Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records

Ruiz, Víctor; Goldsmith, Michael P.; Shi, Lingyun; Simpao, Allan F.; Gálvez, Jorge A.; Naim, Maryam Y.; Gaynor, J. William; Tsui, Fu-Chiang

doi:10.1016/j.jtcvs.2021.10.060

Cited by 23 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, all the subjects were from a single institution and therefore, their results may not be generalizable to different populations or institutions. More recently, the same authors presented an improved version of their model, developed using a bigger cohort of 488 patients with single-ventricle physiology, showing also very good results as discussed above (15).…”

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 81%

“…Most of the postoperative adverse events are preceded by changes in patients' vital signs. Therefore, vital signs, such as heart rate (HR), respiration rate (RR), body temperature (BT), systolic (SBP), diastolic (DBP) and mean blood pressure (MBP) and oxygen saturation (SpO 2 ) are the most common patient's variables used by the different authors to build their predictive models (13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25), with different levels of resolution ranging from few seconds (18,21) to few hours (13). Zhai et al (25) were the first group proposing to use an ML model to predict ward-to-ICU transfer using automatically extracted EHR data.…”

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

“…They implemented a logistic regression model with 155 variables extracted from 36 measurements including vital signs, to predict ICU transfer for children in acute wards within the first 24 h of hospital admission, which showed an 0.91 area under the receiver operating characteristic (AUROC) in the test set. Then, several other ML-based models were proposed to predict clinical deterioration and/or an unplanned ward-to-ICU transfer ( 13 , 14 , 17 , 20 , 22 , 26 ), adverse events within the ICU ( 15 , 18 , 19 , 21 , 23 , 24 , 27 ) or need for critical care within the emergency department ( 28 ). However, the best results were achieved when vital signs data were combined with other variables such as medications and/or laboratory test data as shown by Ruiz et al ( 15 ).…”

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

“…Then, several other ML-based models were proposed to predict clinical deterioration and/or an unplanned ward-to-ICU transfer ( 13 , 14 , 17 , 20 , 22 , 26 ), adverse events within the ICU ( 15 , 18 , 19 , 21 , 23 , 24 , 27 ) or need for critical care within the emergency department ( 28 ). However, the best results were achieved when vital signs data were combined with other variables such as medications and/or laboratory test data as shown by Ruiz et al ( 15 ). They developed an ensemble of 5 extreme gradient boosting models, using a total of 1,028 regularly collected EHR variables (vital signs, medications, laboratory tests and diagnosis) to identify patients in the cardiac ICU at elevated risk of clinical deterioration.…”

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

“…They developed an ensemble of 5 extreme gradient boosting models, using a total of 1,028 regularly collected EHR variables (vital signs, medications, laboratory tests and diagnosis) to identify patients in the cardiac ICU at elevated risk of clinical deterioration. Although they validated the model in a small cohort, the resulting model achieved an AUROC of 0.92 at 4 h before deterioration ( 15 ).…”

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

See 4 more Smart Citations

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

et al. 2022

View full text Add to dashboard Cite

Pediatric congenital heart disease (CHD) patients are at higher risk of postoperative complications and clinical deterioration either due to their underlying pathology or due to the cardiac surgery, contributing significantly to mortality, morbidity, hospital and family costs, and poor quality of life. In current clinical practice, clinical deterioration is detected, in most of the cases, when it has already occurred. Several early warning scores (EWS) have been proposed to assess children at risk of clinical deterioration using vital signs and risk indicators, in order to intervene in a timely manner to reduce the impact of deterioration and risk of death among children. However, EWS are based on measurements performed at a single time point without incorporating trends nor providing information about patient's risk trajectory. Moreover, some of these measurements rely on subjective assessment making them susceptible to different interpretations. All these limitations could explain why the implementation of EWS in high-resource settings failed to show a significant decrease in hospital mortality. By means of machine learning (ML) based algorithms we could integrate heterogeneous and complex data to predict patient's risk of deterioration. In this perspective article, we provide a brief overview of the potential of ML technologies to improve the identification of pediatric CHD patients at high-risk for clinical deterioration after cardiac surgery, and present the CORTEX traffic light, a ML-based predictive system that Sant Joan de Déu Barcelona Children's Hospital is implementing, as an illustration of the application of an ML-based risk stratification system in a relevant hospital setting.

