Less is more: Detecting clinical deterioration in the hospital with machine learning using only age, heart rate, and respiratory rate

Akel, Mary; Carey, Kyle; Winslow, Christopher; Churpek, Matthew M; Edelson, Dana P.

doi:10.1016/j.resuscitation.2021.08.024

Cited by 26 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to the high density of measurements, continuously monitored vital sign data show more variance than intermittent data in our experience, and are more subject to peaks and troughs depending on a patient’s activity level. Akel et al [ 9 ] also found that the (intermittently measured) maximum RR and HR were important predictors. We did not use the maximum value, since we expected the maximum value to rely highly on both activity level and outliers (eg, due to coughing or talking), and would therefore not be clinically useful.…”

Section: Discussionmentioning

confidence: 99%

“…However, machine-learning models have proven to be more accurate than current practice in several fields of medicine [ 26 ]. In predicting deterioration, some studies have shown that machine-learning models outperform “simple” regression models [ 9 , 27 , 28 ]. In a recent study, a machine-learning model was developed that uses several summary measures of vital signs to predict the deterioration of high-risk patients [ 21 ].…”

Section: Discussionmentioning

confidence: 99%

“…Continuous monitoring can be beneficial in two ways. First, trends in vital signs over time have been shown to have higher predictive accuracy than isolated vital sign values when incorporated in prediction models [ 8 , 9 ]. With continuous monitoring, trends in vital signs are available at any point in time, and can therefore be used to make up-to-date predictions more frequently.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Association of Continuously Measured Vital Signs With Respiratory Insufficiency in Hospitalized COVID-19 Patients: Retrospective Cohort Study

Goor¹,

Vernooij²,

Breteler³

et al. 2022

Interact J Med Res

View full text Add to dashboard Cite

Background Continuous monitoring of vital signs has the potential to assist in the recognition of deterioration of patients admitted to the general ward. However, methods to efficiently process and use continuously measured vital sign data remain unclear. Objective The aim of this study was to explore methods to summarize continuously measured vital sign data and evaluate their association with respiratory insufficiency in COVID-19 patients at the general ward. Methods In this retrospective cohort study, we included patients admitted to a designated COVID-19 cohort ward equipped with continuous vital sign monitoring. We collected continuously measured data of respiratory rate, heart rate, and oxygen saturation. For each patient, 7 metrics to summarize vital sign data were calculated: mean, slope, variance, occurrence of a threshold breach, number of episodes, total duration, and area above/under a threshold. These summary measures were calculated over timeframes of either 4 or 8 hours, with a pause between the last data point and the endpoint (the “lead”) of 4, 2, 1, or 0 hours, and with 3 predefined thresholds per vital sign. The association between each of the summary measures and the occurrence of respiratory insufficiency was calculated using logistic regression analysis. Results Of the 429 patients that were monitored, 334 were included for analysis. Of these, 66 (19.8%) patients developed respiratory insufficiency. Summarized continuously measured vital sign data in timeframes close to the endpoint showed stronger associations than data measured further in the past (ie, lead 0 vs 1, 2, or 4 hours), and summarized estimates over 4 hours of data had stronger associations than estimates taken over 8 hours of data. The mean was consistently strongly associated with respiratory insufficiency for the three vital signs: in a 4-hour timeframe without a lead, the standardized odds ratio for heart rate, respiratory rate, and oxygen saturation was 2.59 (99% CI 1.74-4.04), 5.05 (99% CI 2.87-10.03), and 3.16 (99% CI 1.78-6.26), respectively. The strength of associations of summary measures varied per vital sign, timeframe, and lead. Conclusions The mean of a vital sign showed a relatively strong association with respiratory insufficiency for the majority of vital signs and timeframes. The type of vital sign, length of the timeframe, and length of the lead influenced the strength of associations. Highly associated summary measures and their combinations could be used in a clinical prediction score or algorithm for an automatic alarm system.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Association of Continuously Measured Vital Signs With Respiratory Insufficiency in Hospitalized COVID-19 Patients: Retrospective Cohort Study

