1
|
Zhang G, Xie Q, Wang C, Xu J, Liu G, Su C. Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databases. Med Biol Eng Comput 2024:10.1007/s11517-024-03143-7. [PMID: 38861056 DOI: 10.1007/s11517-024-03143-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Accepted: 05/27/2024] [Indexed: 06/12/2024]
Abstract
The use of invasive mechanical ventilation (IMV) is crucial in rescuing patients with respiratory dysfunction. Accurately predicting the demand for IMV is vital for clinical decision-making. However, current techniques are invasive and challenging to implement in pre-hospital and emergency rescue settings. To address this issue, a real-time prediction method utilizing only non-invasive parameters was developed to forecast IMV demand in this study. The model introduced the concept of real-time warning and leveraged the advantages of machine learning and integrated methods, achieving an AUC value of 0.935 (95% CI 0.933-0.937). The AUC value for the multi-center validation using the AmsterdamUMCdb database was 0.727, surpassing the performance of traditional risk adjustment algorithms (OSI(oxygenation saturation index): 0.608, P/F(oxygenation index): 0.558). Feature weight analysis demonstrated that BMI, Gcsverbal, and age significantly contributed to the model's decision-making. These findings highlight the substantial potential of a machine learning real-time dynamic warning model that solely relies on non-invasive parameters to predict IMV demand. Such a model can provide technical support for predicting the need for IMV in pre-hospital and disaster scenarios.
Collapse
Affiliation(s)
- Guang Zhang
- Systems Engineering Institute, People's Liberation Army, Academy of Military Sciences, Tianjin, 300161, China
| | - Qingyan Xie
- School of Life Sciences, Tiangong University, Tianjin, 300387, China
| | - Chengyi Wang
- School of Life Sciences, Tiangong University, Tianjin, 300387, China
| | - Jiameng Xu
- School of Life Sciences, Tiangong University, Tianjin, 300387, China
| | - Guanjun Liu
- Systems Engineering Institute, People's Liberation Army, Academy of Military Sciences, Tianjin, 300161, China
| | - Chen Su
- Systems Engineering Institute, People's Liberation Army, Academy of Military Sciences, Tianjin, 300161, China.
| |
Collapse
|
2
|
Singer P, Robinson E, Raphaeli O. The future of artificial intelligence in clinical nutrition. Curr Opin Clin Nutr Metab Care 2024; 27:200-206. [PMID: 37650706 DOI: 10.1097/mco.0000000000000977] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 09/01/2023]
Abstract
PURPOSE OF REVIEW Artificial intelligence has reached the clinical nutrition field. To perform personalized medicine, numerous tools can be used. In this review, we describe how the physician can utilize the growing healthcare databases to develop deep learning and machine learning algorithms, thus helping to improve screening, assessment, prediction of clinical events and outcomes related to clinical nutrition. RECENT FINDINGS Artificial intelligence can be applied to all the fields of clinical nutrition. Improving screening tools, identifying malnourished cancer patients or obesity using large databases has been achieved. In intensive care, machine learning has been able to predict enteral feeding intolerance, diarrhea, or refeeding hypophosphatemia. The outcome of patients with cancer can also be improved. Microbiota and metabolomics profiles are better integrated with the clinical condition using machine learning. However, ethical considerations and limitations of the use of artificial intelligence should be considered. SUMMARY Artificial intelligence is here to support the decision-making process of health professionals. Knowing not only its limitations but also its power will allow precision medicine in clinical nutrition as well as in the rest of the medical practice.
