Derivation and validation of modified early warning score plus SpO2/FiO2 score for predicting acute deterioration of patients with hematological malignancies

Oncology Intensive Care Units: Distinguishing Features and Clinical Considerations

The rapidly advancing field of cancer therapeutics has led to increased longevity among cancer patients as well as increasing complexity of cancer-related illness and associated comorbid conditions. As a result, institutions and organizations that specialize in the in-patient care of cancer patients have similarly evolved to meet the constantly changing needs of this unique patient population. Within these institutions, the intensive care units that specialize in the care of critically ill cancer patients represent an especially unique clinical resource. This article explores some of the defining and distinguishing characteristics associated with oncology ICUs.

Clinical Outcomes and Determinants of Survival in Patients with Hematologic Malignancies Admitted to Intensive Care Units with Critical Illness

Outcomes of patients with hematologic malignancies requiring ICU care for critical illness are suboptimal and represent a major unmet need in this population. We present data from a dedicated haematology oncology setting including 63 patients with a median age of 60 years admitted to the ICU for critical illness with organ dysfunction. The most common underlying diagnosis was multiple myeloma (30%) followed by acute myeloid leukemia (25%). Chemotherapy had been initiated for 90.7% patients before ICU admission. The most common indication for ICU care was respiratory failure (36.5%) and shock (17.5%) patients. Evidence of sepsis was present in 44 (69%) patients. After shifting to ICU, 32 (50%) patients required inotropic support and 18 (28%) required invasive mechanical ventilation. After a median of 5 days of ICU stay, 43.1% patients had died, most commonly due to multiorgan dysfunction. Risk of mortality was higher with involvement of more than two major organs (p = .001), underlying AML (p = .001), need for mechanical ventilation (p = .001) and high inotrope usage (p = .004). Neutropenia was not associated with mortality. Our study indicates high rates of short term mortality and defines prognostic factors which can be used to prognosticate patients and establish goals of care.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12288-024-01757-3.

Development and Validation of a Prediction Model for 1-Year Mortality in Patients With a Hematologic Malignancy Admitted to the ICU

OBJECTIVES

To develop and validate a prediction model for 1-year mortality in patients with a hematologic malignancy acutely admitted to the ICU.

DESIGN

A retrospective cohort study.

SETTING

Five university hospitals in the Netherlands between 2002 and 2015.

PATIENTS

A total of 1097 consecutive patients with a hematologic malignancy were acutely admitted to the ICU for at least 24 h.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

We created a 13-variable model from 22 potential predictors. Key predictors included active disease, age, previous hematopoietic stem cell transplantation, mechanical ventilation, lowest platelet count, acute kidney injury, maximum heart rate, and type of malignancy. A bootstrap procedure reduced overfitting and improved the model's generalizability. This involved estimating the optimism in the initial model and shrinking the regression coefficients accordingly in the final model. We assessed performance using internal-external cross-validation by center and compared it with the Acute Physiology and Chronic Health Evaluation II model. Additionally, we evaluated clinical usefulness through decision curve analysis. The overall 1-year mortality rate observed in the study was 62% (95% CI, 59-65). Our 13-variable prediction model demonstrated acceptable calibration and discrimination at internal-external validation across centers (C-statistic 0.70; 95% CI, 0.63-0.77), outperforming the Acute Physiology and Chronic Health Evaluation II model (C-statistic 0.61; 95% CI, 0.57-0.65). Decision curve analysis indicated overall net benefit within a clinically relevant threshold probability range of 60-100% predicted 1-year mortality.

CONCLUSIONS

Our newly developed 13-variable prediction model predicts 1-year mortality in hematologic malignancy patients admitted to the ICU more accurately than the Acute Physiology and Chronic Health Evaluation II model. This model may aid in shared decision-making regarding the continuation of ICU care and end-of-life considerations.

The predictive value of the modified early warning score for admission to the intensive care unit in patients with a hematologic malignancy - A multicenter observational study

OBJECTIVES

The modified early warning score (MEWS) is used to detect clinical deterioration of hospitalized patients. We aimed to investigate the predictive value of MEWS and derived quick Sequential Organ Failure Assessment (qSOFA) scores for intensive care unit admission in patients with a hematologic malignancy admitted to the ward.

