-
Respiratory Medicine Oct 2023Scores for predicting the long-term mortality of severe pneumonia are lacking. The purpose of this study is to use machine learning methods to develop new pneumonia...
BACKGROUND
Scores for predicting the long-term mortality of severe pneumonia are lacking. The purpose of this study is to use machine learning methods to develop new pneumonia scores to predict the 1-year mortality and hospital mortality of pneumonia patients on admission to the intensive care unit (ICU).
METHODS
The study population was screened from the MIMIC-IV and eICU databases. The main outcomes evaluated were 1-year mortality and hospital mortality in the MIMIC-IV database and hospital mortality in the eICU database. From the full data set, we separated patients diagnosed with community-acquired pneumonia (CAP) and ventilator-associated pneumonia (VAP) for subgroup analysis. We used common shallow machine learning algorithms, including logistic regression, decision tree, random forest, multilayer perceptron and XGBoost.
RESULTS
The full data set of the MIMIC-IV database contained 4697 patients, while that of the eICU database contained 13760 patients. We defined a new pneumonia score, the "Integrated CCI-APS", using a multivariate logistic regression model including six variables: metastatic solid tumor, Charlson Comorbidity Index, readmission, congestive heart failure, age, and Acute Physiology Score III. The area under the curve (AUC) and accuracy of the integrated CCI-APS were assessed in three data sets (full, CAP, and VAP) using both the test set derived from the MIMIC-IV database and the external validation set derived from the eICU database. The AUC value ranges in predicting 1-year and hospital mortality were 0.784-0.797 and 0.691-0.780, respectively, and the corresponding accuracy ranges were 0.723-0.725 and 0.641-0.718, respectively.
CONCLUSIONS
The main contribution of this study was a benchmark for using machine learning models to build pneumonia scores. Based on the idea of integrated learning, we propose a new integrated CCI-APS score for severe pneumonia. In the prediction of 1-year mortality and hospital mortality, our new pneumonia score outperformed the existing score.
Topics: Humans; Pneumonia; Hospital Mortality; Intensive Care Units; Machine Learning
PubMed: 37451647
DOI: 10.1016/j.rmed.2023.107363 -
Epilepsy & Behavior : E&B Jun 2024Studies on epilepsy mortality in the United States are limited. We used the National Vital Statistics System Multiple Cause of Death data to investigate mortality rates...
Studies on epilepsy mortality in the United States are limited. We used the National Vital Statistics System Multiple Cause of Death data to investigate mortality rates and trends during 2011-2021 for epilepsy (defined by the International Classification of Diseases, 10th Revision, codes G40.0-G40.9) as an underlying, contributing, or any cause of death (i.e., either an underlying or contributing cause) for U.S. residents. We also examined epilepsy as an underlying or contributing cause of death by selected sociodemographic characteristics to assess mortality rate changes and disparities in subpopulations. During 2011-2021, the overall age-standardized mortality rates for epilepsy as an underlying (39 % of all deaths) or contributing (61 % of all deaths) cause of death increased 83.6 % (from 2.9 per million to 6.4 per million population) as underlying cause and 144.1 % (from 3.3 per million to 11.0 per million population) as contributing cause (P < 0.001 for both based on annual percent changes). Compared to 2011-2015, in 2016-2020 mortality rates with epilepsy as an underlying or contributing cause of death were higher overall and in nearly all subgroups. Overall, mortality rates with epilepsy as an underlying or contributing cause of death were higher in older age groups, among males than females, among non-Hispanic Black or non-Hispanic American Indian/Alaska Native persons than non-Hispanic White persons, among those living in the West and Midwest than those living in the Northeast, and in nonmetro counties compared to urban regions. Results identify priority subgroups for intervention to reduce mortality in people with epilepsy and eliminate mortality disparity.
Topics: Humans; Epilepsy; United States; Male; Female; Middle Aged; Adult; Aged; Adolescent; Young Adult; Child; Infant; Child, Preschool; Aged, 80 and over; Cause of Death; Infant, Newborn; Mortality; Health Status Disparities
PubMed: 38636143
DOI: 10.1016/j.yebeh.2024.109770 -
Global Health Action Dec 2023Half of global under-five mortalities is neonatal. The highest rates are found in low-income countries such as Ethiopia. Ethiopia has made progress in reducing...
