scholarly journals Utilization of Deep Learning for Subphenotype Identification in Sepsis-Associated Acute Kidney Injury

2020 ◽  
Vol 15 (11) ◽  
pp. 1557-1565 ◽  
Author(s):  
Kumardeep Chaudhary ◽  
Akhil Vaid ◽  
Áine Duffy ◽  
Ishan Paranjpe ◽  
Suraj Jaladanki ◽  
...  
Keyword(s):  
Intensive Care ◽  
Deep Learning ◽  
Medical Information ◽  
Tertiary Care ◽  
Vital Signs ◽  
Kidney Injury ◽  
The United States ◽  
Care Hospital ◽  
Electronic Health Record Data ◽  
Electronic Health

Background and objectivesSepsis-associated AKI is a heterogeneous clinical entity. We aimed to agnostically identify sepsis-associated AKI subphenotypes using deep learning on routinely collected data in electronic health records.Design, setting, participants, & measurementsWe used the Medical Information Mart for Intensive Care III database, which consists of electronic health record data from intensive care units in a tertiary care hospital in the United States. We included patients ≥18 years with sepsis who developed AKI within 48 hours of intensive care unit admission. We then used deep learning to utilize all available vital signs, laboratory measurements, and comorbidities to identify subphenotypes. Outcomes were mortality 28 days after AKI and dialysis requirement.ResultsWe identified 4001 patients with sepsis-associated AKI. We utilized 2546 combined features for K-means clustering, identifying three subphenotypes. Subphenotype 1 had 1443 patients, and subphenotype 2 had 1898 patients, whereas subphenotype 3 had 660 patients. Subphenotype 1 had the lowest proportion of liver disease and lowest Simplified Acute Physiology Score II scores compared with subphenotypes 2 and 3. The proportions of patients with CKD were similar between subphenotypes 1 and 3 (15%) but highest in subphenotype 2 (21%). Subphenotype 1 had lower median bilirubin levels, aspartate aminotransferase, and alanine aminotransferase compared with subphenotypes 2 and 3. Patients in subphenotype 1 also had lower median lactate, lactate dehydrogenase, and white blood cell count than patients in subphenotypes 2 and 3. Subphenotype 1 also had lower creatinine and BUN than subphenotypes 2 and 3. Dialysis requirement was lowest in subphenotype 1 (4% versus 7% [subphenotype 2] versus 26% [subphenotype 3]). The mortality 28 days after AKI was lowest in subphenotype 1 (23% versus 35% [subphenotype 2] versus 49% [subphenotype 3]). After adjustment, the adjusted odds ratio for mortality for subphenotype 3, with subphenotype 1 as a reference, was 1.9 (95% confidence interval, 1.5 to 2.4).ConclusionsUtilizing routinely collected laboratory variables, vital signs, and comorbidities, we were able to identify three distinct subphenotypes of sepsis-associated AKI with differing outcomes.

scholarly journals Safety huddles to proactively identify and address electronic health record safety

2016 ◽  
Vol 24 (2) ◽  
pp. 261-267 ◽  
Author(s):  
Shailaja Menon ◽  
Hardeep Singh ◽  
Traber D Giardina ◽  
William L Rayburn ◽  
Brenda P Davis ◽  
...  
Keyword(s):  
Situational Awareness ◽  
Tertiary Care ◽  
The United States ◽  
Care Hospital ◽  
Design Data ◽  
Software Application ◽  
Safety Concerns ◽  
Hardware System ◽  
Error Taxonomy ◽  
Electronic Health

Objective: Methods to identify and study safety risks of electronic health records (EHRs) are underdeveloped and largely depend on limited end-user reports. “Safety huddles” have been found useful in creating a sense of collective situational awareness that increases an organization’s capacity to respond to safety concerns. We explored the use of safety huddles for identifying and learning about EHR-related safety concerns. Design: Data were obtained from daily safety huddle briefing notes recorded at a single midsized tertiary-care hospital in the United States over 1 year. Huddles were attended by key administrative, clinical, and information technology staff. We conducted a content analysis of huddle notes to identify what EHR-related safety concerns were discussed. We expanded a previously developed EHR-related error taxonomy to categorize types of EHR-related safety concerns recorded in the notes. Results: On review of daily huddle notes spanning 249 days, we identified 245 EHR-related safety concerns. For our analysis, we defined EHR technology to include a specific EHR functionality, an entire clinical software application, or the hardware system. Most concerns (41.6%) involved “EHR technology working incorrectly,” followed by 25.7% involving “EHR technology not working at all.” Concerns related to “EHR technology missing or absent” accounted for 16.7%, whereas 15.9% were linked to “user errors.” Conclusions: Safety huddles promoted discussion of several technology-related issues at the organization level and can serve as a promising technique to identify and address EHR-related safety concerns. Based on our findings, we recommend that health care organizations consider huddles as a strategy to promote understanding and improvement of EHR safety.