DESIGN

Retrospective, observational study in two Dutch university hospitals.

SETTING

Data from adult patients with a hematologic malignancy, admitted to the ward over a 2-year period, were extracted from electronic patient files.

MAIN OUTCOME MEASURES

Intensive care admission.

RESULTS

We included 395 patients with 736 hospital admissions; 2% (n = 15) of admissions resulted in admission to the intensive care unit. A higher MEWS (OR 1.5; 95 %CI 1.3-1.80) and qSOFA (OR 4.4; 95 %CI 2.1-9.3) were associated with admission. Using restricted cubic splines, a rise in the probability of admission for a MEWS ≥ 6 was observed. The AUC of MEWS for predicting admission was 0.830, the AUC of qSOFA was 0.752. MEWS was indicative for intensive care unit admission two days before admission.

CONCLUSIONS

MEWS was a sensitive predictor of ICU admission in patients with a hematologic malignancy, superior to qSOFA. Future studies should confirm cut-off values and identify potential additional characteristics, to further enhance identification of critically ill hemato-oncology patients.

IMPLICATIONS FOR CLINICAL PRACTICE

The Modified Early Warning Score (MEWS) can be used as a tool for healthcare providers to monitor clinical deterioration and predict the need for intensive care unit admission in patients with a hematologic malignancy. Yet, consistent application and potential reevaluation of current thresholds is crucial. This will enable bedside nurses to more effectively identify patients needing adjunctive care, facilitating timely interventions and improved outcome.

Deep Learning-Based Early Warning Score for Predicting Clinical Deterioration in General Ward Cancer Patients

BACKGROUND

Cancer patients who are admitted to hospitals are at high risk of short-term deterioration due to treatment-related or cancer-specific complications. A rapid response system (RRS) is initiated when patients who are deteriorating or at risk of deteriorating are identified. This study was conducted to develop a deep learning-based early warning score (EWS) for cancer patients (Can-EWS) using delta values in vital signs.

METHODS

A retrospective cohort study was conducted on all oncology patients who were admitted to the general ward between 2016 and 2020. The data were divided into a training set (January 2016-December 2019) and a held-out test set (January 2020-December 2020). The primary outcome was clinical deterioration, defined as the composite of in-hospital cardiac arrest (IHCA) and unexpected intensive care unit (ICU) transfer.

RESULTS

During the study period, 19,739 cancer patients were admitted to the general wards and eligible for this study. Clinical deterioration occurred in 894 cases. IHCA and unexpected ICU transfer prevalence was 1.77 per 1000 admissions and 43.45 per 1000 admissions, respectively. We developed two models: Can-EWS V1, which used input vectors of the original five input variables, and Can-EWS V2, which used input vectors of 10 variables (including an additional five delta variables). The cross-validation performance of the clinical deterioration for Can-EWS V2 (AUROC, 0.946; 95% confidence interval [CI], 0.943-0.948) was higher than that for MEWS of 5 (AUROC, 0.589; 95% CI, 0.587-0.560; p < 0.001) and Can-EWS V1 (AUROC, 0.927; 95% CI, 0.924-0.931). As a virtual prognostic study, additional validation was performed on held-out test data. The AUROC and 95% CI were 0.588 (95% CI, 0.588-0.589), 0.890 (95% CI, 0.888-0.891), and 0.898 (95% CI, 0.897-0.899), for MEWS of 5, Can-EWS V1, and the deployed model Can-EWS V2, respectively. Can-EWS V2 outperformed other approaches for specificities, positive predictive values, negative predictive values, and the number of false alarms per day at the same sensitivity level on the held-out test data.

CONCLUSIONS

We have developed and validated a deep learning-based EWS for cancer patients using the original values and differences between consecutive measurements of basic vital signs. The Can-EWS has acceptable discriminatory power and sensitivity, with extremely decreased false alarms compared with MEWS.

