with these features. Echocardiography (ECHO) was used as the gold standard for diagnosing LVH. The number of LVH cases (of a Taiwanese population) identified was 173. As each ECG sequence generally included 8 to 13 cycles (heartbeats) due to differences in heart rate, etc., we identified 1466 ECG cycles of LVH patients after beat segmentation. Results showed that our BPN model for detecting LVH reached the testing accuracy, precision, sensitivity, and specificity of 0.961, 0.958, 0.966 and 0.956, respectively. Detection performances of our BPN model, on the whole, outperform 7 methods using ECG criteria and many ECG-based artificial intelligence (AI) models reported previously for detecting LVH.
Collapse
Affiliation(s)
- Cheng-Wei Liu
- Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital Songshan Branch, National Defense Medical Center, Taipei, Taiwan
| | - Fu-Hsing Wu
- Bachelor Degree Program of Artificial Intelligence, National Taichung University of Science and Technology, Taichung, Taiwan
| | - Yu-Lun Hu
- Department of Management Information Systems, National Chung-Hsing University, Taichung, Taiwan
| | - Ren-Hao Pan
- La Vida Tec. Co. Ltd., Taichung, Taiwan
- Preventive Medicine Center, National Yang Ming Chiao Tung University, Taipei, Taiwan
- Department of Information Management, Tunghai University, Taichung, Taiwan
| | - Chuen-Horng Lin
- Department of Computer Science and Information Engineering, National Taichung University of Science and Technology, Taichung, Taiwan
| | - Yung-Fu Chen
- Department of Dental Technology and Materials Science, Central Taiwan University of Science and Technology, Taichung, Taiwan
| | - Guo-Shiang Tseng
- Division of Cardiology, Department of Internal Medicine, Taoyuan Armed Force General Hospital Hsinchu Branch, Hsinchu, Taiwan
| | - Yung-Kuan Chan
- Department of Management Information Systems, National Chung-Hsing University, Taichung, Taiwan.
| | - Ching-Lin Wang
- Department of Information Management, National Chin-Yi University of Technology, Taichung, Taiwan.
| |
Collapse
|
3
|
Design and Definition of a New Decision Support System Aimed to the Hierarchization of Patients Candidate to Be Admitted to Intensive Care Units. Healthcare (Basel) 2022; 10:healthcare10030587. [PMID: 35327064 PMCID: PMC8954209 DOI: 10.3390/healthcare10030587] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Revised: 03/15/2022] [Accepted: 03/17/2022] [Indexed: 12/02/2022] Open
Abstract
The triage processes prior to the assignation of healthcare resources in hospitals are some of the decision-making processes that more severely affect patients. This effect gets even worse in health emergency situations and intensive care units (ICUs). Aiming to facilitate the decision-making process, in this work the use of vague fuzzy numbers is proposed, aiming to define a multi-attribute patient hierarchization method to be used in emergency situations at hospital ICUs. The incorporation of fuzzy models allows for modelling the vagueness and uncertainty associated with decision criteria evaluation, with which more efficient support is provided to the decision-making process. After defining the methodology, the effectiveness of this new system for patient hierarchization is shown in a case study. As a consequence of that, it is proved that the integration of decision-support systems into healthcare environments results to be efficient and productive, suggesting that if a part of the decision process is supported by these systems, then the errors associated with wrong interpretations and/or diagnoses might be reduced.
Collapse
|