Collapse
Affiliation(s)
- Pierre Singer
- Herzlia Medical Center, Intensive Care Unit, Herzlia
- Critical Care Department and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, affiliated to the Sackler School of Medicine, Tel Aviv University, Tel Aviv
| | - Eyal Robinson
- Critical Care Department and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, affiliated to the Sackler School of Medicine, Tel Aviv University, Tel Aviv
| | - Orit Raphaeli
- Critical Care Department and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, affiliated to the Sackler School of Medicine, Tel Aviv University, Tel Aviv
- Ariel University, Department of Industrial Engineering & Management, Ariel, Israel
| |
Collapse
|
3
|
Statlender L, Shvartser L, Teppler S, Bendavid I, Kushinir S, Azullay R, Singer P. Predicting invasive mechanical ventilation in COVID 19 patients: A validation study. PLoS One 2024; 19:e0296386. [PMID: 38166095 PMCID: PMC10760863 DOI: 10.1371/journal.pone.0296386] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Accepted: 12/12/2023] [Indexed: 01/04/2024] Open
Abstract
INTRODUCTION The decision to intubate and ventilate a patient is mainly clinical. Both delaying intubation (when needed) and unnecessarily invasively ventilating (when it can be avoided) are harmful. We recently developed an algorithm predicting respiratory failure and invasive mechanical ventilation in COVID-19 patients. This is an internal validation study of this model, which also suggests a categorized "time-weighted" model. METHODS We used a dataset of COVID-19 patients who were admitted to Rabin Medical Center after the algorithm was developed. We evaluated model performance in predicting ventilation, regarding the actual endpoint of each patient. We further categorized each patient into one of four categories, based on the strength of the prediction of ventilation over time. We evaluated this categorized model performance regarding the actual endpoint of each patient. RESULTS 881 patients were included in the study; 96 of them were ventilated. AUC of the original algorithm is 0.87-0.94. The AUC of the categorized model is 0.95. CONCLUSIONS A minor degradation in the algorithm accuracy was noted in the internal validation, however, its accuracy remained high. The categorized model allows accurate prediction over time, with very high negative predictive value.
Collapse
Affiliation(s)
- Liran Statlender
- Department of Gefneral Intensive Care and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, Petah Tikva, Israel
| | | | | | - Itai Bendavid
- Department of Gefneral Intensive Care and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, Petah Tikva, Israel
| | - Shiri Kushinir
- Rabin Medical Center Research Authority, Beilinson Hospital, Petah Tikva, Israel
| | - Roy Azullay
- TSG IT Advanced Systems Ltd., Or Yehuda, Israel
| | - Pierre Singer
- Department of Gefneral Intensive Care and Institute for Nutrition Research, Rabin Medical Center, Beilinson Hospital, Petah Tikva, Israel
| |
Collapse
|
4
|
Le JP, Shashikumar SP, Malhotra A, Nemati S, Wardi G. Making the Improbable Possible: Generalizing Models Designed for a Syndrome-Based, Heterogeneous Patient Landscape. Crit Care Clin 2023; 39:751-768. [PMID: 37704338 PMCID: PMC10758922 DOI: 10.1016/j.ccc.2023.02.003] [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] [Indexed: 09/15/2023]
Abstract
Syndromic conditions, such as sepsis, are commonly encountered in the intensive care unit. Although these conditions are easy for clinicians to grasp, these conditions may limit the performance of machine-learning algorithms. Individual hospital practice patterns may limit external generalizability. Data missingness is another barrier to optimal algorithm performance and various strategies exist to mitigate this. Recent advances in data science, such as transfer learning, conformal prediction, and continual learning, may improve generalizability of machine-learning algorithms in critically ill patients. Randomized trials with these approaches are indicated to demonstrate improvements in patient-centered outcomes at this point.
Collapse
Affiliation(s)
- Joshua Pei Le
- School of Medicine, University of Limerick, Castletroy, Co, Limerick V94 T9PX, Ireland
| | | | - Atul Malhotra
- Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego, San Diego, CA, USA
| | - Shamim Nemati
- Division of Biomedical Informatics, University of California San Diego, San Diego, CA, USA
| | - Gabriel Wardi
- Division of Pulmonary, Critical Care and Sleep Medicine, University of California San Diego, San Diego, CA, USA; Department of Emergency Medicine, University of California San Diego, 200 W Arbor Drive, San Diego, CA 92103, USA.
