Performance of a machine-learning algorithm to predict hypotension in mechanically ventilated patients with COVID-19 admitted to the intensive care unit: a cohort study

AbstractThe Hypotension Prediction Index (HPI) is a commercially available machine-learning algorithm that provides warnings for impending hypotension, based on real-time arterial waveform analysis. The HPI was developed with arterial waveform data of surgical and intensive care unit (ICU) patients, but has never been externally validated in the latter group. In this study, we evaluated diagnostic ability of the HPI with invasively collected arterial blood pressure data in 41 patients with COVID-19 admitted to the ICU for mechanical ventilation. Predictive ability was evaluated at HPI thresholds from 0 to 100, at incremental intervals of 5. After exceeding the studied threshold, the next 20 min were screened for positive (mean arterial pressure (MAP) < 65 mmHg for at least 1 min) or negative (absence of MAP < 65 mmHg for at least 1 min) events. Subsequently, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and time to event were determined for every threshold. Almost all patients (93%) experienced at least one hypotensive event. Median number of events was 21 [7–54] and time spent in hypotension was 114 min [20–303]. The optimal threshold was 90, with a sensitivity of 0.91 (95% confidence interval 0.81–0.98), specificity of 0.87 (0.81–0.92), PPV of 0.69 (0.61–0.77), NPV of 0.99 (0.97–1.00), and median time to event of 3.93 min (3.72–4.15). Discrimination ability of the HPI was excellent, with an area under the curve of 0.95 (0.93–0.97). This validation study shows that the HPI correctly predicts hypotension in mechanically ventilated COVID-19 patients in the ICU, and provides a basis for future studies to assess whether hypotension can be reduced in ICU patients using this algorithm.

Download Full-text

Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Comparative Machine Learning Study (Preprint)

10.2196/preprints.23508 ◽

2020 ◽

Author(s):

Sujeong Hur ◽

Ji Young Min ◽

Junsang Yoo ◽

Kyunga Kim ◽

Chi Ryang Chung ◽

...

Keyword(s):

Machine Learning ◽

Intensive Care Unit ◽

Patient Safety ◽

Intensive Care ◽

Predictive Value ◽

Prediction Models ◽

Support Vector ◽

Unplanned Extubation ◽

Electronic Health Record Data ◽

Icu Patients

BACKGROUND Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered as the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care. OBJECTIVE This study aimed to develop and validate prediction models for UE in ICU patients using machine learning. METHODS This study was conducted an academic tertiary hospital in Seoul. The hospital had approximately 2,000 inpatient beds and 120 intensive care unit (ICU) beds. The number of patients, on daily basis, was approximately 9,000 for the out-patient. The number of annual ICU admission was approximately 10,000. We conducted a retrospective study between January 1, 2010 and December 31, 2018. A total of 6,914 extubation cases were included. We developed an unplanned extubation prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model’s performance, we used area under the receiver operator characteristic curve (AUROC). Sensitivity, specificity, positive predictive value negative predictive value, and F1-score were also determined for each model. For performance evaluation, we also used calibration curve, the Brier score, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS Among the 6,914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was more likely to occur during the night shift compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality was higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.762, and for SVM was 0.740. CONCLUSIONS We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787, which was obtained using RF. CLINICALTRIAL N/A

Download Full-text

Man vs. Machine: Comparison of a Machine Learning Algorithm to Clinician Intuition for Predicting Intensive Care Unit Readmission

10.1164/ajrccm-conference.2019.199.1_meetingabstracts.a2459 ◽

2019 ◽

Author(s):

J.C. Rojas ◽

P.G. Lyons ◽

M. Kilaru ◽

K.A. Carey ◽

L.R. Venable ◽

...

Keyword(s):

Machine Learning ◽

Intensive Care Unit ◽

Intensive Care ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Intensive Care Unit Readmission

Download Full-text

Association of opioid exposure during intensive care unit stays with post-discharge opioid use: A retrospective study and literature review

Journal of Opioid Management ◽

10.5055/jom.2021.0685 ◽

2021 ◽

Vol 17 (6) ◽

pp. 511-516

Author(s):

Yoonsun Mo, MS, PharmD, BCPS, BCCCP ◽

John Zeibeq, MD ◽

Nabil Mesiha, MD ◽

Abou Bakar, PharmD ◽

Maram Sarsour, PharmD ◽

...