BACKGROUND
Half of global under-five mortalities is neonatal. The highest rates are found in low-income countries such as Ethiopia. Ethiopia has made progress in reducing under-five mortality, but neonatal mortality remains high. Evidence collected continuously at the community level is crucial for understanding the trends and causes of neonatal mortality.
OBJECTIVES
To analyse the trends and causes of neonatal mortality at the Kilte-Awlelo Health and Demographic Surveillance System (KAHDSS) site in Ethiopia from 2010 to 2017.
METHODS
A descriptive study was conducted using data from neonates born between 2010 and 2017 at the KAHDSS site. Data were collected using interviewer-administered questionnaires. Causes of death were examined, and neonatal mortality trends were described using simple linear regression.
RESULTS
The overall average neonatal mortality rate was 17/1000 live births (LBs). The rate increased from 12 per 1000 LBs in 2010 to 15 per 1000 LBs in 2017. The majority of neonatal deaths occurred during the first week of life, and more than one-half died at home. The leading causes were sepsis, pre-term birth (including respiratory distress), disease related to the perinatal period, birth asphyxia, and neonatal pneumonia.
CONCLUSIONS
The high neonatal mortality in Ethiopia requires urgent attention and action. Sepsis, preterm birth, perinatal diseases, asphyxia, and neonatal pneumonia are the leading causes of death in neonates. Facility- and community-based health services should target the leading causes of neonatal deaths.
Topics: Pregnancy; Female; Infant, Newborn; Humans; Perinatal Death; Ethiopia; Asphyxia; Cause of Death; Premature Birth; Infant Mortality; Sepsis; Pneumonia
PubMed: 38126362
DOI: 10.1080/16549716.2023.2289710 -
JAMA Network Open May 2024Higher adherence to the Mediterranean diet has been associated with reduced risk of all-cause mortality, but data on underlying molecular mechanisms over long follow-up...
IMPORTANCE
Higher adherence to the Mediterranean diet has been associated with reduced risk of all-cause mortality, but data on underlying molecular mechanisms over long follow-up are limited.
OBJECTIVES
To investigate Mediterranean diet adherence and risk of all-cause mortality and to examine the relative contribution of cardiometabolic factors to this risk reduction.
DESIGN, SETTING, AND PARTICIPANTS
This cohort study included initially healthy women from the Women's Health Study, who had provided blood samples, biomarker measurements, and dietary information. Baseline data included self-reported demographics and a validated food-frequency questionnaire. The data collection period was from April 1993 to January 1996, and data analysis took place from June 2018 to November 2023.
EXPOSURES
Mediterranean diet score (range, 0-9) was computed based on 9 dietary components.
MAIN OUTCOME AND MEASURES
Thirty-three blood biomarkers, including traditional and novel lipid, lipoprotein, apolipoprotein, inflammation, insulin resistance, and metabolism measurements, were evaluated at baseline using standard assays and nuclear magnetic resonance spectroscopy. Mortality and cause of death were determined from medical and death records. Cox proportional hazards regression was used to calculate hazard ratios (HRs) for Mediterranean diet adherence and mortality risk, and mediation analyses were used to calculate the mediated effect of different biomarkers in understanding this association.
RESULTS
Among 25 315 participants, the mean (SD) baseline age was 54.6 (7.1) years, with 329 (1.3%) Asian women, 406 (1.6%) Black women, 240 (0.9%) Hispanic women, 24 036 (94.9%) White women, and 95 (0.4%) women with other race and ethnicity; the median (IQR) Mediterranean diet adherence score was 4.0 (3.0-5.0). Over a mean (SD) of 24.7 (4.8) years of follow-up, 3879 deaths occurred. Compared with low Mediterranean diet adherence (score 0-3), adjusted risk reductions were observed for middle (score 4-5) and upper (score 6-9) groups, with HRs of 0.84 (95% CI, 0.78-0.90) and 0.77 (95% CI, 0.70-0.84), respectively (P for trend < .001). Further adjusting for lifestyle factors attenuated the risk reductions, but they remained statistically significant (middle adherence group: HR, 0.92 [95% CI, 0.85-0.99]; upper adherence group: HR, 0.89 [95% CI, 0.82-0.98]; P for trend = .001). Of the biomarkers examined, small molecule metabolites and inflammatory biomarkers contributed most to the lower mortality risk (explaining 14.8% and 13.0%, respectively, of the association), followed by triglyceride-rich lipoproteins (10.2%), body mass index (10.2%), and insulin resistance (7.4%). Other pathways, including branched-chain amino acids, high-density lipoproteins, low-density lipoproteins, glycemic measures, and hypertension, had smaller contributions (<3%).
