1
|
Giri J, Al-Lohedan HA, Mohammad F, Soleiman AA, Chadge R, Mahatme C, Sunheriya N, Giri P, Mutyarapwar D, Dhapke S. A Comparative Study on Predication of Appropriate Mechanical Ventilation Mode through Machine Learning Approach. Bioengineering (Basel) 2023; 10:bioengineering10040418. [PMID: 37106605 PMCID: PMC10136217 DOI: 10.3390/bioengineering10040418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Revised: 03/17/2023] [Accepted: 03/24/2023] [Indexed: 03/29/2023] Open
Abstract
Ventilation mode is one of the most crucial ventilator settings, selected and set by knowledgeable critical care therapists in a critical care unit. The application of a particular ventilation mode must be patient-specific and patient-interactive. The main aim of this study is to provide a detailed outline regarding ventilation mode settings and determine the best machine learning method to create a deployable model for the appropriate selection of ventilation mode on a per breath basis. Per-breath patient data is utilized, preprocessed and finally a data frame is created consisting of five feature columns (inspiratory and expiratory tidal volume, minimum pressure, positive end-expiratory pressure, and previous positive end-expiratory pressure) and one output column (output column consisted of modes to be predicted). The data frame has been split into training and testing datasets with a test size of 30%. Six machine learning algorithms were trained and compared for performance, based on the accuracy, F1 score, sensitivity, and precision. The output shows that the Random-Forest Algorithm was the most precise and accurate in predicting all ventilation modes correctly, out of the all the machine learning algorithms trained. Thus, the Random-Forest machine learning technique can be utilized for predicting optimal ventilation mode setting, if it is properly trained with the help of the most relevant data. Aside from ventilation mode, control parameter settings, alarm settings and other settings may also be adjusted for the mechanical ventilation process utilizing appropriate machine learning, particularly deep learning approaches.
Collapse
Affiliation(s)
- Jayant Giri
- Mechanical Department, Yeshwantrao Chavan College of Engineering, Nagpur 441110, India
- Correspondence:
| | - Hamad A. Al-Lohedan
- Department of Chemistry, College of Science, King Saud University, Riyadh 11451, Saudi Arabia
| | - Faruq Mohammad
- Department of Chemistry, College of Science, King Saud University, Riyadh 11451, Saudi Arabia
| | - Ahmed A. Soleiman
- Department of Chemistry, College of Science, Southern University and A&M College, Baton Rouge, LA 70813, USA
| | - Rajkumar Chadge
- Mechanical Department, Yeshwantrao Chavan College of Engineering, Nagpur 441110, India
| | - Chetan Mahatme
- Mechanical Department, Yeshwantrao Chavan College of Engineering, Nagpur 441110, India
| | - Neeraj Sunheriya
- Mechanical Department, Yeshwantrao Chavan College of Engineering, Nagpur 441110, India
| | - Pallavi Giri
- Laxminarayan Institute of Technology, Nagpur 440033, India
| | | | | |
Collapse
|
2
|
Liu J, Liu S. The management of coronavirus disease 2019 (COVID-19). J Med Virol 2020; 92:1484-1490. [PMID: 32369222 PMCID: PMC7267323 DOI: 10.1002/jmv.25965] [Citation(s) in RCA: 51] [Impact Index Per Article: 12.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2020] [Revised: 04/28/2020] [Accepted: 05/01/2020] [Indexed: 02/06/2023]
Abstract
In December 2019, a novel coronavirus causing severe acute respiratory disease occurred in Wuhan, China. It is an emerging infectious disease with widespread and rapid infectiousness. The World Health Organization declared the coronavirus outbreak to be a public health emergency of international concern on 31 January 2020. Severe COVID-19 patients should be managed and treated in a critical care unit. Performing a chest X-ray/CT can judge the severity of the disease. The management of COVID-19 patients includes epidemiological risk and patient isolation; treatment entails general supportive care, respiratory support, symptomatic treatment, nutritional support, psychological intervention, etc. The prognosis of the patients depends upon the severity of the disease, the patient's age, the underlying diseases of the patients, and the patient's overall medical condition. The management of COVID-19 should focus on early diagnosis, immediate isolation, general and optimized supportive care, and infection prevention and control.