scholarly journals Evaluation of Aetiology and Outcome of Acute Kidney Injury in a Tertiary Care Hospital of India- A Prospective Observational Study

2020 ◽  
Author(s):  
VS Gaurav Narayan ◽  
SG Ramya ◽  
Sonal Rajesh Kumar ◽  
SK Nellaiappa Ganesan
Keyword(s):  
Acute Kidney Injury ◽  
Intensive Care ◽  
Observational Study ◽  
Prospective Observational Study ◽  
Tertiary Care ◽  
Kidney Injury ◽  
Rapid Decline ◽  
Care Hospital ◽  
Medical Intensive Care

Introduction: The Acute Kidney Injury (AKI) is a rapid decline in renal filtration function. The aetiological spectrum, prevalence of AKI and outcome is highly variable. This variation exists due to the difference in the criteria used, study population and demographic features. Huge differences are noted when AKI is compared in developing and developed countries. Hence, it is important to analyse the spectrum of AKI to facilitate earlier diagnosis and treatment which shall help in improving the outcome. Aim: To study the prevalence, aetiology and outcome of AKI in the medical intensive care. Materials and Methods: This was a prospective observational study conducted in a medical intensive care for 18 months where 1490 patients were screened and 403 patients were included as AKI by KDIGO criteria. History, examination, appropriate investigations and treatment details including dialysis were noted. The serum creatinine levels were obtained every day, to know the time of onset of AKI, at the time of death or discharge, and after one month for patients who turned up for follow-up. Patients were categorised based on outcome as survivors and nonsurvivors. Survivors were divided into as fully recovered and partially recovered and those who left the Intensive Care Unit (ICU) against medical advice were termed as lost to follow-up. Results: A total of 403 patients (27.04% of 1490) of medical intensive care admissions were found to have AKI. Sepsis was the most common cause of AKI. At the end of the month, 78.4% of AKI patients fully recovered, 1.2% partially recovered and the mortality was 14.9%. Mortality was higher in AKI associated with chronic medical conditions like cardiac failure, chronic liver disease and stroke. Conclusion: If treated early, AKI is mostly reversible. Regional differences in AKI should be studied extensively and local guidelines should be formulated by experts for prevention and early treatment, to improve the disease outcome.

scholarly journals Predicting mortality among patients with liver cirrhosis in electronic health records with machine learning

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256428
Author(s):  
Aixia Guo ◽  
Nikhilesh R. Mazumder ◽  
Daniela P. Ladner ◽  
Randi E. Foraker
Keyword(s):  
Machine Learning ◽  
Liver Cirrhosis ◽  
Deep Learning ◽  
Risk Prediction ◽  
The United States ◽  
Meld Score ◽  
Receiver Operating Curve ◽  
Categorical Variables ◽  
Electronic Health Record Data ◽  
Electronic Health