CONCLUSIONS AND RELEVANCE
In this cohort study, higher adherence to the Mediterranean diet was associated with 23% lower risk of all-cause mortality. This inverse association was partially explained by multiple cardiometabolic factors.
Topics: Humans; Diet, Mediterranean; Female; Middle Aged; Biomarkers; Cohort Studies; Patient Compliance; Mortality; Cause of Death; Aged; Adult; Proportional Hazards Models; Risk Factors
PubMed: 38819819
DOI: 10.1001/jamanetworkopen.2024.14322 -
Scientific Reports Oct 2023This study intends to predict in-hospital and 6-month mortality, as well as 30-day and 90-day hospital readmission, using Machine Learning (ML) approach via conventional...
This study intends to predict in-hospital and 6-month mortality, as well as 30-day and 90-day hospital readmission, using Machine Learning (ML) approach via conventional features. A total of 737 patients remained after applying the exclusion criteria to 1101 heart failure patients. Thirty-four conventional features were collected for each patient. First, the data were divided into train and test cohorts with a 70-30% ratio. Then train data were normalized using the Z-score method, and its mean and standard deviation were applied to the test data. Subsequently, Boruta, RFE, and MRMR feature selection methods were utilized to select more important features in the training set. In the next step, eight ML approaches were used for modeling. Next, hyperparameters were optimized using tenfold cross-validation and grid search in the train dataset. All model development steps (normalization, feature selection, and hyperparameter optimization) were performed on a train set without touching the hold-out test set. Then, bootstrapping was done 1000 times on the hold-out test data. Finally, the obtained results were evaluated using four metrics: area under the ROC curve (AUC), accuracy (ACC), specificity (SPE), and sensitivity (SEN). The RFE-LR (AUC: 0.91, ACC: 0.84, SPE: 0.84, SEN: 0.83) and Boruta-LR (AUC: 0.90, ACC: 0.85, SPE: 0.85, SEN: 0.83) models generated the best results in terms of in-hospital mortality. In terms of 30-day rehospitalization, Boruta-SVM (AUC: 0.73, ACC: 0.81, SPE: 0.85, SEN: 0.50) and MRMR-LR (AUC: 0.71, ACC: 0.68, SPE: 0.69, SEN: 0.63) models performed the best. The best model for 3-month rehospitalization was MRMR-KNN (AUC: 0.60, ACC: 0.63, SPE: 0.66, SEN: 0.53) and regarding 6-month mortality, the MRMR-LR (AUC: 0.61, ACC: 0.63, SPE: 0.44, SEN: 0.66) and MRMR-NB (AUC: 0.59, ACC: 0.61, SPE: 0.48, SEN: 0.63) models outperformed the others. Reliable models were developed in 30-day rehospitalization and in-hospital mortality using conventional features and ML techniques. Such models can effectively personalize treatment, decision-making, and wiser budget allocation. Obtained results in 3-month rehospitalization and 6-month mortality endpoints were not astonishing and further experiments with additional information are needed to fetch promising results in these endpoints.
Topics: Humans; Patient Readmission; Hospital Mortality; Machine Learning; Heart Failure
PubMed: 37907666
DOI: 10.1038/s41598-023-45925-3 -
Journal of Public Health (Oxford,... Nov 2023Research from various countries has shown increases in alcohol- and drug-related deaths and suicide, known as 'deaths of despair' over recent decades, particularly among...
BACKGROUND
Research from various countries has shown increases in alcohol- and drug-related deaths and suicide, known as 'deaths of despair' over recent decades, particularly among low-educated middle-aged individuals. However, little is known about trends in death-of-despair causes in Spain. Therefore, we aim to descriptively examine this among 25-64-year-olds from 1980 to 2019 and by educational attainment for the years 2017-19.