| |
Collapse
|
5
|
Ansari AK, Pitamberwale A, Ansari SA, Mahmood T, Limgaokar K, Karki G, Singh L. Study of Biochemical Parameters as Predictors for Need of Invasive Ventilation in Severely Ill COVID-19 Patients. J Crit Care Med (Targu Mures) 2023; 9:262-270. [PMID: 37969877 PMCID: PMC10644279 DOI: 10.2478/jccm-2023-0030] [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: 07/19/2023] [Accepted: 10/19/2023] [Indexed: 11/17/2023] Open
Abstract
Background Though laboratory tests have been shown to predict mortality in COVID-19, there is still a dearth of information regarding the role of biochemical parameters in predicting the type of ventilatory support that these patients may require. Methods The purpose of our retrospective observational study was to investigate the relationship between biochemical parameters and the type of ventilatory support needed for the intensive care of severely ill COVID-19 patients. We comprehensively recorded history, physical examination, vital signs from point-of-care testing (POCT) devices, clinical diagnosis, details of the ventilatory support required in intensive care and the results of the biochemical analysis at the time of admission. Appropriate statistical methods were used and P-values < 0.05 were considered significant. Receiver operating characteristics (ROC) analysis was performed and Area Under the Curve (AUC) of 0.6 to 0.7, 0.7 to 0.8, 0.8 to 0.9, and >0.9, respectively, were regarded as acceptable, fair, good, and exceptional for discrimination. Results Statistically significant differences (p<0.05) in Urea (p = 0.0351), Sodium (p = 0.0142), Indirect Bilirubin (p = 0.0251), Albumin (p = 0.0272), Aspartate Transaminase (AST) (p = 0.0060) and Procalcitonin (PCT) (p = 0.0420) were observed between the patients who were maintained on non-invasive ventilations as compared to those who required invasive ventilation. In patients who required invasive ventilation, the levels of Urea, Sodium, Indirect bilirubin, AST and PCT were higher while Albumin was lower. On ROC analysis, higher levels of Albumin was found to be acceptable indicator of maintenance on non-invasive ventilation while higher levels of Sodium and PCT were found to be fair predictor of requirement of invasive ventilation. Conclusion Our study emphasizes the role of biochemical parameters in predicting the type of ventilatory support that is needed in order to properly manage severely ill COVID-19 patients.
Collapse
Affiliation(s)
- Azmat Kamal Ansari
- Shri Ram Murti Smarak Institute of Medical Sciences, Bareilly, Uttar Pradesh, India
| | | | | | - Tariq Mahmood
- Teerthanker Mahaveer Medical College and Research Centre, Moradabad, Uttar Pradesh, India
| | | | - Geeta Karki
- Shri Ram Murti Smarak Institute of Medical Sciences, Bareilly, Uttar Pradesh, India
| | - Lalit Singh
- Shri Ram Murti Smarak Institute of Medical Sciences, Bareilly, Uttar Pradesh, India
| |
Collapse
|
6
|
Lentzen M, Linden T, Veeranki S, Madan S, Kramer D, Leodolter W, Frohlich H. A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression. IEEE J Biomed Health Inform 2023; 27:4548-4558. [PMID: 37347632 DOI: 10.1109/jbhi.2023.3288768] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/24/2023]
Abstract
In situations like the COVID-19 pandemic, healthcare systems are under enormous pressure as they can rapidly collapse under the burden of the crisis. Machine learning (ML) based risk models could lift the burden by identifying patients with a high risk of severe disease progression. Electronic Health Records (EHRs) provide crucial sources of information to develop these models because they rely on routinely collected healthcare data. However, EHR data is challenging for training ML models because it contains irregularly timestamped diagnosis, prescription, and procedure codes. For such data, transformer-based models are promising. We extended the previously published Med-BERT model by including age, sex, medications, quantitative clinical measures, and state information. After pre-training on approximately 988 million EHRs from 3.5 million patients, we developed models to predict Acute Respiratory Manifestations (ARM) risk using the medical history of 80,211 COVID-19 patients. Compared to Random Forests, XGBoost, and RETAIN, our transformer-based models more accurately forecast the risk of developing ARM after COVID-19 infection. We used Integrated Gradients and Bayesian networks to understand the link between the essential features of our model. Finally, we evaluated adapting our model to Austrian in-patient data. Our study highlights the promise of predictive transformer-based models for precision medicine.