Objective Liver cirrhosis is a leading cause of death and effects millions of people in the United States. Early mortality prediction among patients with cirrhosis might give healthcare providers more opportunity to effectively treat the condition. We hypothesized that laboratory test results and other related diagnoses would be associated with mortality in this population. Our another assumption was that a deep learning model could outperform the current Model for End Stage Liver disease (MELD) score in predicting mortality. Materials and methods We utilized electronic health record data from 34,575 patients with a diagnosis of cirrhosis from a large medical center to study associations with mortality. Three time-windows of mortality (365 days, 180 days and 90 days) and two cases with different number of variables (all 41 available variables and 4 variables in MELD-NA) were studied. Missing values were imputed using multiple imputation for continuous variables and mode for categorical variables. Deep learning and machine learning algorithms, i.e., deep neural networks (DNN), random forest (RF) and logistic regression (LR) were employed to study the associations between baseline features such as laboratory measurements and diagnoses for each time window by 5-fold cross validation method. Metrics such as area under the receiver operating curve (AUC), overall accuracy, sensitivity, and specificity were used to evaluate models. Results Performance of models comprising all variables outperformed those with 4 MELD-NA variables for all prediction cases and the DNN model outperformed the LR and RF models. For example, the DNN model achieved an AUC of 0.88, 0.86, and 0.85 for 90, 180, and 365-day mortality respectively as compared to the MELD score, which resulted in corresponding AUCs of 0.81, 0.79, and 0.76 for the same instances. The DNN and LR models had a significantly better f1 score compared to MELD at all time points examined. Conclusion Other variables such as alkaline phosphatase, alanine aminotransferase, and hemoglobin were also top informative features besides the 4 MELD-Na variables. Machine learning and deep learning models outperformed the current standard of risk prediction among patients with cirrhosis. Advanced informatics techniques showed promise for risk prediction in patients with cirrhosis.

scholarly journals Etiology & Outcome of Acute kidney Injury in Intensive Care Unit Settings of a Tertiary Care Hospital

2020 ◽  
Vol 4 (2) ◽  
pp. 01-05
Author(s):  
Hassan Mumtaz
Keyword(s):  
Intensive Care Unit ◽  
Acute Kidney Injury ◽  
Risk Factor ◽  
Intensive Care ◽  
Tertiary Care ◽  
Hospital Setting ◽  
Kidney Injury ◽  
Morbidity And Mortality ◽  
High Morbidity ◽  
Care Hospital

Introduction: Acute kidney injury (AKI) is defined as a rapid loss of kidney function occurring over few hours or days. In intensive care unit settings, acute kidney injury (AKI) is a very prevalent condition as most of the patients who are admitted in intensive care units are critically ill. The incidence of acute kidney injury is increasing throughout the world mainly because of aging population and co morbidities which are associated with aging. In intensive care unit settings, the incidence of AKI may reach up to 67%. Though AKI effects depend on clinical situation yet associated with high morbidity and mortality. The rationale of this study is that, as acute kidney is one of major factors contributing in mortality and morbidity of ICU patients, this study will be helpful in identifying important risk factor for development of acute kidney injury in ICU settings, leading to its early detection and thus decreasing associated morbidity and mortality. Objective: To determine the frequency of etiology and outcome of acute kidney injury in medical intensive care unit of KRL Hospital. Setting: Medical ICU, KRL Hospital, Islamabad. Duration: six months from 17th May 2017 to 17th November 2017. Study design: Descriptive case series. Material and method: In this study 118 patients were observed. After screening and application of exclusion criteria, a total of 118 patients who were fulfilling the inclusion criteria were selected as the study sample and were included in the final analysis regarding prevalence of risk factors associated with AKI and the outcome associated with AKI. AKI was further classified using acute kidney injury network (AKIN) classification system. Patient age, gender, serum creatinine, etiology and outcome in form of recovery or mortality was recorded. Results: Overall incidence of AKI in ICU settings in this study was 37.8% (n=118). Out of 118 patients who had AKI, 59.3% (n=70) were male, whereas 40.7% (n=48) were females. Most common risk factor associated with development of AKI was sepsis secondary to infectious illnesses and 39% (n=46) of the patients who developed AKI were suffering from infectious illnesses. Gastrointestinal, drugs and cardiac causes constitutes the 32.2 % (n=38), 18.6% (n=22) and 10.2% (n=12) respectively of the AKI in ICU settings. In terms of outcome, mortality rate in patients with AKI was significantly higher as compared to patients without AKI(P =<0.001) and 56.8%(n=67) of the patients who had AKI died during their ICU stay as compared to 30.4%(n=59) in patients without AKI. Conclusion: Our study concludes that the frequency of etiology including infectious causes was 39%, cardiac pathology 10%, GI causes 32%, drugs was 19% and mortality was 56.8% in patients with acute kidney injury.

scholarly journals Unsupervised Machine learning to subtype Sepsis-Associated Acute Kidney Injury

