1
|
Zhang Y, Pan S, Hu Y, Ling B, Hua T, Tang L, Yang M. Establishing an artificial intelligence-based predictive model for long-term health-related quality of life for infected patients in the ICU. Heliyon 2024; 10:e35521. [PMID: 39170285 PMCID: PMC11336746 DOI: 10.1016/j.heliyon.2024.e35521] [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: 01/14/2024] [Revised: 07/30/2024] [Accepted: 07/30/2024] [Indexed: 08/23/2024] Open
Abstract
Objective To develop a model using a Chinese ICU infection patient database to predict long-term health-related quality of life (HRQOL) in survivors. Methods A patient database from the ICU of the Fourth People's Hospital in Zigong was analyzed, including data from 2019 to 2020. The subjects of the study were ICU infection survivors, and their post-discharge HRQOL was assessed through the SF-36 survey. The primary outcomes were the physical component summary (PCS) and mental component summary (MCS). We used artificial intelligence techniques for both feature selection and model building. Least absolute shrinkage and selection operator regression was used for feature selection, extreme gradient boosting (XGBoost) was used for model building, and the area under the receiver operating characteristic curve (AUROC) was used to assess model performance. Results The study included 917 ICU infection survivors. The median follow-up was 507.8 days. Their SF-36 scores, including PCS and MCS, were below the national average. The final prognostic model showed an AUROC of 0.72 for PCS and 0.63 for MCS. Within the sepsis subgroup, the predictive model AUROC values for PCS and MCS were 0.76 and 0.68, respectively. Conclusions This study established a valuable prognostic model using artificial intelligence to predict long-term HRQOL in ICU infection patients, which supports clinical decision making, but requires further optimization and validation.
Collapse
Affiliation(s)
- Yang Zhang
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| | - Sinong Pan
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| | - Yan Hu
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| | - Bingrui Ling
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| | - Tianfeng Hua
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| | - Lunxian Tang
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Department of Internal Emergency Medicine (North), Shanghai East Hospital, Tongji University School of Medicine, Shanghai, 200120, PR China
| | - Min Yang
- The Second Department of Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
- Laboratory of Cardiopulmonary Resuscitation and Critical Care, The Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, 230601, PR China
| |
Collapse
|
2
|
Paul N, Cittadino J, Krampe H, Denke C, Spies CD, Weiss B. Determinants of Subjective Mental and Functional Health of Critical Illness Survivors: Comparing Pre-ICU and Post-ICU Status. Crit Care Med 2024; 52:704-716. [PMID: 38189649 PMCID: PMC11008443 DOI: 10.1097/ccm.0000000000006158] [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: 01/09/2024]
Abstract
OBJECTIVES To compare ICU survivors' subjective mental and functional health before ICU admission and after discharge and to assess determinants of subjective health decline or improvement. DESIGN Secondary analysis of the multicenter cluster-randomized Enhanced Recovery after Intensive Care trial ( ClinicalTrials.gov : NCT03671447). SETTING Ten ICU clusters in Germany. PATIENTS Eight hundred fifty-five patients with 1478 follow-up assessments. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS At two patient follow-ups scheduled 3 and 6 months after ICU discharge, patients rated their subjective mental and functional/physical health on two separate visual analog scales from 0 (worst) to 10 (best) in the previous week and before ICU admission. We compared pre-ICU and post-ICU subjective health and used mixed-effects regression to assess determinants of a health decline or improvement. At the first follow-up, 20% ( n = 165/841) and 30% ( n = 256/849) of patients reported a decline in subjective mental and functional health of at least three points, respectively; 16% ( n = 133/841 and n = 137/849) outlined improvements of mental and functional health. For 65% ( n = 543/841) and 54% ( n = 456/849), mental and functional health did not change three points or more at the first follow-up. Multivariable mixed-effects logistic regressions revealed that the ICU length of stay was a predictor of mental (adjusted odds ratio [OR] per ICU day, 1.04; 95% CI, 1.00-1.09; p = 0.038) and functional health (adjusted OR per ICU day, 1.06; 95% CI, 1.01-1.12; p = 0.026) decline. The odds of a mental health decline decreased with age (adjusted OR per year, 0.98; 95% CI, 0.96-0.99; p = 0.003) and the odds of a functional health decline decreased with time after discharge (adjusted OR per month, 0.86; 95% CI, 0.79-0.94; p = 0.001). CONCLUSIONS The majority of ICU survivors did not experience substantial changes in their subjective health status, but patients with long ICU stays were prone to subjective mental and functional health decline. Hence, post-ICU care in post-ICU clinics could focus on these patients.