Collapse
|
7
|
Charkoftaki G, Aalizadeh R, Santos-Neto A, Tan WY, Davidson EA, Nikolopoulou V, Wang Y, Thompson B, Furnary T, Chen Y, Wunder EA, Coppi A, Schulz W, Iwasaki A, Pierce RW, Cruz CSD, Desir GV, Kaminski N, Farhadian S, Veselkov K, Datta R, Campbell M, Thomaidis NS, Ko AI, Thompson DC, Vasiliou V. An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model. Hum Genomics 2023; 17:80. [PMID: 37641126 PMCID: PMC10463861 DOI: 10.1186/s40246-023-00521-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2023] [Accepted: 07/30/2023] [Indexed: 08/31/2023] Open
Abstract
Over the last century, outbreaks and pandemics have occurred with disturbing regularity, necessitating advance preparation and large-scale, coordinated response. Here, we developed a machine learning predictive model of disease severity and length of hospitalization for COVID-19, which can be utilized as a platform for future unknown viral outbreaks. We combined untargeted metabolomics on plasma data obtained from COVID-19 patients (n = 111) during hospitalization and healthy controls (n = 342), clinical and comorbidity data (n = 508) to build this patient triage platform, which consists of three parts: (i) the clinical decision tree, which amongst other biomarkers showed that patients with increased eosinophils have worse disease prognosis and can serve as a new potential biomarker with high accuracy (AUC = 0.974), (ii) the estimation of patient hospitalization length with ± 5 days error (R2 = 0.9765) and (iii) the prediction of the disease severity and the need of patient transfer to the intensive care unit. We report a significant decrease in serotonin levels in patients who needed positive airway pressure oxygen and/or were intubated. Furthermore, 5-hydroxy tryptophan, allantoin, and glucuronic acid metabolites were increased in COVID-19 patients and collectively they can serve as biomarkers to predict disease progression. The ability to quickly identify which patients will develop life-threatening illness would allow the efficient allocation of medical resources and implementation of the most effective medical interventions. We would advocate that the same approach could be utilized in future viral outbreaks to help hospitals triage patients more effectively and improve patient outcomes while optimizing healthcare resources.
Collapse
Affiliation(s)
- Georgia Charkoftaki
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
| | - Reza Aalizadeh
- Laboratory of Analytical Chemistry, Department of Chemistry, National and Kapodistrian University of Athens, Athens, Zografou, 15771, Greece
| | - Alvaro Santos-Neto
- São Carlos Institute of Chemistry, University of São Paulo, São Carlos, SP, 13566-590, Brazil
| | - Wan Ying Tan
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
- Internal Medicine Residency Program, Department of Internal Medicine, Norwalk Hospital, Norwalk, CT, USA
| | - Emily A Davidson
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
- Department of Cellular and Molecular Physiology, Yale University School of Medicine, New Haven, CT, USA
| | - Varvara Nikolopoulou
- Laboratory of Analytical Chemistry, Department of Chemistry, National and Kapodistrian University of Athens, Athens, Zografou, 15771, Greece
| | - Yewei Wang
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
| | - Brian Thompson
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
| | - Tristan Furnary
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
- Harvard Medical School, Harvard University, Boston, MA, USA
| | - Ying Chen
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
| | - Elsio A Wunder
- Department of Epidemiology of Microbial Diseases, Yale School of Public Health, Yale University, New Haven, CT, USA
- Institute Gonçalo Moniz, Fundação Oswaldo Cruz, Brazilian Ministry of Health, Salvador, Brazil
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Wade Schulz
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Laboratory Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Akiko Iwasaki
- Department of Immunobiology, Yale University School of Medicine, New Haven, CT, USA
- Howard Hughes Medical Institute, MD, Chevy Chase, USA
| | - Richard W Pierce
- Department of Pediatrics , Yale School of Medicine, New Haven, CT, USA
| | - Charles S Dela Cruz
- Section of Pulmonary, Critical Care and Sleep Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Gary V Desir
- Department of Internal Medicine, Section of Nephrology, Yale University School of Medicine, New Haven, CT, USA
| | - Naftali Kaminski
- Section of Pulmonary, Critical Care and Sleep Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Shelli Farhadian
- Department of Internal Medicine, Section of Infectious Diseases, Yale School of Medicine, New Haven, CT, USA
- Department of Neurology, Yale School of Medicine, New Haven, CT, USA
- Department of Epidemiology of Microbial Diseases, Yale School of Public Health, Yale University, New Haven, USA
| | - Kirill Veselkov
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
- Department of Surgery and Cancer, Imperial College London, South Kensington Campus, London, UK
| | - Rupak Datta
- Veterans Affairs Connecticut Healthcare System, CT, West Haven, USA
- Department of Internal Medicine, Yale School of Medicine, CT, New Haven, USA
| | - Melissa Campbell
- Department of Pediatrics, Division of Pediatric Infectious Diseases, School of Medicine, Duke University, NC, Durham, USA
| | - Nikolaos S Thomaidis
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
- Laboratory of Analytical Chemistry, Department of Chemistry, National and Kapodistrian University of Athens, Athens, Zografou, 15771, Greece
| | - Albert I Ko
- Department of Epidemiology of Microbial Diseases, Yale School of Public Health, Yale University, New Haven, CT, USA
- Institute Gonçalo Moniz, Fundação Oswaldo Cruz, Brazilian Ministry of Health, Salvador, Brazil
- Department of Internal Medicine, Section of Infectious Diseases, Yale School of Medicine, New Haven, CT, USA
| | - David C Thompson
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA
| | - Vasilis Vasiliou
- Department of Environmental Health Sciences, Yale School of Public Health, Yale University, New Haven, CT, USA.
