1
|
Wang Q, Zou T, Zeng X, Bao T, Yin W. Establishment of seven lung ultrasound phenotypes: a retrospective observational study of an LUS registry. BMC Pulm Med 2024; 24:483. [PMID: 39363211 PMCID: PMC11450992 DOI: 10.1186/s12890-024-03299-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2024] [Accepted: 09/19/2024] [Indexed: 10/05/2024] Open
Abstract
BACKGROUND Lung phenotypes have been extensively utilized to assess lung injury and guide precise treatment. However, current phenotypic evaluation methods rely on CT scans and other techniques. Although lung ultrasound (LUS) is widely employed in critically ill patients, there is a lack of comprehensive and systematic identification of LUS phenotypes based on clinical data and assessment of their clinical value. METHODS Our study was based on a retrospective database. A total of 821 patients were included from September 2019 to October 2020. 1902 LUS examinations were performed in this period. Using a dataset of 55 LUS examinations focused on lung injuries, a group of experts developed an algorithm for classifying LUS phenotypes based on clinical practice, expert experience, and lecture review. This algorithm underwent validation and refinement with an additional 140 LUS images, leading to five iterative revisions and the generation of 1902 distinct LUS phenotypes. Subsequently, a validated machine learning algorithm was applied to these phenotypes. To assess the algorithm's effectiveness, experts manually verified 30% of the phenotypes, confirming its efficacy. Using K-means cluster analysis and expert image selection from the 1902 LUS examinations, we established seven distinct LUS phenotypes. To further explore the diagnostic value of these phenotypes for clinical diagnosis, we investigated their auxiliary diagnostic capabilities. RESULTS A total of 1902 LUS phenotypes were tested by randomly selecting 30% to verify the phenotypic accuracy. With the 1902 LUS phenotypes, seven lung ultrasound phenotypes were established through statistical K-means cluster analysis and expert screening. The acute respiratory distress syndrome (ARDS) exhibited gravity-dependent phenotypes, while the cardiogenic pulmonary edema exhibited nongravity phenotypes. The baseline characteristics of the 821 patients included age (66.14 ± 11.76), sex (560/321), heart rate (96.99 ± 23.75), mean arterial pressure (86.5 ± 13.57), Acute Physiology and Chronic Health Evaluation II (APACHE II)score (20.49 ± 8.60), and duration of ICU stay (24.50 ± 26.22); among the 821 patients, 78.8% were cured. In severe pneumonia patients, the gravity-dependent phenotype accounted for 42% of the cases, whereas the nongravity-dependent phenotype constituted 58%. These findings highlight the value of applying different LUS phenotypes in various diagnoses. CONCLUSIONS Seven sets of LUS phenotypes were established through machine learning analysis of retrospective data; these phenotypes could represent the typical characteristics of patients with different types of critical illness.
Collapse
Affiliation(s)
- Qian Wang
- Department of Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
- Department of Critical Care Medicine, Affiliated Hospital of Chengdu University, Chengdu, Sichuan Province, 610081, China
| | - Tongjuan Zou
- Department of Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
- Visualization Diagnosis and Treatment & Artificial Intelligence Laboratory, Institute of Critical Care Medicine Research, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
| | - Xueying Zeng
- Department of Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
- Visualization Diagnosis and Treatment & Artificial Intelligence Laboratory, Institute of Critical Care Medicine Research, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
| | - Ting Bao
- Health Management Center, General Practice Medical Center, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China
| | - Wanhong Yin
- Department of Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China.
- Visualization Diagnosis and Treatment & Artificial Intelligence Laboratory, Institute of Critical Care Medicine Research, West China Hospital, Sichuan University, Chengdu, Sichuan Province, 610041, China.
| |
Collapse
|
2
|
Zou T, Yin W, Li Y, Deng L, Zhou R, Wang X, Chao Y, Zhang L, Kang Y. Hemodynamics in Shock Patients Assessed by Critical Care Ultrasound and Its Relationship to Outcome: A Prospective Study. BIOMED RESEARCH INTERNATIONAL 2020; 2020:5175393. [PMID: 33015171 PMCID: PMC7512042 DOI: 10.1155/2020/5175393] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/07/2020] [Revised: 06/08/2020] [Accepted: 07/03/2020] [Indexed: 02/05/2023]
Abstract
BACKGROUND Shock is one of the causes of mortality in the intensive care unit (ICU). Traditionally, hemodynamics related to shock have been monitored by broad-spectrum devices with treatment guided by many inaccurate variables to describe the pathophysiological changes. Critical care ultrasound (CCUS) has been widely advocated as a preferred tool to monitor shock patients. The purpose of this study was to analyze and broaden current knowledge of the characteristics of ultrasonic hemodynamic pattern and investigate their relationship to outcome. METHODS This prospective study of shock patients in CCUS was conducted in 181 adult patients between April 2016 and June 2017 in the Department of Intensive Care Unit of West China Hospital. CCUS was performed within the initial 6 hours after shock patients were enrolled. The demographic and clinical characteristics, ultrasonic pattern of hemodynamics, and outcome were recorded. A stepwise bivariate logistic regression model was established to identify the correlation between ultrasonic variables and the 28-day mortality. RESULTS A total of 181 patients with shock were included in our study (male/female: 113/68). The mean age was 58.2 ± 18.0 years; the mean Acute Physiology and Chronic Health Evaluation II (APACHE II score) was 23.7 ± 8.7, and the 28-day mortality was 44.8% (81/181). The details of ultrasonic pattern were well represented, and the multivariate analysis revealed that mitral annular plane systolic excursion (MAPSE), mitral annular peak systolic velocity (S'-MV), tricuspid annular plane systolic excursion (TAPSE), and lung ultrasound score (LUSS) were the independent risk factors for 28-day mortality in our study, as well as APACHE II score, PaO2/FiO2, and lactate (p = 0.047, 0.041, 0.022, 0.002, 0.027, 0.028, and 0.01, respectively). CONCLUSIONS CCUS exam on admission provided valuable information to describe the pathophysiological changes of shock patients and the mechanism of shock. Several critical variables obtained by CCUS were related to outcome, hence deserving more attention in clinical decision-making. Trial Registration. The study was approved by the Ethics Committee of West China Hospital Review Board for human research with the following reference number 201736 and was registered on ClinicalTrials. This trial is registered with NCT03082326 on 3 March 2017 (retrospectively registered).
Collapse
Affiliation(s)
- Tongjuan Zou
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| | - Wanhong Yin
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| | - Yi Li
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| | - Lijing Deng
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| | - Ran Zhou
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| | - Xiaoting Wang
- Department of Critical Care Medicine, Peking Union Medical College Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing 100730, China
| | - Yangong Chao
- Department of Critical Care Medicine, The First Hospital of Tsinghua University, Beijing 100016, China
| | - Lina Zhang
- Department of Critical Care Medicine, Xiangya Hospital, Central South University, Changsha, Hunan 410008, China
| | - Yan Kang
- Department of Critical Care Medicine, West China Hospital/West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
| |
Collapse
|