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Retrospective Study ◽

Hospital Discharge ◽

Invasive Mechanical Ventilation ◽

High Dose ◽

Opioid Use ◽

Electronic Health Record Data ◽

Icu Patients ◽

Mechanically Ventilated

Objective: To evaluate whether pain management strategies within intensive care unit (ICU) settings contribute to chronic opioid use upon hospital discharge in opioid-naive patients requiring invasive mechanical ventilation. Design: A retrospective, observational study.Setting: An 18-bed mixed ICU at a community teaching hospital located in Brooklyn, New York.Participants: This study included mechanically ventilated patients requiring continuous opioid infusion from April 25, 2017 to May 16, 2019. Patients were excluded if they received chronic opioid therapy at home or expired during this hospital admission. Eligible patients were identified using an electronic health record data query.Main outcome measure(s): The proportion of ICU patients who continued to require opioids upon ICU and hospital discharge. Results: A total of 196 ICU patients were included in this study. Of these, 22 patients were transferred to a regular floor while receiving a fentanyl transdermal patch. However, the fentanyl patch treatment was continued only for three patients (2 percent) at hospital discharge.Conclusions: This retrospective study suggested that high-dose use of opioids in mechanically ventilated, opioid-naive ICU patients was not associated with continued opioid use upon hospital discharge.

Download Full-text

Wearable Sensors Incorporating Compensatory Reserve Measurement for Advancing Physiological Monitoring in Critically Injured Trauma Patients

Sensors ◽

10.3390/s20226413 ◽

2020 ◽

Vol 20 (22) ◽

pp. 6413

Author(s):

Victor A. Convertino ◽

Steven G. Schauer ◽

Erik K. Weitzel ◽

Sylvain Cardin ◽

Mark E. Stackle ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Wearable Sensors ◽

Clinical Status ◽

Vital Signs ◽

Human Model ◽

Machine Learning Algorithm ◽

Medical Monitoring ◽

Arterial Waveform ◽

Compensatory Reserve

Vital signs historically served as the primary method to triage patients and resources for trauma and emergency care, but have failed to provide clinically-meaningful predictive information about patient clinical status. In this review, a framework is presented that focuses on potential wearable sensor technologies that can harness necessary electronic physiological signal integration with a current state-of-the-art predictive machine-learning algorithm that provides early clinical assessment of hypovolemia status to impact patient outcome. The ability to study the physiology of hemorrhage using a human model of progressive central hypovolemia led to the development of a novel machine-learning algorithm known as the compensatory reserve measurement (CRM). Greater sensitivity, specificity, and diagnostic accuracy to detect hemorrhage and onset of decompensated shock has been demonstrated by the CRM when compared to all standard vital signs and hemodynamic variables. The development of CRM revealed that continuous measurements of changes in arterial waveform features represented the most integrated signal of physiological compensation for conditions of reduced systemic oxygen delivery. In this review, detailed analysis of sensor technologies that include photoplethysmography, tonometry, ultrasound-based blood pressure, and cardiogenic vibration are identified as potential candidates for harnessing arterial waveform analog features required for real-time calculation of CRM. The integration of wearable sensors with the CRM algorithm provides a potentially powerful medical monitoring advancement to save civilian and military lives in emergency medical settings.

Download Full-text

A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study (Preprint)

10.2196/preprints.22400 ◽

2020 ◽

Author(s):

Angier Allen ◽

Samson Mataraso ◽

Anna Siefkas ◽

Hoyt Burdick ◽

Gregory Braden ◽

...

Keyword(s):

Machine Learning ◽

Health Care ◽

Intensive Care ◽

Racial Disparities ◽

Equal Opportunity ◽

Racial Bias ◽

Learning Algorithm ◽

Early Warning Score ◽

Machine Learning Algorithm ◽

Saps Ii

BACKGROUND Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. OBJECTIVE The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. METHODS Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). RESULTS The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P<.001, respectively). CONCLUSIONS This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

Download Full-text

Detection of Aspergillus fumigatus in Blood Samples from Critically Ill Patients in Intensive Care Units by Use of the SeptiFast Assay: TABLE 1