| |
Collapse
|
8
|
Recio-Garcia JA, Diaz-Agudo B, Acuaviva A. Becalm: Intelligent Monitoring of Respiratory Patients. IEEE J Biomed Health Inform 2023; 27:3806-3817. [PMID: 37192034 DOI: 10.1109/jbhi.2023.3276638] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/18/2023]
Abstract
The Becalm project is an open and low-cost solution for the remote monitoring of respiratory support therapies like the ones used in COVID-19 patients. Becalm combines a decision-making system based on Case-Based Reasoning with a low-cost, non-invasive mask that enables the remote monitoring, detection, and explanation of risk situations for respiratory patients. This paper first describes the mask and the sensors that allow remote monitoring. Then, it describes the intelligent decision-making system that detects anomalies and raises early warnings. This detection is based on the comparison of cases that represent patients using a set of static variables plus the dynamic vector of the patient time series from sensors. Finally, personalized visual reports are created to explain the causes of the warning, data patterns, and patient context to the healthcare professional. To evaluate the case-based early-warning system, we use a synthetic data generator that simulates patients' clinical evolution from the physiological features and factors described in healthcare literature. This generation process has been verified with a real dataset and allows the validation of the reasoning system with noisy and incomplete data, threshold values, and life/death situations. The evaluation demonstrates promising results and good accuracy (0.91) for the proposed low-cost solution to monitor respiratory patients.
Collapse
|
9
|
Zhang Y, Zhu YJ, Zhu DJ, Yu BY, Liu TT, Wang LY, Zhang LL. Development and validation of a prediction model for mechanical ventilation based on comorbidities in hospitalized patients with COVID-19. Front Public Health 2023; 11:1227935. [PMID: 37522004 PMCID: PMC10375294 DOI: 10.3389/fpubh.2023.1227935] [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: 05/24/2023] [Accepted: 07/03/2023] [Indexed: 08/01/2023] Open
Abstract
Background Timely recognition of respiratory failure and the need for mechanical ventilation is crucial in managing patients with coronavirus disease 2019 (COVID-19) and reducing hospital mortality rate. A risk stratification tool could assist to avoid clinical deterioration of patients with COVID-19 and optimize allocation of scarce resources. Therefore, we aimed to develop a prediction model for early identification of patients with COVID-19 who may require mechanical ventilation. Methods We included patients with COVID-19 hospitalized in United States. Demographic and clinical data were extracted from the records of the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Model construction involved the use of the least absolute shrinkage and selection operator and multivariable logistic regression. The model's performance was evaluated based on discrimination, calibration, and clinical utility. Results The training set comprised 73,957 patients (5,971 requiring mechanical ventilation), whereas the validation set included 10,428 (887 requiring mechanical ventilation). The prediction model incorporating age, sex, and 11 other comorbidities (deficiency anemias, congestive heart failure, coagulopathy, dementia, diabetes with chronic complications, complicated hypertension, neurological disorders unaffecting movement, obesity, pulmonary circulation disease, severe renal failure, and weight loss) demonstrated moderate discrimination (area under the curve, 0.715; 95% confidence interval, 0.709-0.722), good calibration (Brier score = 0.070, slope = 1, intercept = 0) and a clinical net benefit with a threshold probability ranged from 2 to 34% in the training set. Similar model's performances were observed in the validation set. Conclusion A robust prognostic model utilizing readily available predictors at hospital admission was developed for the early identification of patients with COVID-19 who may require mechanical ventilation. Application of this model could support clinical decision-making to optimize patient management and resource allocation.