METHODS
We obtained mortality and population data from the National Institute of Statistics to estimate age-standardized mortality rates and assess educational inequalities using the relative index of inequality (RII).
RESULTS
Deaths of despair as a share of total mortality slightly increased from 2000 onwards, particularly among 25-64-year-old men (from 9 to 10%). Only alcohol-related mortality declined relatively more since 1980 compared with all-cause mortality. Regarding educational differences, low-educated men presented higher mortality rates in all death-of-despair causes (alcohol-related: RII 3.54 (95% CI: 2.21-5.66); drug-related: RII 3.49 (95% CI: 1.80-6.77); suicide: RII 1.97 (95% CI: 1.49-2.61)). Women noteworthy differences were only observed for alcohol-related (RII 3.50 (95% CI: 2.13-5.75)).
CONCLUSIONS
Findings suggest an increasing proportion of deaths of despair among 25-64-year-olds since 2000, particularly among men. Public health policies are needed to reduce and prevent these premature and preventable causes of mortality.
Topics: Middle Aged; Male; Humans; Female; Adult; Cause of Death; Spain; Educational Status; Academic Success; Suicide; Mortality; Socioeconomic Factors
PubMed: 37491646
DOI: 10.1093/pubmed/fdad133 -
BMC Research Notes Jul 2023Surveillance of infant and fetal deaths is of paramount importance in thinking about government strategies to reduce these rates, provide greater visibility of these...
OBJECTIVES
Surveillance of infant and fetal deaths is of paramount importance in thinking about government strategies to reduce these rates, provide greater visibility of these mortality figures in the country, enable the adoption of prevention measures, as well as contribute to a better record of deaths.
DATA DESCRIPTION
The dataset comprises fetal, neonatal, early neonatal, late neonatal, and perinatal Mortality Rates of Brazilian municipalities with their respective information, between 2010 to 2020, aggregated by epidemiological week.
Topics: Infant; Infant, Newborn; Pregnancy; Female; Humans; Brazil; Infant Mortality; Fetal Death; Perinatal Mortality; Prenatal Care
PubMed: 37461048
DOI: 10.1186/s13104-023-06425-9 -
The Lancet. Public Health May 2024Globally, 1·3 billion people have a disability and are more likely to experience poor health than the general population. However, little is known about the mortality... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Globally, 1·3 billion people have a disability and are more likely to experience poor health than the general population. However, little is known about the mortality or life expectancy gaps experienced by people with disabilities. We aimed to undertake a systematic review and meta-analysis of the association between disability and mortality, compare these findings to the evidence on the association of impairment types and mortality, and model the estimated life expectancy gap experienced by people with disabilities.
METHODS
We did a mixed-methods study, which included a systematic review and meta-analysis, umbrella review, and life expectancy modelling. For the systematic review and meta-analysis, we searched MEDLINE, Global Health, PsycINFO, and Embase for studies published in English between Jan 1, 2007, and June 7, 2023, investigating the association of mortality and disability. We included prospective and retrospective cohort studies and randomised controlled trials with a baseline assessment of disability and a longitudinal assessment of all-cause mortality or cause-specific mortality. Two reviewers independently assessed study eligibility, extracted the data, and assessed risk of bias. We did a random-effects meta-analysis to calculate a pooled estimate of the mortality rate ratio for people with disabilities compared with those without disabilities. We did an umbrella review of meta-analyses examining the association between different impairment types and mortality. We used life table modelling to translate the mortality rate ratio into an estimate of the life expectancy gap between people with disabilities and the general population. The systematic review and meta-analysis is registered with PROSPERO, CRD42023433374.
FINDINGS
Our search identified 3731 articles, of which 42 studies were included in the systematic review. The meta-analysis included 31 studies. Pooled estimates showed that all-cause mortality was 2·24 times (95% CI 1·84-2·72) higher in people with disabilities than among people without disabilities, although heterogeneity between the studies was high (τ=0·28, I=100%). Modelling indicated a median gap in life expectancy of 13·8 years (95% CI 13·1-14·5) by disability status. Cause-specific mortality was also higher for people with disabilities, including for cancer, COVID-19, cardiovascular disease, and suicide. The umbrella review identified nine meta-analyses, which showed consistently elevated mortality rates among people with different impairment types.