Collapse
Affiliation(s)
- Nicolas Paul
- All authors: Department of Anesthesiology and Intensive Care Medicine, Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Berlin, Germany
| | | | | | | | | | | |
Collapse
|
3
|
van Sleeuwen D, Zegers M, Ramjith J, Cruijsberg JK, Simons KS, van Bommel D, Burgers-Bonthuis D, Koeter J, Bisschops LLA, Janssen I, Rettig TCD, van der Hoeven JG, van de Laar FA, van den Boogaard M. Prediction of Long-Term Physical, Mental, and Cognitive Problems Following Critical Illness: Development and External Validation of the PROSPECT Prediction Model. Crit Care Med 2024; 52:200-209. [PMID: 38099732 PMCID: PMC10793772 DOI: 10.1097/ccm.0000000000006073] [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: 01/19/2024]
Abstract
OBJECTIVES ICU survivors often suffer from long-lasting physical, mental, and cognitive health problems after hospital discharge. As several interventions that treat or prevent these problems already start during ICU stay, patients at high risk should be identified early. This study aimed to develop a model for early prediction of post-ICU health problems within 48 hours after ICU admission. DESIGN Prospective cohort study in seven Dutch ICUs. SETTING/PATIENTS ICU patients older than 16 years and admitted for greater than or equal to 12 hours between July 2016 and March 2020. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Outcomes were physical problems (fatigue or ≥ 3 new physical symptoms), mental problems (anxiety, depression, or post-traumatic stress disorder), and cognitive impairment. Patient record data and questionnaire data were collected at ICU admission, and after 3 and 12 months, of 2,476 patients. Several models predicting physical, mental, or cognitive problems and a composite score at 3 and 12 months were developed using variables collected within 48 hours after ICU admission. Based on performance and clinical feasibility, a model, PROSPECT, predicting post-ICU health problems at 3 months was chosen, including the predictors of chronic obstructive pulmonary disease, admission type, expected length of ICU stay greater than or equal to 2 days, and preadmission anxiety and fatigue. Internal validation using bootstrapping on data of the largest hospital ( n = 1,244) yielded a C -statistic of 0.73 (95% CI, 0.70-0.76). External validation was performed on data ( n = 864) from the other six hospitals with a C -statistic of 0.77 (95% CI, 0.73-0.80). CONCLUSIONS The developed and externally validated PROSPECT model can be used within 48 hours after ICU admission for identifying patients with an increased risk of post-ICU problems 3 months after ICU admission. Timely preventive interventions starting during ICU admission and follow-up care can prevent or mitigate post-ICU problems in these high-risk patients.