Collapse
Affiliation(s)
- Yi Zhang
- Department of Gastroenterology, Changzheng Hospital, Naval Medical University, Shanghai, China
- Department of Gastroenterology, The Affiliated Hospital of Southwest Medical University, Luzhou, China
| | - Yang-Jie Zhu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Dao-Jun Zhu
- Operating Room, West China Hospital, Sichuan University, Chengdu, China
- West China School of Nursing, Sichuan University, Chengdu, China
| | - Bo-Yang Yu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Tong-Tong Liu
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Lu-Yao Wang
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| | - Lu-Lu Zhang
- Department of Military Health Management, College of Health Service, Naval Medical University, Shanghai, China
| |
Collapse
|
10
|
Morís DI, de Moura J, Marcos PJ, Rey EM, Novo J, Ortega M. Comprehensive analysis of clinical data for COVID-19 outcome estimation with machine learning models. Biomed Signal Process Control 2023; 84:104818. [PMID: 36915863 PMCID: PMC9995330 DOI: 10.1016/j.bspc.2023.104818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2022] [Revised: 11/22/2022] [Accepted: 03/05/2023] [Indexed: 03/11/2023]
Abstract
COVID-19 is a global threat for the healthcare systems due to the rapid spread of the pathogen that causes it. In such situation, the clinicians must take important decisions, in an environment where medical resources can be insufficient. In this task, the computer-aided diagnosis systems can be very useful not only in the task of supporting the clinical decisions but also to perform relevant analyses, allowing them to understand better the disease and the factors that can identify the high risk patients. For those purposes, in this work, we use several machine learning algorithms to estimate the outcome of COVID-19 patients given their clinical information. Particularly, we perform 2 different studies: the first one estimates whether the patient is at low or at high risk of death whereas the second estimates if the patient needs hospitalization or not. The results of the analyses of this work show the most relevant features for each studied scenario, as well as the classification performance of the considered machine learning models. In particular, the XGBoost algorithm is able to estimate the need for hospitalization of a patient with an AUC-ROC of 0 . 8415 ± 0 . 0217 while it can also estimate the risk of death with an AUC-ROC of 0 . 7992 ± 0 . 0104 . Results have demonstrated the great potential of the proposal to determine those patients that need a greater amount of medical resources for being at a higher risk. This provides the healthcare services with a tool to better manage their resources.
Collapse
Affiliation(s)
- Daniel I Morís
- Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain.,Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Joaquim de Moura
- Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain.,Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Pedro J Marcos
- Dirección Asistencial y Servicio de Neumología, Complejo Hospitalario Universitario de A Coruña (CHUAC), Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Sergas, 15006 A Coruña, Spain
| | - Enrique Míguez Rey
- Grupo de Investigación en Virología Clínica, Sección de Enfermedades Infecciosas, Servicio de Medicina Interna, Instituto de Investigación Biomédica de A Coruña (INIBIC), Área Sanitaria A Coruña y CEE (ASCC), SERGAS, 15006 A Coruña, Spain
| | - Jorge Novo
- Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain.,Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Marcos Ortega
- Centro de Investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain.,Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| |
Collapse
|
11
|
Raphaeli O, Statlender L, Hajaj C, Bendavid I, Goldstein A, Robinson E, Singer P. Using Machine-Learning to Assess the Prognostic Value of Early Enteral Feeding Intolerance in Critically Ill Patients: A Retrospective Study. Nutrients 2023; 15:2705. [PMID: 37375609 DOI: 10.3390/nu15122705] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Accepted: 06/07/2023] [Indexed: 06/29/2023] Open
Abstract
BACKGROUND The association between gastrointestinal intolerance during early enteral nutrition (EN) and adverse clinical outcomes in critically ill patients is controversial. We aimed to assess the prognostic value of enteral feeding intolerance (EFI) markers during early ICU stays and to predict early EN failure using a machine learning (ML) approach. METHODS We performed a retrospective analysis of data from adult patients admitted to Beilinson Hospital ICU between January 2011 and December 2018 for more than 48 h and received EN. Clinical data, including demographics, severity scores, EFI markers, and medications, along with 72 h after admission, were analyzed by ML algorithms. Prediction performance was assessed by the area under the receiver operating characteristics (AUCROC) of a ten-fold cross-validation set. RESULTS The datasets comprised 1584 patients. The means of the cross-validation AUCROCs for 90-day mortality and early EN failure were 0.73 (95% CI 0.71-0.75) and 0.71 (95% CI 0.67-0.74), respectively. Gastric residual volume above 250 mL on the second day was an important component of both prediction models. CONCLUSIONS ML underlined the EFI markers that predict poor 90-day outcomes and early EN failure and supports early recognition of at-risk patients. Results have to be confirmed in further prospective and external validation studies.