Journal of Clinical Microbiology ◽

10.1128/jcm.00478-16 ◽

2016 ◽

Vol 54 (7) ◽

pp. 1918-1921 ◽

Cited By ~ 11

Author(s):

Joerg Steinmann ◽

Jan Buer ◽

Peter-Michael Rath

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Positive Predictive Value ◽

Aspergillus Fumigatus ◽

Critically Ill ◽

Predictive Value ◽

Icu Patients ◽

Blood Samples ◽

Content Type ◽

Whole Blood Samples

We retrospectively analyzed the performance and relevance of the SeptiFast assay in detectingAspergillus fumigatusDNA in whole blood samples from 38 critically ill intensive care unit (ICU) patients with probable or proven invasive aspergillosis (IA) and 100 ICU patients without IA. The assay exhibited 66% sensitivity, 98% specificity, a 93% positive predictive value, and an 88% negative predictive value.A. fumigatusDNAemia was associated with poor outcome.

Download Full-text

THE VALUE OF ROUTINE CHEST X-RAY (CXR) IN MECHANICALLY VENTILATED INTENSIVE CARE UNIT (ICU) PATIENTS

CHEST Journal ◽

10.1378/chest.128.4_meetingabstracts.208s ◽

2005 ◽

Vol 128 (4) ◽

pp. 208S

Author(s):

Marleen E. Graat ◽

Esther K. Wolthuis ◽

Goda Choi ◽

Johanna C. Korevaar ◽

Marcus J. Schultz

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Icu Patients ◽

Mechanically Ventilated ◽

X Ray ◽

Chest X Ray ◽

Routine Chest

Download Full-text

Evaluating a sepsis prediction machine learning algorithm in the emergency department and intensive care unit: a before and after comparative study

10.1101/224014 ◽

2017 ◽

Cited By ~ 3

Author(s):

Hoyt Burdick ◽

Eduardo Pino ◽

Denise Gabel-Comeau ◽

Carol Gu ◽

Heidi Huang ◽

...

Keyword(s):

Machine Learning ◽

Emergency Department ◽

Intensive Care ◽

Length Of Stay ◽

Learning Algorithm ◽

Detection System ◽

Machine Learning Algorithm ◽

Implementation Phase ◽

Before And After ◽

Sepsis Detection

AbstractIntroductionSepsis is a major health crisis in US hospitals, and several clinical identification systems have been designed to help care providers with early diagnosis of sepsis. However, many of these systems demonstrate low specificity or sensitivity, which limits their clinical utility. We evaluate the effects of a machine learning algodiagnostic (MLA) sepsis prediction and detection system using a before-and-after clinical study performed at Cabell Huntington Hospital (CHH) in Huntington, West Virginia. Prior to this study, CHH utilized the St. John’s Sepsis Agent (SJSA) as a rules-based sepsis detection system.MethodsThe Predictive algoRithm for EValuation and Intervention in SEpsis (PREVISE) study was carried out between July 1, 2017 and August 30, 2017. All patients over the age of 18 who were admitted to the emergency department or intensive care units at CHH were monitored during the study. We assessed pre-implementation baseline metrics during the month of July, 2017, when the SJSA was active. During implementation in the month of August, 2017, SJSA and the MLA concurrently monitored patients for sepsis risk. At the conclusion of the study period, the primary outcome of sepsis-related in-hospital mortality and secondary outcome of sepsis-related hospital length of stay were compared between the two groups.ResultsSepsis-related in-hospital mortality decreased from 3.97% to 2.64%, a 33.5% relative decrease (P = 0.038), and sepsis-related length of stay decreased from 2.99 days in the pre-implementation phase to 2.48 days in the post-implementation phase, a 17.1% relative reduction (P < 0.001).ConclusionReductions in patient mortality and length-of-stay were observed with use of a machine learning algorithm for early sepsis detection in the emergency department and intensive care units at Cabell Huntington Hospital, and may present a method for improving patient outcomes.Trial RegistrationClinicalTrials.gov, NCT03235193, retrospectively registered on July 27th 2017.

Download Full-text

A Racially Unbiased, Machine Learning Approach to Prediction of Mortality: Algorithm Development Study

JMIR Public Health and Surveillance ◽

10.2196/22400 ◽

2020 ◽

Vol 6 (4) ◽

pp. e22400

Author(s):

Angier Allen ◽

Samson Mataraso ◽

Anna Siefkas ◽

Hoyt Burdick ◽

Gregory Braden ◽

...

