scholarly journals Expected and observed in‐hospital mortality in heart failure patients before and during the COVID‐19 pandemic: Introduction of the machine learning‐based standardized mortality ratio at Helios hospitals

2021 ◽  
Author(s):  
Sebastian König ◽  
Vincent Pellissier ◽  
Johannes Leiner ◽  
Sven Hohenstein ◽  
Laura Ueberham ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Hospital Mortality ◽  
Standardized Mortality Ratio ◽  
Heart Failure Patients ◽  
Mortality Ratio

scholarly journals Hospital Standardized Mortality Ratio: Consequences of Adjusting Hospital Mortality with Indirect Standardization

PLoS ONE ◽  
2013 ◽  
Vol 8 (4) ◽  
pp. e59160 ◽  
Author(s):  
Maurice E. Pouw ◽  
Linda M. Peelen ◽  
Hester F. Lingsma ◽  
Daniel Pieter ◽  
Ewout Steyerberg ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Standardized Mortality Ratio ◽  
Mortality Ratio ◽  
Indirect Standardization

Trends in hospitalization and in-hospital mortality of patients with heart failure in Spain. A population-based study (2003–2015)

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
J.L Bonilla Palomas ◽  
M.P Anguita-Sanchez ◽  
F.J Elola ◽  
J.L Bernal ◽  
C Fernandez-Perez ◽  
...  
Keyword(s):  
Heart Failure ◽  
Mortality Rate ◽  
Hospital Mortality ◽  
National Health System ◽  
Admission Rate ◽  
Population Data ◽  
Principal Diagnosis ◽  
Data Set ◽  
Discharge Rates ◽  
Mortality Ratio

Abstract Background Heart failure (HF) is one of the most pressing current public health concerns. However, in Spain there is a lack of population data. Purpose To investigate trends in HF hospitalization and in-hospital mortality rates. Methods We conducted a retrospective observational study of patients discharged with the principal diagnosis of HF from The National Health System' acute hospitals during 2003–2015. The source of the data was the Minimum Basic Data Set of the Ministry of Health, Consumer and Social Welfare. We analyzed trends in hospital discharge rates for HF (discharge rates were weighted by age and gender) an in-hospital mortality. The risk-standardized in-hospital mortality ratio (RSMR) was defined as the ratio between predicted mortality (which individually considers the performance of the hospital where the patient is attended) and expected mortality (which considers a standard performance according to the average of all hospitals) multiplied by the crude rate of mortality. RSMR was calculated using a risk adjustment multilevel logistic regression models developed by the Medicare and Medicaid Services. Temporal trend during the observed period was modelled using Poisson regression analysis with year as the only independent variable. In this model, the incidence rate ratio (IRR) and their 95% confidence intervals (95% CI) was calculated. Results A total of 1 254 830 episodes of HF were selected. Throughout 2003–2015 the number of hospital discharges with principal diagnosis of HF increased by 61% (IRR: 1.04; CI: 1.03–1.04; p<0.001), meanwhile the crude mortality rate and the mean length of stay (LOS) diminished significantly (IRR: 0.99; CI: 0.98–1; and IRR: 1.04; CI: 0.99–0.99; p<0.001, for both). Discharge rates weighted by age and sex showed a statistically significant increase during the period (IRR: 1.03; CI: 1.03–1.03; p<0.001); however, whereas discharge rates increased significantly in older groups of age (≥75 years old) (IRR: 1–1.02; p<0.001) they diminished in younger groups of age (45–74 years old) (IRR: 0.99; p<0.001 and there was not a significant trend in the discharge rates for the group of 35–44 years old (Figure). The risk-standardized in-hospital mortality ratio did not significantly change throughout 2003–2015 (IRR: 0.997; CI: 0.992–1; p=0.32), however the risk-standardized LOS ratio diminished from 1.07 in 2003 to 0.97 in 2015 (IRR: 0.98: IC: 0.98–0.99; p<0.001). Conclusions From 2003 to 2015, HF admission rate increased significantly in Spain as a consequence of the sustained increase of hospitalization in the population over 75. The crude in-hospital mortality rate diminished significantly for the same period, but the risk-standardized in-hospital mortality ratio did not significantly change. Figure 1 Funding Acknowledgement Type of funding source: None

Abstract 17060: Machine Learning and Video Recognition for Automated Detection of Fluid Status in Heart Failure Patients

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Pratik Doshi ◽  
John Tanaka ◽  
Jedrek Wosik ◽  
Natalia M Gil ◽  
Martin Bertran ◽  
...  
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Point Of Care ◽  
Machine Learning Algorithms ◽  
Right Atrial ◽  
Heart Catheterization ◽  
Heart Failure Patients ◽  
Non Invasive ◽  
Fluid Status ◽  
Video Recognition

Introduction: There is a need for innovative solutions to better screen and diagnose the 7 million patients with chronic heart failure. A key component of assessing these patients is monitoring fluid status by evaluating for the presence and height of jugular venous distension (JVD). We hypothesize that video analysis of a patient’s neck using machine learning algorithms and image recognition can identify the amount of JVD. We propose the use of high fidelity video recordings taken using a mobile device camera to determine the presence or absence of JVD, which we will use to develop a point of care testing tool for early detection of acute exacerbation of heart failure. Methods: In this feasibility study, patients in the Duke cardiac catheterization lab undergoing right heart catheterization were enrolled. RGB and infrared videos were captured of the patient’s neck to detect JVD and correlated with right atrial pressure on the heart catheterization. We designed an adaptive filter based on biological priors that enhances spatially consistent frequency anomalies and detects jugular vein distention, with implementation done on Python. Results: We captured and analyzed footage for six patients using our model. Four of these six patients shared a similar strong signal outliner within the frequency band of 95bpm – 200bpm when using a conservative threshold, indicating the presence of JVD. We did not use statistical analysis given the small nature of our cohort, but in those we detected a positive JVD signal the RA mean was 20.25 mmHg and PCWP mean was 24.3 mmHg. Conclusions: We have demonstrated the ability to evaluate for JVD via infrared video and found a relationship with RHC values. Our project is innovative because it uses video recognition and allows for novel patient interactions using a non-invasive screening technique for heart failure. This tool can become a non-invasive standard to both screen for and help manage heart failure patients.

