ABSTRACT
Inhaled corticosteroids (ICS) are efficacious in the treatment of asthma, which affects more than 300 million people in the world. While genome-wide association studies have identified genes involved in differential treatment responses to ICS in asthma, few studies have evaluated the effects of combined rare and common variants on ICS response among children with asthma. Among children with asthma treated with ICS with whole exome sequencing (WES) data in the PrecisionLink Biobank (91 White and 20 Black children), we examined the effect and contribution of rare and common variants with hospitalizations or emergency department visits. For 12 regions previously associated with asthma and ICS response (DPP10, FBXL7, NDFIP1, TBXT, GLCCI1, HDAC9, TBXAS1, STAT6, GSDMB/ORMDL3, CRHR1, GNGT2, FCER2), we used the combined sum test for the sequence kernel association test (SKAT) adjusting for age, sex, and BMI and stratified by race. Validation was conducted in the Biorepository and Integrative Genomics (BIG) Initiative (83 White and 134 Black children). Using a Bonferroni threshold for the 12 regions tested (i.e., 0.05/12 = 0.004), GSDMB/ORMDL3 was significantly associated with ICS response for the combined effect of rare and common variants (p-value = 0.003) among White children in the PrecisionLink Biobank and replicated in the BIG Initiative (p-value = 0.02). Using WES data, the combined effect of rare and common variants for GSDMB/ORMDL3 was associated with ICS response among asthmatic children in the PrecisionLink Biobank and replicated in the BIG Initiative. This proof-of-concept study demonstrates the power of biobanks of pediatric real-life populations in asthma genomic investigations.
Subject(s)
Adrenal Cortex Hormones , Asthma , Gasdermins , Membrane Proteins , Humans , Asthma/drug therapy , Asthma/genetics , Child , Female , Male , Adrenal Cortex Hormones/therapeutic use , Adrenal Cortex Hormones/administration & dosage , Administration, Inhalation , Membrane Proteins/genetics , Genome-Wide Association Study , Adolescent , Child, Preschool , Exome Sequencing , Polymorphism, Single NucleotideABSTRACT
INTRODUCTION: Acute kidney injury (AKI) is common among hospitalized patients with sickle cell disease (SCD) and contributes to increased morbidity and mortality. Early identification and management of AKI is essential to preventing poor outcomes. We aimed to predict AKI earlier in patients with SCD using a machine-learning model that utilized continuous minute-by-minute physiological data. METHODS: A total of6,278 adult SCD patient encounters were admitted to inpatient units across five regional hospitals in Memphis, TN, over 3 years, from July 2017 to December 2020. From these, 1,178 patients were selected after filtering for data availability. AKI was identified in 82 (7%) patient encounters, using the 2012 Kidney Disease Improving Global Outcomes (KDIGO) criteria. The remaining 1,096 encounters served as controls. Features derived from five physiological data streams, heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from bedside monitors were used. An XGBoost classifier was used for classification. RESULTS: Our model accurately predicted AKI up to 12 h before onset with an area under the receiver operator curve (AUROC) of 0.91 (95% CI [0.89-0.93]) and up to 48 h before AKI with an AUROC of 0.82 (95% CI [0.80-0.83]). Patients with AKI were more likely to be female (64.6%) and have history of hypertension, pulmonary hypertension, chronic kidney disease, and pneumonia than the control group. CONCLUSION: XGBoost accurately predicted AKI as early as 12 h before onset in hospitalized SCD patients and may enable the development of innovative prevention strategies.
Subject(s)
Acute Kidney Injury , Anemia, Sickle Cell , Adult , Humans , Female , Male , Acute Kidney Injury/diagnosis , Acute Kidney Injury/epidemiology , Acute Kidney Injury/etiology , Anemia, Sickle Cell/complications , Anemia, Sickle Cell/epidemiology , Kidney , Risk Assessment , Machine Learning , Retrospective StudiesABSTRACT
Endothelial and epithelial cells are morphologically different and play a critical role in host defense during Candida albicans infection. Both cells respond to C. albicans infection by activating various signaling pathways and gene expression patterns. Their interactions with these pathogens can have beneficial and detrimental effects, and a better understanding of these interactions can help guide the development of new therapies for C. albicans infection. To identify the differences and similarities between human endothelial and oral epithelial cell transcriptomics during C. albicans infection, we performed consensus WGCNA on 32 RNA-seq samples by relating the consensus modules to endothelial-specific modules and analyzing the genes connected. This analysis resulted in the identification of 14 distinct modules. We demonstrated that the magenta module correlates significantly with C. albicans infection in each dataset. In addition, we found that the blue and cyan modules in the two datasets had opposite correlation coefficients with a C. albicans infection. However, the correlation coefficients and p-values between the two datasets were slightly different. Functional analyses of the hub of genes from endothelial cells elucidated the enrichment in TNF, AGE-RAGE, MAPK, and NF-κB signaling. On the other hand, glycolysis, pyruvate metabolism, amino acid, fructose, mannose, and vitamin B6 metabolism were enriched in epithelial cells. However, mitophagy, necroptosis, apoptotic processes, and hypoxia were enriched in both endothelial and epithelial cells. Protein-protein interaction analysis using STRING and CytoHubba revealed STAT3, SNRPE, BIRC2, and NFKB2 as endothelial hub genes, while RRS1, SURF6, HK2, and LDHA genes were identified in epithelial cells. Understanding these similarities and differences may provide new insights into the pathogenesis of C. albicans infections and the development of new therapeutic targets and interventional strategies.