2018 ◽  
Author(s):  
Kumardeep Chaudhary ◽  
Aine Duffy ◽  
Priti Poojary ◽  
Aparna Saha ◽  
Kinsuk Chauhan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Tertiary Care ◽  
Vital Signs ◽  
Kidney Injury ◽  
Machine Learning Techniques ◽  
Care Hospital ◽  
Unsupervised Machine Learning ◽  
Laboratory Variables ◽  
Cluster 2

AbstractObjectiveAcute kidney injury (AKI) is highly prevalent in critically ill patients with sepsis. Sepsis-associated AKI is a heterogeneous clinical entity, and, like many complex syndromes, is composed of distinct subtypes. We aimed to agnostically identify AKI subphenotypes using machine learning techniques and routinely collected data in electronic health records (EHRs).DesignCohort study utilizing the MIMIC-III Database.SettingICUs from tertiary care hospital in the U.S.PatientsPatients older than 18 years with sepsis and who developed AKI within 48 hours of ICU admission.InterventionsUnsupervised machine learning utilizing all available vital signs and laboratory measurements.Measurements and Main ResultsWe identified 1,865 patients with sepsis-associated AKI. Ten vital signs and 691 unique laboratory results were identified. After data processing and feature selection, 59 features, of which 28 were measures of intra-patient variability, remained for inclusion into an unsupervised machine-learning algorithm. We utilized k-means clustering with k ranging from 2 – 10; k=2 had the highest silhouette score (0.62). Cluster 1 had 1,358 patients while Cluster 2 had 507 patients. There were no significant differences between clusters on age, race or gender. We found significant differences in comorbidities and small but significant differences in several laboratory variables (hematocrit, bicarbonate, albumin) and vital signs (systolic blood pressure and heart rate). In-hospital mortality was higher in cluster 2 patients, 25% vs. 20%, p=0.008. Features with the largest differences between clusters included variability in basophil and eosinophil counts, alanine aminotransferase levels and creatine kinase values.ConclusionsUtilizing routinely collected laboratory variables and vital signs in the EHR, we were able to identify two distinct subphenotypes of sepsis-associated AKI with different outcomes. Variability in laboratory variables, as opposed to their actual value, was more important for determination of subphenotypes. Our findings show the potential utility of unsupervised machine learning to better subtype AKI.

scholarly journals Hyperchloremia in critically ill patients: association with outcomes and prediction using electronic health record data

2020 ◽  
Vol 20 (S14) ◽  
Author(s):  
Pete Yeh ◽  
Yiheng Pan ◽  
L. Nelson Sanchez-Pinto ◽  
Yuan Luo
Keyword(s):  
Intensive Care ◽  
Supervised Learning ◽  
Medical Information ◽  
Kidney Injury ◽  
Learning Model ◽  
Multiple Organ ◽  
Icu Mortality ◽  
Electronic Health Record Data ◽  
Icu Patients ◽  
Clinical Records

Abstract Background Increased chloride in the context of intravenous fluid chloride load and serum chloride levels (hyperchloremia) have previously been associated with increased morbidity and mortality in select subpopulations of intensive care unit (ICU) patients (e.g patients with sepsis). Here, we study the general ICU population of the Medical Information Mart for Intensive Care III (MIMIC-III) database to corroborate these associations, and propose a supervised learning model for the prediction of hyperchloremia in ICU patients. Methods We assessed hyperchloremia and chloride load and their associations with several outcomes (ICU mortality, new acute kidney injury [AKI] by day 7, and multiple organ dysfunction syndrome [MODS] on day 7) using regression analysis. Four predictive supervised learning classifiers were trained to predict hyperchloremia using features representative of clinical records from the first 24h of adult ICU stays. Results Hyperchloremia was shown to have an independent association with increased odds of ICU mortality, new AKI by day 7, and MODS on day 7. High chloride load was also associated with increased odds of ICU mortality. Our best performing supervised learning model predicted second-day hyperchloremia with an AUC of 0.76 and a number needed to alert (NNA) of 7—a clinically-actionable rate. Conclusions Our results support the use of predictive models to aid clinicians in monitoring for and preventing hyperchloremia in high-risk patients and offers an opportunity to improve patient outcomes.

Sign in / Sign up

Export Citation Format

Share Document