show abstract

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 81%

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

Section: Machine Learning To Predict Clinical Deterioration And/or Ic...mentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

et al. 2022

View full text Add to dashboard Cite

show abstract

Risk for Suicide Attempts Assessed Using the Patient Health Questionnaire–9 Modified for Teens

Tsui,

Ruiz,

Ryan

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceSuicide is a leading cause of death in US youths.ObjectiveTo assess whether screening with supplemental items 10 to 13 on the Patient Health Questionnaire–9 modified for teens (PHQ-9M) improves prediction of youth suicide attempts beyond the information provided by the first 9 items alone (the PHQ-9).Design, Setting, and ParticipantsThis retrospective cohort study used a retrospective cohort of adolescents aged 12 to 17 years who were screened for depression in outpatient facilities within a pediatric health care system between January 1, 2016, and December 31, 2022, with up to 1 year of follow-up to assess the occurrence of suicidal behavior. Follow-up was completed on December 31, 2023.ExposureScreening with the PHQ-9M.Main Outcomes and MeasuresThis study developed and compared prediction using 3 Cox proportional hazards regression models (CR-9, CR-13, and CR-3) of subsequent suicide attempts, determined by the hospital’s electronic health records up to 1 year following the last PHQ-9M screening. The CR-9 model used the PHQ-9 and the CR-13 model used all 13 items of PHQ-9M. The CR-3 model used the 3 most impactful variables selected from the 13 PHQ-9M items and PHQ-9 total score. All models were evaluated across 4 prediction horizons (30, 90, 180, and 365 days) following PHQ-9M screenings. Evaluation metrics were the area under the receiver operating characteristic curve (AUROC) and the area under the precision recall curve (AUPRC).ResultsOf 130 028 outpatients (65 520 [50.4%] male) with 272 402 PHQ-9M screenings, 549 (0.4%) had subsequent suicide attempts within 1 year following the PHQ-9M screening. The AUROC of the CR-9 model in the 365-day horizon was 0.77 (95% CI, 0.75-0.79); of the CR-13 model, 0.80 (95% CI, 0.78-0.82); and of the CR-3 model, 0.79 (95% CI, 0.76-0.81); the AUPRC of the CR-9 model was 0.02 (95% CI, 0.02-0.03); of the CR-13 model, 0.03 (95% CI, 0.02-0.03); and of the CR-3 model, 0.02 (95% CI, 0.02-0.03). The 3 most impactful items using adjusted hazard ratios were supplemental item 13 (lifetime suicide attempts; 3.06 [95% CI, 2.47-3.80]), supplemental item 10 (depressed mood severity in the past year; 2.99 [95% CI, 2.32-3.86]), and supplemental item 12 (serious suicidal ideation in the past month; 1.63 [95% CI, 1.25-2.12]). All of the models achieved higher AUROCs as prediction horizons shortened.Conclusions and RelevanceIn this cohort study of adolescent PHQ-9M screenings, the supplemental items on PHQ-9M screening improved prediction of youth suicide attempts compared with screening using the PHQ-9 across all prediction horizons, suggesting that PHQ-9M screening should be considered during outpatient visits to improve prediction of suicide attempts.

show abstract

An Anytime Querying Algorithm for Predicting Cardiac Arrest in Children: Work-in-Progress

Skinner

Raman

et al. 2022

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Early prediction of clinical deterioration using data-driven machine-learning modeling of electronic health records

Cited by 23 publications

References 29 publications

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

Risk for Suicide Attempts Assessed Using the Patient Health Questionnaire–9 Modified for Teens

An Anytime Querying Algorithm for Predicting Cardiac Arrest in Children: Work-in-Progress

Contact Info

Product

Resources

About