Collapse
Affiliation(s)
- Orit Raphaeli
- Industrial Engineering and Management, Ariel University, Ariel 40700, Israel
- Institute for Nutrition Research, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
- Data Science and Artificial Intelligence Research Center, Ariel University, Ariel 40700, Israel
| | - Liran Statlender
- Intensive Care Unit, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
| | - Chen Hajaj
- Industrial Engineering and Management, Ariel University, Ariel 40700, Israel
- Data Science and Artificial Intelligence Research Center, Ariel University, Ariel 40700, Israel
| | - Itai Bendavid
- Intensive Care Unit, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
| | - Anat Goldstein
- Industrial Engineering and Management, Ariel University, Ariel 40700, Israel
- Data Science and Artificial Intelligence Research Center, Ariel University, Ariel 40700, Israel
| | - Eyal Robinson
- Intensive Care Unit, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
| | - Pierre Singer
- Institute for Nutrition Research, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
- Intensive Care Unit, Beilinson Hospital, Rabin Medical Center, Petah Tikva 4941492, Israel
| |
Collapse
|
12
|
Abdeltawab H, Khalifa F, ElNakieb Y, Elnakib A, Taher F, Alghamdi NS, Sandhu HS, El-Baz A. Predicting the Level of Respiratory Support in COVID-19 Patients Using Machine Learning. Bioengineering (Basel) 2022; 9:bioengineering9100536. [PMID: 36290506 PMCID: PMC9598090 DOI: 10.3390/bioengineering9100536] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 09/26/2022] [Accepted: 10/04/2022] [Indexed: 01/08/2023] Open
Abstract
In this paper, a machine learning-based system for the prediction of the required level of respiratory support in COVID-19 patients is proposed. The level of respiratory support is divided into three classes: class 0 which refers to minimal support, class 1 which refers to non-invasive support, and class 2 which refers to invasive support. A two-stage classification system is built. First, the classification between class 0 and others is performed. Then, the classification between class 1 and class 2 is performed. The system is built using a dataset collected retrospectively from 3491 patients admitted to tertiary care hospitals at the University of Louisville Medical Center. The use of the feature selection method based on analysis of variance is demonstrated in the paper. Furthermore, a dimensionality reduction method called principal component analysis is used. XGBoost classifier achieves the best classification accuracy (84%) in the first stage. It also achieved optimal performance in the second stage, with a classification accuracy of 83%.
Collapse
Affiliation(s)
- Hisham Abdeltawab
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
| | - Fahmi Khalifa
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
| | - Yaser ElNakieb
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
| | - Ahmed Elnakib
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
| | - Fatma Taher
- College of Technological Innovation, Zayed University, Dubai P.O. Box 19282, United Arab Emirates
| | - Norah Saleh Alghamdi
- Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
| | - Harpal Singh Sandhu
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
| | - Ayman El-Baz
- Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA
- Correspondence:
| |
Collapse
|
13
|
Chen S, Qiu X, Tan X, Fang Z, Jin Y. A model-based hybrid soft actor-critic deep reinforcement learning algorithm for optimal ventilator settings. Inf Sci (N Y) 2022. [DOI: 10.1016/j.ins.2022.08.028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|