Keyword(s):

Machine Learning ◽

Health Care ◽

Intensive Care ◽

Racial Disparities ◽

Equal Opportunity ◽

Racial Bias ◽

Learning Algorithm ◽

Early Warning Score ◽

Machine Learning Algorithm ◽

Saps Ii

Background Racial disparities in health care are well documented in the United States. As machine learning methods become more common in health care settings, it is important to ensure that these methods do not contribute to racial disparities through biased predictions or differential accuracy across racial groups. Objective The goal of the research was to assess a machine learning algorithm intentionally developed to minimize bias in in-hospital mortality predictions between white and nonwhite patient groups. Methods Bias was minimized through preprocessing of algorithm training data. We performed a retrospective analysis of electronic health record data from patients admitted to the intensive care unit (ICU) at a large academic health center between 2001 and 2012, drawing data from the Medical Information Mart for Intensive Care–III database. Patients were included if they had at least 10 hours of available measurements after ICU admission, had at least one of every measurement used for model prediction, and had recorded race/ethnicity data. Bias was assessed through the equal opportunity difference. Model performance in terms of bias and accuracy was compared with the Modified Early Warning Score (MEWS), the Simplified Acute Physiology Score II (SAPS II), and the Acute Physiologic Assessment and Chronic Health Evaluation (APACHE). Results The machine learning algorithm was found to be more accurate than all comparators, with a higher sensitivity, specificity, and area under the receiver operating characteristic. The machine learning algorithm was found to be unbiased (equal opportunity difference 0.016, P=.20). APACHE was also found to be unbiased (equal opportunity difference 0.019, P=.11), while SAPS II and MEWS were found to have significant bias (equal opportunity difference 0.038, P=.006 and equal opportunity difference 0.074, P<.001, respectively). Conclusions This study indicates there may be significant racial bias in commonly used severity scoring systems and that machine learning algorithms may reduce bias while improving on the accuracy of these methods.

Download Full-text

Renal dysfunction decreases specificity and overturns cutoff value of serum CC16 while prohibiting 7-day mortality prediction in diagnosing acute respiratory distress syndrome in intensive care unit.

10.21203/rs.2.20735/v1 ◽

2020 ◽

Author(s):

Jinle Lin ◽

Wuyuan Tao ◽

Jian Wei ◽

Wu Jian ◽

Wenwu Zhang ◽

...

Keyword(s):

Intensive Care Unit ◽

Acute Respiratory Distress Syndrome ◽

Intensive Care ◽

Respiratory Distress Syndrome ◽

Respiratory Distress ◽

Renal Dysfunction ◽

Predictive Value ◽

Distress Syndrome ◽

Icu Patients ◽

Cutoff Value

Abstract Background: A contradictory tendency between occurrence of acute respiratory distress syndrome (ARDS) and serum club cell protein 16 (CC16) level, However, renal dysfunction (RD) separately raised serum CC16 in our current observation. The purpose of this study was to find the limitation caused by renal dysfunction in the diagnostic performance of CC16 on ARDS in intensive care unit (ICU) patients. Method: We measured serum CC16 in 479 ICU patients. Patients were divided into six subgroups: control, acute kidney injury (AKI), chronic kidney dysfunction (CKD), ARDS, ARDS+AKI, and ARDS+CKD. The cutoff value, sensitivity and specificity of serum CC16 were assessed by receiver operating characteristic curves. Result: Serum CC16 increased among the ARDS group when compared to the control group, which helps identify ARDS and predicts the outcome in patients with normal renal function. However, level of serum CC16 was similar among ARDS+AKI, ARDS+CKD, AIK and CKD groups. Consequently, when compare to AKI and CKD, specificity for diagnosing whether ARDS or ARDS with renal failure decreased from 86.62% to 2.82% or 81.70% to 2.12%. Consistently, a cutoff value of 11.57 ng/mL was overturned from previously at 32.77 ng/mL or 33.72 ng/mL. Moreover, its predictive value for mortality is prohibited before 7 day but works after 28 day. Conclusion: Renal dysfunction limits the specificity, cutoff point, and predictive value at 7-day mortality of CC16 in diagnosing ARDS among ICU patients.

Download Full-text