Goor¹,

Vernooij²,

Breteler³

et al. 2022

Interact J Med Res

View full text Add to dashboard Cite

show abstract

“…ML facilitates the automatic analysis of highly complex data and produces meaningful results. ML models can improve prediction accuracy with the same data or reduce features with the same performance 17 . Cho and Kwon used vital signs over the past 8 h to develop a deep learning-based early warning score to predict deterioration in patients in general wards accurately.…”

Section: Introductionmentioning

confidence: 99%

Improved inpatient deterioration detection in general wards by using time-series vital signs

Chiu

Jang

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Although in-hospital cardiac arrest is uncommon, it has a high mortality rate. Risk identification of at-risk patients is critical for post-cardiac arrest survival rates. Early warning scoring systems are generally used to identify hospitalized patients at risk of deterioration. However, these systems often require clinical data that are not always regularly measured. We developed a more accurate, machine learning-based model to predict clinical deterioration. The time series early warning score (TEWS) used only heart rate, systolic blood pressure, and respiratory data, which are regularly measured in general wards. We tested the performance of the TEWS in two tasks performed with data from the electronic medical records of 16,865 adult admissions and compared the results with those of other classifications. The TEWS detected more deteriorations with the same level of specificity as the different algorithms did when inputting vital signs data from 48 h before an event. Our framework improved in-hospital cardiac arrest prediction and demonstrated that previously obtained vital signs data can be used to identify at-risk patients in real-time. This model may be an alternative method for detecting patient deterioration.

show abstract

“…eCART2 is a nonlinear logistic regression model, which includes laboratory data and vital signs. The authors have also developed a random forest model, although this does not appear to have been implemented into real-time clinical systems[28 ]. eCART has been evaluated in multiple retrospective validation studies against widely used EWS, including Between The Flags (BTF), NEWS and the Modified Early Warning Score (MEWS) and was shown to better predict IHCA, unplanned ICU admission and death[29,30…”

mentioning

confidence: 99%

Artificial intelligence and clinical deterioration

Malycha

Bacchi

Redfern

2022

Current Opinion in Critical Care

View full text Add to dashboard Cite

Purpose of reviewTo provide an overview of the systems being used to identify and predict clinical deterioration in hospitalised patients, with focus on the current and future role of artificial intelligence (AI). Recent findingsThere are five leading AI driven systems in this field: the Advanced Alert Monitor (AAM), the electronic Cardiac Arrest Risk Triage (eCART) score, Hospital wide Alert Via Electronic Noticeboard, the Mayo Clinic Early Warning Score, and the Rothman Index (RI). Each uses Electronic Patient Record (EPR) data and machine learning to predict adverse events. Less mature but relevant evolutions are occurring in the fields of Natural Language Processing, Time and Motion Studies, AI Sepsis and COVID-19 algorithms. SummaryResearch-based AI-driven systems to predict clinical deterioration are increasingly being developed, but few are being implemented into clinical workflows. Escobar et al. (AAM) provide the current gold standard for robust model development and implementation methodology. Multiple technologies show promise, however, the pathway to meaningfully affect patient outcomes remains challenging.

show abstract

Less is more: Detecting clinical deterioration in the hospital with machine learning using only age, heart rate, and respiratory rate

Cited by 26 publications

References 9 publications

Association of Continuously Measured Vital Signs With Respiratory Insufficiency in Hospitalized COVID-19 Patients: Retrospective Cohort Study

Association of Continuously Measured Vital Signs With Respiratory Insufficiency in Hospitalized COVID-19 Patients: Retrospective Cohort Study

Improved inpatient deterioration detection in general wards by using time-series vital signs

Artificial intelligence and clinical deterioration

Contact Info

Product

Resources

About