Collapse
Affiliation(s)
- Jialin Liu
- Department of Otolaryngology, West China HospitalSichuan UniversitySichuanChina
- Department of Medical InformaticsWest China Medical SchoolSichuanChina
| | - Siru Liu
- Department of Biomedical InformaticsUniversity of UtahSalt LakeUtah
| |
Collapse
|
3
|
Przybylo JA, Wittels K, Wilcox SR. Respiratory Distress in a Patient with a Tracheostomy. J Emerg Med 2018; 56:97-101. [PMID: 30527617 DOI: 10.1016/j.jemermed.2018.10.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2018] [Accepted: 10/18/2018] [Indexed: 11/25/2022]
Affiliation(s)
- Jennifer A Przybylo
- Department of Emergency Medicine, Harvard Medical School, Boston, Massachusetts; Department of Emergency Medicine, Brigham and Women's Hospital, Boston, Massachusetts; Department of Emergency Medicine, Massachusetts General Hospital, Boston, Massachusetts
| | - Kathleen Wittels
- Department of Emergency Medicine, Harvard Medical School, Boston, Massachusetts; Department of Emergency Medicine, Brigham and Women's Hospital, Boston, Massachusetts
| | - Susan R Wilcox
- Department of Emergency Medicine, Harvard Medical School, Boston, Massachusetts; Department of Emergency Medicine, Massachusetts General Hospital, Boston, Massachusetts
| |
Collapse
|
4
|
Abstract
The management of acute respiratory failure varies according to the etiology. A clear understanding of physiology of respiration and pathophysiological mechanisms of respiratory failure is mandatory for managing these patients. The extent of abnormality in arterial blood gas values is a result of the balance between the severity of disease and the degree of compensation by cardiopulmonary system. Normal blood gases do not mean that there is an absence of disease because the homeostatic system can compensate. However, an abnormal arterial blood gas value reflects uncompensated disease that might be life threatening.
Collapse
|
5
|
Wilcox SR, Strout TD, Schneider JI, Mitchell PM, Smith J, Lutfy-Clayton L, Marcolini EG, Aydin A, Seigel TA, Richards JB. Academic Emergency Medicine Physicians' Knowledge of Mechanical Ventilation. West J Emerg Med 2016; 17:271-9. [PMID: 27330658 PMCID: PMC4899057 DOI: 10.5811/westjem.2016.2.29517] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2015] [Revised: 01/19/2016] [Accepted: 02/05/2016] [Indexed: 11/17/2022] Open
Abstract
Introduction Although emergency physicians frequently intubate patients, management of mechanical ventilation has not been emphasized in emergency medicine (EM) education or clinical practice. The objective of this study was to quantify EM attendings’ education, experience, and knowledge regarding mechanical ventilation in the emergency department. Methods We developed a survey of academic EM attendings’ educational experiences with ventilators and a knowledge assessment tool with nine clinical questions. EM attendings at key teaching hospitals for seven EM residency training programs in the northeastern United States were invited to participate in this survey study. We performed correlation and regression analyses to evaluate the relationship between attendings’ scores on the assessment instrument and their training, education, and comfort with ventilation. Results Of 394 EM attendings surveyed, 211 responded (53.6%). Of respondents, 74.5% reported receiving three or fewer hours of ventilation-related education from EM sources over the past year and 98 (46%) reported receiving between 0–1 hour of education. The overall correct response rate for the assessment tool was 73.4%, with a standard deviation of 19.9. The factors associated with a higher score were completion of an EM residency, prior emphasis on mechanical ventilation during one’s own residency, working in a setting where an emergency physician bears primary responsibility for ventilator management, and level of comfort with managing ventilated patients. Physicians’ comfort was associated with the frequency of ventilator changes and EM management of ventilation, as well as hours of education. Conclusion EM attendings report caring for mechanically ventilated patients frequently, but most receive fewer than three educational hours a year on mechanical ventilation, and nearly half receive 0–1 hour. Physicians’ performance on an assessment tool for mechanical ventilation is most strongly correlated with their self-reported comfort with mechanical ventilation.