INTERPRETATION
Mortality inequities experienced by people with disabilities necessitate health system changes and efforts to address inclusion and the social determinants of health.
FUNDING
National Institute for Health and Care Research, Rhodes Scholarship, Indonesia Endowment Funds for Education, Foreign, Commonwealth and Development Office (Programme for Evidence to Inform Disability Action), and the Arts and Humanities Research Council.
Topics: Humans; Disabled Persons; Life Expectancy; Mortality
PubMed: 38702095
DOI: 10.1016/S2468-2667(24)00054-9 -
Demography Apr 2024We propose a novel decomposition approach that breaks down the levels and trends of lifespan inequality as the sum of cause-of-death contributions. The suggested method...
We propose a novel decomposition approach that breaks down the levels and trends of lifespan inequality as the sum of cause-of-death contributions. The suggested method shows whether the levels and changes in lifespan inequality are attributable to the levels and changes in (1) the extent of inequality in the cause-specific age-at-death distribution (the "Inequality" component), (2) the total share of deaths attributable to each cause (the "Proportion" component), or (3) the cause-specific mean age at death (the "Mean" component). This so-called Inequality-Proportion-Mean (or IPM) method is applied to 10 low-mortality countries in Europe. Our findings suggest that the most prevalent causes of death (in our setting, "circulatory system" and "neoplasms") do not necessarily contribute the most to overall levels of lifespan inequality. In fact, "perinatal and congenital" causes are the strongest drivers of lifespan inequality declines. The contribution of the IPM components to changes in lifespan inequality varies considerably across causes, genders, and countries. Among the three components, the Mean one explains the least lifespan inequality dynamics, suggesting that shifts in cause-specific mean ages at death alone contributed little to changes in lifespan inequality.
Topics: Pregnancy; Humans; Male; Female; Longevity; Life Expectancy; Cause of Death; Europe; Mortality
PubMed: 38526181
DOI: 10.1215/00703370-11245278 -
Sleep Health Apr 2024To identify longitudinal trajectories of sleep duration and quality and estimate their association with mild cognitive impairment, frailty, and all-cause mortality.
OBJECTIVES
To identify longitudinal trajectories of sleep duration and quality and estimate their association with mild cognitive impairment, frailty, and all-cause mortality.
METHODS
We used data from three waves (2009, 2014, 2017) of the WHO Study on Global Aging and Adult Health in Mexico. The sample consisted of 2722 adults aged 50 and over. Sleep duration and quality were assessed by self-report. Sleep trajectories were determined by applying growth mixture models. Mixed-effects logistic (mild cognitive impairment) and ordinal logistic (frailty), and Cox proportional hazards (all-cause mortality) models were fitted.
RESULTS
Three classes for sleep duration ("optimal-stable," "long-increasing," and "short-decreasing") and quality ("very good-increasing," "very good-decreasing," and "moderate/poor stable") were identified. Compared to the optimal-stable group, the long-increasing trajectory had greater odds for mild cognitive impairment (odds ratio=1.68, 95% CI: 1.01-2.78) and frailty (odds ratio=1.66, 95% CI: 1.13-2.46), and higher risk for all-cause mortality (hazard ratio=1.91, 95% CI: 1.14-3.19); and the short-decreasing class had a higher probability of frailty (odds ratio=1.83, 95% CI: 1.26-2.64). Regarding the sleep quality, the moderate/poor stable trajectory had higher odds of frailty (odds ratio=1.71, 95% CI: 1.18-2.47) than very good-increasing group.
CONCLUSIONS
These results have important implications for clinical practice and public health policies, given that the evaluation and treatment of sleep disorders need more attention in primary care settings. Interventions to detect and treat sleep disorders should be integrated into clinical practice to prevent or delay the appearance of alterations in older adults' physical and cognitive function. Further research on sleep quality and duration is warranted to understand their contribution to healthy aging.
Topics: Aged; Aged, 80 and over; Female; Humans; Male; Middle Aged; Cause of Death; Cognitive Dysfunction; Frailty; Longitudinal Studies; Mexico; Mortality; Sleep Duration; Sleep Quality; Time Factors
PubMed: 38238122
DOI: 10.1016/j.sleh.2023.12.002