Modified Early Warning Score (MEWS) as a predictor of intensive care unit admission in cancer patient on chemotherapy with positive blood culture: A retrospective cohort study

BACKGROUND

Although the usefulness of the Modified Early Warning Score (MEWS) in predicting clinical deterioration or the need for intensive care unit (ICU) admission has been evaluated in several studies, only few reports have considered the immune status of the patient. Patients receiving chemotherapy for cancer are at risk of sepsis. This study aimed to assess the validity of MEWS in predicting clinical deterioration, ICU admission, and mortality among immunocompromised cancer patients on chemotherapy (CPOC).

METHODS

This retrospective cohort study was conducted at a tertiary care center in Jeddah, Saudi Arabia. Subjects aged>14 years with positive blood cultures, who were hospitalized between June 2016 and June 2017, were included. MEWS was calculated at different time intervals: before, after, and at the time (0-time) of positive blood culture.

RESULTS

Overall, 192 patients were enrolled, including 89 CPOC and 103 immunocompetent individuals (controls). ICU admission rate was significantly lower in the CPOC group than in the control group (21 % vs. 50 %, P < .001). Positive MEWS rate (score ≥4) at 0-time was lower in the CPOC group, but the difference was not significant (39.7 % vs. 60.3 %, P = .129). In the CPOC group, positive MEWS rate (score ≥4) had a sensitivity, specificity, positive predictive value, and negative predictive value of 52.6 %, 70 %, 32.3 %, and 84 %, respectively, which was comparable to that observed in the control group. Furthermore, the receiver operating characteristic curve in the CPOC group showed that MEWS calculated 12-36 h before positive blood culture was a significant predictor of ICU admission. The optimal threshold of MEWS with the best sensitivity and specificity was ≥ 3 for the CPOC group and ≥ 4 for the control group to predict ICU admission. MEWS was a generally poor predictor of mortality.

CONCLUSION

MEWS ≥ 3 calculated 12-36 h before positive blood culture is the best predictor of ICU admission for CPOC.

Predictors of Repeat Medical Emergency Team Activation in Deteriorating Ward Patients: A Retrospective Cohort Study

Recurrent clinical deterioration and repeat medical emergency team (MET) activation are common and associated with high in-hospital mortality. This study assessed the predictors for repeat MET activation in deteriorating patients admitted to a general ward. We retrospectively analyzed the data of 5512 consecutive deteriorating hospitalized adult patients who required MET activation in the general ward. The patients were divided into two groups according to repeat MET activation. Multivariate logistic regression analyses were used to identify the predictors for repeat MET activation. Hematological malignancies (odds ratio, 2.07; 95% confidence interval, 1.54-2.79) and chronic lung disease (1.49; 1.07-2.06) were associated with a high risk of repeat MET activation. Among the causes for MET activation, respiratory distress (1.76; 1.19-2.60) increased the risk of repeat MET activation. A low oxygen saturation-to-fraction of inspired oxygen ratio (0.97; 0.95-0.98), high-flow nasal cannula oxygenation (4.52; 3.56-5.74), airway suctioning (4.63; 3.59-5.98), noninvasive mechanical ventilation (1.52; 1.07-2.68), and vasopressor support (1.76; 1.22-2.54) at first MET activation increased the risk of repeat MET activation. The risk factors identified in this study may be useful to identify patients at risk of repeat MET activation at the first MET activation. This would allow the classification of high-risk patients and the application of aggressive interventions to improve outcomes.

Early Warning Scores and Their Application in the Inpatient Oncology Settings

Early Warning Score (EWS) systems are tools that use alterations in vital signs to rapidly identify clinically deteriorating patients and escalate care accordingly. Since its conception in 1997, EWSs have been used in several settings, including the general inpatient ward, intensive care units, and the emergency department. Several iterations of EWSs have been developed with varying levels of sensitivity and specificity for use in different populations. There are multiple strengths of these tools, including their simplicity and their ability to standardize communication and to reduce inappropriate or delayed referrals to the intensive care unit. Although early identification of deteriorating patients in the oncology population is vital to reduce morbidity and mortality and to improve long-term prognosis, the application in the oncology setting has been limited. Patients with an oncological diagnosis are usually older, medically complex, and can have increased susceptibility to infections, end-organ damage, and death. A search using PubMed and Scopus was conducted for articles published between January 1997 and November 2020 pertaining to EWSs in the oncology setting. Seven relevant studies were identified and analyzed. The most commonly used EWS in this setting was the Modified Early Warning Score. Of the seven studies, only two included prospective validation of the EWS in the oncology population and the other five only included a retrospective assessment of the data. The majority of studies were limited by their small sample size, single-institution analysis, and retrospective nature. Future studies should assess dynamic changes in scores over time and evaluate balance measures to identify use of health care resources.