Collapse
Affiliation(s)
- Susan R Wilcox
- Medical University of South Carolina, Divisions of Emergency Medicine and Pulmonary, Critical Care and Sleep Medicine, Charleston, South Carolina
| | - Tania D Strout
- Maine Medical Center, Department of Emergency Medicine, Portland, Maine
| | - Jeffrey I Schneider
- Boston Medical Center, Department of Emergency Medicine, Boston, Massachusetts
| | - Patricia M Mitchell
- Boston Medical Center, Department of Emergency Medicine, Boston, Massachusetts
| | - Jessica Smith
- Alpert Medical School of Brown University, Department of Emergency Medicine, Providence, Rhode Island
| | | | - Evie G Marcolini
- Yale University School of Medicine, Departments of Emergency Medicine and Neurology, Divisions of Neurocritical Care and Emergency Neurology and Surgical Critical Care, New Haven, Connecticut
| | - Ani Aydin
- Yale University School of Medicine, Department of Emergency Medicine, New Haven, Connecticut
| | - Todd A Seigel
- Department of Emergency Medicine and Critical Care, Kaiser Permanente East Bay, Oakland and Richmond Medical Centers, California
| | - Jeremy B Richards
- Medical University of South Carolina, Division of Pulmonary, Critical Care and Sleep Medicine, Charleston, South Carolina
| |
Collapse
|
6
|
Wilcox SR, Richards JB, Fisher DF, Sankoff J, Seigel TA. Initial mechanical ventilator settings and lung protective ventilation in the ED. Am J Emerg Med 2016; 34:1446-51. [PMID: 27139256 DOI: 10.1016/j.ajem.2016.04.027] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2016] [Revised: 03/18/2016] [Accepted: 04/17/2016] [Indexed: 12/17/2022] Open
Abstract
OBJECTIVE Mechanical ventilation with low tidal volumes has been shown to improve outcomes for patients both with and without acute respiratory distress syndrome. This study aims to characterize mechanically ventilated patients in the emergency department (ED), describe the initial ED ventilator settings, and assess for associations between lung protective ventilation strategies in the ED and outcomes. METHODS This was a multicenter, prospective, observational study of mechanical ventilation at 3 academic EDs. We defined lung protective ventilation as a tidal volume of less than or equal to 8 mL/kg of predicted body weight and compared outcomes for patients ventilated with lung protective vs non-lung protective ventilation, including inhospital mortality, ventilator days, intensive care unit length of stay, and hospital length of stay. RESULTS Data from 433 patients were analyzed. Altered mental status without respiratory pathology was the most common reason for intubation, followed by trauma and respiratory failure. Two hundred sixty-one patients (60.3%) received lung protective ventilation, but most patients were ventilated with a low positive end-expiratory pressure, high fraction of inspired oxygen strategy. Patients were ventilated in the ED for a mean of 5 hours and 7 minutes but had few ventilator adjustments. Outcomes were not significantly different between patients receiving lung protective vs non-lung protective ventilation. CONCLUSIONS Nearly 40% of ED patients were ventilated with non-lung protective ventilation as well as with low positive end-expiratory pressure and high fraction of inspired oxygen. Despite a mean ED ventilation time of more than 5 hours, few patients had adjustments made to their ventilators.
Collapse
Affiliation(s)
- Susan R Wilcox
- Division of Pulmonary, Critical Care, Allergy, and Sleep Medicine, Division of Emergency Medicine, Medical University of South Carolina, Charleston, SC, USA.
| | - Jeremy B Richards
- Division of Pulmonary, Critical Care, Allergy, and Sleep Medicine, Medical University of South Carolina, Charleston, SC, USA.
| | - Daniel F Fisher
- Respiratory Care Services, Massachusetts General Hospital, Boston, MA, USA.
| | - Jeffrey Sankoff
- Department of Emergency Medicine, University of Colorado School of Medicine, Denver Health Medical Center, Denver, CO, USA.