scholarly journals P4381Predictors of in-hospital mortality among hospitalised adult heart failure patients in the Philippines

2017 ◽  
Vol 38 (suppl_1) ◽  
Author(s):  
R.B. Natividad ◽  
B.A. Tumanan-Mendoza ◽  
F.E.R. Punzalan ◽  
N.S. Pestano ◽  
V.L. Mendoza ◽  
...  
Keyword(s):  
Heart Failure ◽  
Hospital Mortality ◽  
The Philippines ◽  
Adult Heart ◽  
Heart Failure Patients

Effects of glycemic control on in-hospital mortality among acute heart failure patients with reduced, mid-range, and preserved ejection fraction

2018 ◽  
Vol 33 (9) ◽  
pp. 1022-1028 ◽  
Author(s):  
Kenichi Matsushita ◽  
Kazumasa Harada ◽  
Tetsuro Miyazaki ◽  
Takamichi Miyamoto ◽  
Kiyoshi Iida ◽  
...  
Keyword(s):  
Heart Failure ◽  
Glycemic Control ◽  
Ejection Fraction ◽  
Hospital Mortality ◽  
Acute Heart Failure ◽  
Preserved Ejection Fraction ◽  
Heart Failure Patients

scholarly journals Relationship between Volume and Survival in Closed Intensive Care Units Is Weak and Apparent Only in Mechanically Ventilated Patients

2013 ◽  
Vol 119 (4) ◽  
pp. 871-879 ◽  
Author(s):  
Rafael Fernández ◽  
Susana Altaba ◽  
Lluis Cabre ◽  
Victoria Lacueva ◽  
Antonio Santos ◽  
...  
Keyword(s):  
Hospital Mortality ◽  
Standardized Mortality Ratio ◽  
Hospital Level ◽  
Mechanically Ventilated ◽  
Mechanically Ventilated Patients ◽  
Risk Of Death ◽  
Mortality Ratio ◽  
Low Volume ◽  
Predicted Risk ◽  
Ventilated Patients

Abstract Background: Recent studies have found an association between increased volume and increased intensive care unit (ICU) survival; however, this association might not hold true in ICUs with permanent intensivist coverage. Our objective was to determine whether ICU volume correlates with survival in the Spanish healthcare system. Methods: Post hoc analysis of a prospective study of all patients admitted to 29 ICUs during 3 months. At ICU discharge, the authors recorded demographic variables, severity score, and specific ICU treatments. Follow-up variables included ICU readmission and hospital mortality. Statistics include logistic multivariate analyses for hospital mortality according to quartiles of volume of patients. Results: The authors studied 4,001 patients with a mean predicted risk of death of 23% (range at hospital level: 14–46%). Observed hospital mortality was 19% (range at hospital level: 11–35%), resulting in a standardized mortality ratio of 0.81 (range: 0.5–1.3). Among the 1,923 patients needing mechanical ventilation, the predicted risk of death was 32% (14–60%) and observed hospital mortality was 30% (12–61%), resulting in a standardized mortality ratio of 0.96 (0.5–1.7). The authors found no correlation between standardized mortality ratio and ICU volume in the entire population or in mechanically ventilated patients. Only mechanically ventilated patients in very low-volume ICUs had slightly worse outcome. Conclusion: In the currently studied healthcare system characterized by 24/7 intensivist coverage, the authors found wide variability in outcome among ICUs even after adjusting for severity of illness but no relationship between ICU volume and outcome. Only mechanically ventilated patients in very low-volume centers had slightly worse outcomes.

Trends in COVID-19 Risk-Adjusted Mortality Rates

2020 ◽  
Author(s):  
Leora I Horwitz ◽  
Simon A Jones ◽  
Robert J Cerfolio ◽  
Fritz Francois ◽  
Joseph Greco ◽  
...  
Keyword(s):  
New York ◽  
Hospital Mortality ◽  
Health System ◽  
Vital Signs ◽  
Patient Characteristics ◽  
Mortality Rates ◽  
Standardized Mortality Ratio ◽  
Marginal Effect ◽  
Average Probability ◽  
Mortality Ratio

Early reports showed high mortality from coronavirus disease 2019 (COVID-19). Mortality rates have recently been lower, raising hope that treatments have improved. However, patients are also now younger, with fewer comorbidities. We explored whether hospital mortality was associated with changing demographics at a 3-hospital academic health system in New York. We examined in-hospital mortality or discharge to hospice from March through August 2020, adjusted for demographic and clinical factors, including comorbidities, admission vital signs, and laboratory results. Among 5,121 hospitalizations, adjusted mortality dropped from 25.6% (95% CI, 23.2-28.1) in March to 7.6% (95% CI, 2.5-17.8) in August. The standardized mortality ratio dropped from 1.26 (95% CI, 1.15-1.39) in March to 0.38 (95% CI, 0.12-0.88) in August, at which time the average probability of death (average marginal effect) was 18.2 percentage points lower than in March. Data from one health system suggest that mortality from COVID-19 is decreasing even after accounting for patient characteristics.

Sign in / Sign up

Export Citation Format

Share Document