Subject(s)
Candida albicans , Candidiasis , Humans , Candida albicans/genetics , Gene Regulatory Networks , Endothelial Cells/metabolism , Consensus , Candidiasis/metabolism , Epithelial Cells/metabolism , Nuclear Proteins/geneticsABSTRACT
Invasive fungal infections are a significant reason for morbidity and mortality among organ transplant recipients. Therefore, it is critical to investigate the host and candida niches to understand the epidemiology of fungal infections in transplantation. Candida albicans is an opportunistic fungal pathogen that causes fatal invasive mucosal infections, particularly in solid organ transplant patients. Therefore, identifying and characterizing these genes would play a vital role in understanding the complex regulation of host-pathogen interactions. Using 32 RNA-sequencing samples of human cells infected with C. albicans, we developed WGCNA coexpression networks and performed DESeq2 differential gene expression analysis to identify the genes that positively correlate with human candida infection. Using hierarchical clustering, we identified 5 distinct modules. We studied the inter- and intramodular gene network properties in the context of sample status traits and identified the highly enriched genes in the correlated modules. We identified 52 genes that were common in the most significant WGCNA turquoise module and differentially expressed genes in human endothelial cells (HUVEC) infection vs. control samples. As a validation step, we identified the differentially expressed genes from the independent Candida-infected human oral keratinocytes (OKF6) samples and validated 30 of the 52 common genes. We then performed the functional enrichment analysis using KEGG and GO. Finally, we performed protein-protein interaction (PPI) analysis using STRING and CytoHubba from 30 validated genes. We identified 8 hub genes (JUN, ATF3, VEGFA, SLC2A1, HK2, PTGS2, PFKFB3, and KLF6) that were enriched in response to hypoxia, angiogenesis, vasculogenesis, hypoxia-induced signaling, cancer, diabetes, and transplant-related disease pathways. The discovery of genes and functional pathways related to the immune system and gene coexpression and differential gene expression analyses may serve as novel diagnostic markers and potential therapeutic targets.
ABSTRACT
Clinicians frequently observe hemodynamic changes preceding elevated intracranial pressure events. We employed a machine learning approach to identify novel and differentially expressed features associated with elevated intracranial pressure events in children with severe brain injuries. Statistical features from physiologic data streams were derived from non-overlapping 30-min analysis windows prior to 21 elevated intracranial pressure events; 200 records without elevated intracranial pressure events were used as controls. Ten Monte Carlo simulations with training/testing splits provided performance benchmarks for 4 machine learning approaches. XGBoost yielded the best performing predictive models. Shapley Additive Explanations analyses demonstrated that a majority of the top 20 contributing features consistently derived from blood pressure data streams up to 240 min prior to elevated intracranial events. The best performing prediction model was using the 30-60 min analysis window; for this model, the area under the receiver operating characteristic window using XGBoost was 0.82 (95% CI 0.81-0.83); the area under the precision-recall curve was 0.24 (95% CI 0.23-0.25), above the expected baseline of 0.1. We conclude that physiomarkers discernable by machine learning are concentrated within blood pressure and intracranial pressure data up to 4 h prior to elevated intracranial pressure events.
Subject(s)
Intracranial Hypertension , Intracranial Pressure , Child , Humans , Intracranial Pressure/physiology , Blood Pressure , Intracranial Hypertension/diagnosis , ROC Curve , Machine LearningABSTRACT
BACKGROUND: Prediction of low Apgar score for vaginal deliveries following labor induction intervention is critical for improving neonatal health outcomes. We set out to investigate important attributes and train popular machine learning (ML) algorithms to correctly classify neonates with a low Apgar scores from an imbalanced learning perspective. METHODS: We analyzed 7716 induced vaginal deliveries from the electronic birth registry of the Kilimanjaro Christian Medical Centre (KCMC). 733 (9.5%) of which constituted of low (< 7) Apgar score neonates. The 'extra-tree classifier' was used to assess features' importance. We used Area Under Curve (AUC), recall, precision, F-score, Matthews Correlation Coefficient (MCC), balanced accuracy (BA), bookmaker informedness (BM), and markedness (MK) to evaluate the performance of the selected six (6) machine learning classifiers. To address class imbalances, we examined three widely used resampling techniques: the Synthetic Minority Oversampling Technique (SMOTE) and Random Oversampling Examples (ROS) and Random undersampling techniques (RUS). We applied Decision Curve Analysis (DCA) to evaluate the net benefit of the selected classifiers. RESULTS: Birth weight, maternal age, and gestational age were found to be important predictors for the low Apgar score following induced vaginal delivery. SMOTE, ROS and and RUS techniques were more effective at improving "recalls" among other metrics in all the models under investigation. A slight improvement was observed in the F1 score, BA, and BM. DCA revealed potential benefits of applying Boosting method for predicting low Apgar scores among the tested models. CONCLUSION: There is an opportunity for more algorithms to be tested to come up with theoretical guidance on more effective rebalancing techniques suitable for this particular imbalanced ratio. Future research should prioritize a debate on which performance indicators to look up to when dealing with imbalanced or skewed data.