| | - Todd A Seigel
- Department of Emergency Medicine and Critical Care, Kaiser Permanente East Bay, Oakland and Richmond Medical Centers, CA, USA.
| |
Collapse
|
7
|
Wilcox SR, Seigel TA, Strout TD, Schneider JI, Mitchell PM, Marcolini EG, Cocchi MN, Smithline HA, Lutfy-Clayton L, Mullen M, Ilgen JS, Richards JB. Emergency medicine residents' knowledge of mechanical ventilation. J Emerg Med 2014; 48:481-91. [PMID: 25497896 DOI: 10.1016/j.jemermed.2014.09.059] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2014] [Revised: 08/15/2014] [Accepted: 09/30/2014] [Indexed: 01/28/2023]
Abstract
BACKGROUND Although Emergency physicians frequently intubate patients, management of mechanical ventilation has not been emphasized in emergency medicine (EM) residency curricula. OBJECTIVES The objective of this study was to quantify EM residents' education, experience, and knowledge regarding mechanical ventilation. METHODS We developed a survey of residents' educational experiences with ventilators and an assessment tool with nine clinical questions. Correlation and regression analyses were performed to evaluate the relationship between residents' scores on the assessment instrument and their training, education, and comfort with ventilation. RESULTS Of 312 EM residents, 218 responded (69.9%). The overall correct response rate for the assessment tool was 73.3%, standard deviation (SD) ± 22.3. Seventy-seven percent (n = 167) of respondents reported ≤ 3 h of mechanical ventilation education in their residency curricula over the past year. Residents reported frequently caring for ventilated patients in the ED, as 64% (n = 139) recalled caring for ≥ 4 ventilated patients per month. Fifty-three percent (n = 116) of residents endorsed feeling comfortable caring for mechanically ventilated ED patients. In multiregression analysis, the only significant predictor of total test score was residents' comfort with caring for mechanically ventilated patients (F = 10.963, p = 0.001). CONCLUSIONS EM residents report caring for mechanically ventilated patients frequently, but receive little education on mechanical ventilation. Furthermore, as residents' performance on the assessment tool is only correlated with their self-reported comfort with caring for ventilated patients, these results demonstrate an opportunity for increased educational focus on mechanical ventilation management in EM residency training.
Collapse
Affiliation(s)
- Susan R Wilcox
- Department of Emergency Medicine, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, Massachusetts; Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Boston, Massachusetts
| | - Todd A Seigel
- Department of Emergency Medicine, Rhode Island Hospital, Providence, Rhode Island; University of California San Francisco, San Francisco, California
| | - Tania D Strout
- Department of Emergency Medicine, Maine Medical Center, Portland, Maine
| | - Jeffrey I Schneider
- Department of Emergency Medicine, Boston Medical Center, Boston, Massachusetts
| | - Patricia M Mitchell
- Department of Emergency Medicine, Boston Medical Center, Boston, Massachusetts
| | - Evie G Marcolini
- Department of Emergency Medicine, Yale-New Haven Hospital, New Haven, Connecticut
| | - Michael N Cocchi
- Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts; Department of Anesthesia Critical Care, Division of Critical Care, Beth Israel Deaconess Medical Center, Boston, Massachusetts
| | - Howard A Smithline
- Department of Emergency Medicine, Baystate Medical Center, Springfield, Massachusetts
| | | | - Marie Mullen
- Department of Emergency Medicine, University of Massachusetts Medical School, Worcester, Massachusetts
| | - Jonathan S Ilgen
- Division of Emergency Medicine, University of Washington School of Medicine, Seattle, Washington
| | - Jeremy B Richards
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts
| |
Collapse
|
8
|
Abstract
Respiratory failure may occur due to hypoventilation or hypoxemia. Regardless of the cause, emergent anesthesia and intubation, accompanied by positive pressure ventilation, may be necessary and life saving. Long-term mechanical ventilation requires some specialized equipment and knowledge; however, short-term ventilation can be accomplished without the use of an intensive care unit ventilator, and can provide oxygen supplementation and carbon dioxide removal in critical patients.
Collapse
|