Predicting and Responding to Clinical Deterioration in Hospitalized Patients by Using Artificial Intelligence: Protocol for a Mixed Methods, Stepped Wedge Study

Background

The early identification of clinical deterioration in patients in hospital units can decrease mortality rates and improve other patient outcomes; yet, this remains a challenge in busy hospital settings. Artificial intelligence (AI), in the form of predictive models, is increasingly being explored for its potential to assist clinicians in predicting clinical deterioration.

Objective

Using the Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 model, this study aims to assess whether an AI-enabled work system improves clinical outcomes, describe how the clinical deterioration index (CDI) predictive model and associated work processes are implemented, and define the emergent properties of the AI-enabled work system that mediate the observed clinical outcomes.

Methods

This study will use a mixed methods approach that is informed by the SEIPS 2.0 model to assess both processes and outcomes and focus on how physician-nurse clinical teams are affected by the presence of AI. The intervention will be implemented in hospital medicine units based on a modified stepped wedge design featuring three stages over 11 months—stage 0 represents a baseline period 10 months before the implementation of the intervention; stage 1 introduces the CDI predictions to physicians only and triggers a physician-driven workflow; and stage 2 introduces the CDI predictions to the multidisciplinary team, which includes physicians and nurses, and triggers a nurse-driven workflow. Quantitative data will be collected from the electronic health record for the clinical processes and outcomes. Interviews will be conducted with members of the multidisciplinary team to understand how the intervention changes the existing work system and processes. The SEIPS 2.0 model will provide an analytic framework for a mixed methods analysis.

Results

A pilot period for the study began in December 2020, and the results are expected in mid-2022.

Conclusions

This protocol paper proposes an approach to evaluation that recognizes the importance of assessing both processes and outcomes to understand how a multifaceted AI-enabled intervention affects the complex team-based work of identifying and managing clinical deterioration.

International Registered Report Identifier (IRRID)

PRR1-10.2196/27532

Validation of National Early Warning Score for predicting 30-day mortality after rapid response system activation in Japan

Aim

Although rapid response systems (RRS) are used to prevent adverse events, Japan reportedly has low activation rates and high mortality rates. The National Early Warning Score (NEWS) could provide a solution, but it has not been validated in Japan. We aimed to validate NEWS for Japanese patients.

Methods

This retrospective observational study included data of 2,255 adult patients from 33 facilities registered in the In‐Hospital Emergency Registry in Japan between January 2014 and March 2018. The primary evaluated outcome was mortality rate 30 days after RRS activation. Accuracy of NEWS was analyzed with the correlation coefficient and area under the receiver operating characteristic curve. Prediction weights of NEWS parameters were then analyzed using multiple logistic regression and a machine learning method, classification and regression trees.

Results

The correlation coefficient of NEWS for 30‐day mortality rate was 0.95 (95% confidence interval [CI], 0.88–0.98) and the area under the receiver operating characteristic curve was 0.668 (95% CI, 0.642–0.693). Sensitivity and specificity values with a cut‐off score of 7 were 89.8% and 45.1%, respectively. Regarding prediction values of each parameter, oxygen saturation showed the highest odds ratio of 1.36 (95% CI, 1.25–1.48), followed by altered mental status 1.23 (95% CI, 1.14–1.32), heart rate 1.21 (95% CI, 1.09–1.34), systolic blood pressure 1.12 (95% CI, 1.04–1.22), and respiratory rate 1.03 (95% CI, 1.05–1.26). Body temperature and oxygen supplementation were not significantly associated. Classification and regression trees showed oxygen saturation as the most heavily weighted parameter, followed by altered mental status and respiratory rate.

Conclusions

National Early Warning Score could stratify 30‐day mortality risk following RRS activation in Japanese patients.