Collapse
Affiliation(s)
- Dries van Sleeuwen
- Department of Primary and Community Care, Radboud University Medical Center, Nijmegen, The Netherlands
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Marieke Zegers
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Jordache Ramjith
- Department for Health Evidence, Biostatistics Research Group, Radboud University Medical Center, Nijmegen, The Netherlands
| | | | - Koen S Simons
- Department of Intensive Care Medicine, Jeroen Bosch Hospital, 's Hertogenbosch, The Netherlands
| | - Daniëlle van Bommel
- Department of Intensive Care Medicine, Bernhoven Hospital, Uden, The Netherlands
| | | | - Julia Koeter
- Department of Intensive Care Medicine, CWZ, Nijmegen, The Netherlands
| | - Laurens L A Bisschops
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Inge Janssen
- Department of Intensive Care Medicine, Maasziekenhuis, Boxmeer, The Netherlands
| | - Thijs C D Rettig
- Department of Anesthesiology, Intensive Care Medicine, and Pain Medicine, Amphia Hospital, Breda, The Netherlands
| | | | - Floris A van de Laar
- Department of Primary and Community Care, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Mark van den Boogaard
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| |
Collapse
|
4
|
Porter LL, Simons KS, van den Boogaard M, Zegers M. The authors reply. Crit Care Med 2023; 51:e245-e246. [PMID: 37902355 DOI: 10.1097/ccm.0000000000005972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/31/2023]
Affiliation(s)
- Lucy L Porter
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
- Department of Intensive Care, Jeroen Bosch Hospital, 's-Hertogenbosch, The Netherlands
| | - Koen S Simons
- Department of Intensive Care, Jeroen Bosch Hospital, 's-Hertogenbosch, The Netherlands
| | - Mark van den Boogaard
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Marieke Zegers
- Department of Intensive Care, Radboud University Medical Center, Nijmegen, The Netherlands
| |
Collapse
|
5
|
Gilholm P, Gibbons K, Brüningk S, Klatt J, Vaithianathan R, Long D, Millar J, Tomaszewski W, Schlapbach LJ. Machine learning to predict poor school performance in paediatric survivors of intensive care: a population-based cohort study. Intensive Care Med 2023; 49:785-795. [PMID: 37354231 PMCID: PMC10354166 DOI: 10.1007/s00134-023-07137-1] [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: 02/23/2023] [Accepted: 06/09/2023] [Indexed: 06/26/2023]
Abstract
PURPOSE Whilst survival in paediatric critical care has improved, clinicians lack tools capable of predicting long-term outcomes. We developed a machine learning model to predict poor school outcomes in children surviving intensive care unit (ICU). METHODS Population-based study of children < 16 years requiring ICU admission in Queensland, Australia, between 1997 and 2019. Failure to meet the National Minimum Standard (NMS) in the National Assessment Program-Literacy and Numeracy (NAPLAN) assessment during primary and secondary school was the primary outcome. Routine ICU information was used to train machine learning classifiers. Models were trained, validated and tested using stratified nested cross-validation. RESULTS 13,957 childhood ICU survivors with 37,200 corresponding NAPLAN tests after a median follow-up duration of 6 years were included. 14.7%, 17%, 15.6% and 16.6% failed to meet NMS in school grades 3, 5, 7 and 9. The model demonstrated an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.8 (standard deviation SD, 0.01), with 51% specificity to reach 85% sensitivity [relative Area Under the Precision Recall Curve (rel-AUPRC) 3.42, SD 0.06]. Socio-economic status, illness severity, and neurological, congenital, and genetic disorders contributed most to the predictions. In children with no comorbidities admitted between 2009 and 2019, the model achieved a AUROC of 0.77 (SD 0.03) and a rel-AUPRC of 3.31 (SD 0.42). CONCLUSIONS A machine learning model using data available at time of ICU discharge predicted failure to meet minimum educational requirements at school age. Implementation of this prediction tool could assist in prioritizing patients for follow-up and targeting of rehabilitative measures.
Collapse
Affiliation(s)
- Patricia Gilholm
- Child Health Research Centre, The University of Queensland, Brisbane, QLD, Australia
| | - Kristen Gibbons
- Child Health Research Centre, The University of Queensland, Brisbane, QLD, Australia
| | - Sarah Brüningk
- Department of Biosystems Science and Engineering, ETH Zurich, 4058, Basel, Switzerland
- SIB Swiss Institute of Bioinformatics, 1015, Lausanne, Switzerland
| | - Juliane Klatt
- Department of Biosystems Science and Engineering, ETH Zurich, 4058, Basel, Switzerland
- SIB Swiss Institute of Bioinformatics, 1015, Lausanne, Switzerland
| | - Rhema Vaithianathan
- Institute for Social Science Research, The University of Queensland, Brisbane, QLD, Australia
| | - Debbie Long
- Child Health Research Centre, The University of Queensland, Brisbane, QLD, Australia
- School of Nursing, Centre for Healthcare Transformation, Queensland University of Technology, Brisbane, QLD, Australia
| | - Johnny Millar
- Paediatric Intensive Care Unit, The Royal Children's Hospital, Melbourne, VIC, Australia
- The Australian and New Zealand Intensive Care Society (ANZICS) Centre for Outcome and Resource Evaluation (CORE), ANZICS House, Melbourne, VIC, Australia
- Murdoch Children's Research Institute, Melbourne, VIC, Australia
| | - Wojtek Tomaszewski
- Institute for Social Science Research, The University of Queensland, Brisbane, QLD, Australia
| | - Luregn J Schlapbach
- Child Health Research Centre, The University of Queensland, Brisbane, QLD, Australia.
- Department of Intensive Care and Neonatology, and Children's Research Center, University Children's Hospital Zurich, Steinwiesstrasse 75, 8032, Zurich, Switzerland.
| |
Collapse
|
6
|
Porter LL, Simons KS, Ramjith J, Corsten S, Westerhof B, Rettig TCD, Ewalds E, Janssen I, van der Hoeven JG, van den Boogaard M, Zegers M. Development and External Validation of a Prediction Model for Quality of Life of ICU Survivors: A Subanalysis of the MONITOR-IC Prospective Cohort Study. Crit Care Med 2023; 51:632-641. [PMID: 36825895 DOI: 10.1097/ccm.0000000000005800] [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: 02/25/2023]
Abstract
OBJECTIVES To develop and externally validate a prediction model for ICU survivors' change in quality of life 1 year after ICU admission that can support ICU physicians in preparing patients for life after ICU and managing their expectations. DESIGN Data from a prospective multicenter cohort study (MONITOR-IC) were used. SETTING Seven hospitals in the Netherlands. PATIENTS ICU survivors greater than or equal to 16 years old. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS Outcome was defined as change in quality of life, measured using the EuroQol 5D questionnaire. The developed model was based on data from an academic hospital, using multivariable linear regression analysis. To assist usability, variables were selected using the least absolute shrinkage and selection operator method. External validation was executed using data of six nonacademic hospitals. Of 1,804 patients included in analysis, 1,057 patients (58.6%) were admitted to the academic hospital, and 747 patients (41.4%) were admitted to a nonacademic hospital. Forty-nine variables were entered into a linear regression model, resulting in an explained variance ( R2 ) of 56.6%. Only three variables, baseline quality of life, admission type, and Glasgow Coma Scale, were selected for the final model ( R2 = 52.5%). External validation showed good predictive power ( R2 = 53.2%). CONCLUSIONS This study developed and externally validated a prediction model for change in quality of life 1 year after ICU admission. Due to the small number of predictors, the model is appealing for use in clinical practice, where it can be implemented to prepare patients for life after ICU. The next step is to evaluate the impact of this prediction model on outcomes and experiences of patients.
Collapse
Affiliation(s)
- Lucy L Porter
- Department of Intensive Care, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
- Department of Intensive Care, Jeroen Bosch Hospital, 's-Hertogenbosch, The Netherlands
| | - Koen S Simons
- Department of Intensive Care, Jeroen Bosch Hospital, 's-Hertogenbosch, The Netherlands
| | - Jordache Ramjith
- Department of Health Evidence, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Stijn Corsten
- Department of Intensive Care, Canisius Wilhelmina Hospital, Nijmegen, The Netherlands
| | - Brigitte Westerhof
- Department of Intensive Care, Rijnstate Hospital, Arnhem, The Netherlands
| | - Thijs C D Rettig
- Department of Anesthesiology, Intensive Care and Pain Medicine, Amphia Hospital, Breda, The Netherlands
| | - Esther Ewalds
- Department of Intensive Care, Bernhoven Hospital, Uden, The Netherlands
| | - Inge Janssen
- Department of Intensive Care, Maas Hospital Pantein, Boxmeer, The Netherlands
| | - Johannes G van der Hoeven
- Department of Intensive Care, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Mark van den Boogaard
- Department of Intensive Care, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Marieke Zegers
- Department of Intensive Care, Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands
| |
Collapse
|