Subject(s)
Delivery, Obstetric , Machine Learning , Apgar Score , Female , Humans , Infant, Newborn , Labor, Induced , Pregnancy , Tanzania , Tertiary Care CentersABSTRACT
BACKGROUND: The green peach aphid, Myzus persicae Sulzer, and the bean aphid, Aphis fabae Scopoli (both Hemiptera: Aphididae), are serious pests of greenhouse vegetable crops in Iraq and other regions of the globe. In this study, two morphological identical isolates (AA80 and AA82) of the entomopathogenic fungus Clonostachys rosea Schroers (Hypocreales: Bionectriaceae) from Iraq were isolated and characterized with phylogenetic analysis based on the internal transcribed spacer (ITS) region. The efficacy of C. rosea against M. persicae and A. fabae was previously unknown. RESULTS: In the laboratory bioassays, mortality of adult M. persicae and A. fabae caused by both C. rosea isolates varied according to conidial concentrations, with complete mortality occurring at 1 × 109 conidia ml-1 10 day post treatment. For M. persicae, LC50 values of AA80 and AA80 isolates were 3.6 × 106 and 3.8 × 106 conidia ml-1. For A. fabae, LC50 values of AA80 and AA80 isolates were 4.5 × 106 and 4.35 × 106 conidia ml-1. Infection by both fungal isolates at LC50 values reduced total fecundity of the treated aphids by 20% when compared to the untreated aphids. CONCLUSIONS: The results from laboratory bioassays showed that C. rosea has potential as a biological control agent of M. persicae and A. fabae which is crucial for ecofriendly biopesticide development. However, further field and greenhouse studies are required for mass production.
ABSTRACT
BACKGROUND: Hypertension is a known risk factor for several chronic conditions including diabetes and cardiovascular diseases. However, little is known about its impact on Health-related quality of life (HRQoL) in the context of Bangladesh. This study aimed to evaluate the association of hypertension on HRQoL among Bangladeshi patients corresponding to the socio-demographic condition, comorbid conditions, treatment, and health outcomes. METHODS: A hospital based cross-sectional study was conducted using a pre-tested structured questionnaire among patients with hypertension in 22 tertiary medical college hospitals in Bangladesh. The study recruited male and female hypertensive patients of age ≥18 years between July 2020 to February 2021 using consecutive sampling methods. Health related quality of life was measured using the widely-used index of EQ-5D that considers 243 different health-related attributes and uses a scale in which 0 indicates a health state equivalent to death and 1 indicates perfect health status. The five dimensions of the quality index included mobility, self-care, usual activities, pain or discomfort, and anxiety or depression. Ordered logit regression and linear regression models were used to estimate the predictors of comorbidity and HRQoL. RESULTS: Of the 1,912 hypertensive patients, 56.2% were female, 86.5% were married, 70.7% were either overweight or obese, 67.6% had a family history of hypertension, and 85.5% were on anti-hypertensive medication. Among the individuals with comorbidities, 47.6% had diabetes, 32.3% were obese, 16.2% had heart disease, 15% were visually impaired, and 13.8% were suffering from psychological diseases. HRQoL was found to be inversely proportional to the number of comorbidities. The most frequent comorbidities of diabetes and obesity showed the highest EQ- 5D mean utilities of 0.59 and 0.64, respectively. CONCLUSIONS: Prevalent comorbidities, diabetes and obesity were found to be the significant underlying causes of declining HRQoL. It is recommended that the comorbidities should be adequately addressed for better HRQoL. Special attention should be given to address mental health issues of patients with hypertension.
Subject(s)
Hypertension , Quality of Life , Adolescent , Bangladesh/epidemiology , Comorbidity , Cross-Sectional Studies , Female , Hospitals , Humans , Hypertension/epidemiology , Hypertension/psychology , Male , Obesity/epidemiology , Quality of Life/psychology , Surveys and QuestionnairesABSTRACT
Red mud is a solid hazardous alumina industrial waste, which is rich in iron, titanium, aluminum, silicon, calcium, etc. The red mud contains 30-60% of hematite, which is suitable for shielding high energy X- and gamma rays. So, the iron rich red mud was converted into diagnostic X-ray shielding tiles through ceramic route by adding a certain weight percentage of BaSO4 and binders (kaolin clay or sodium hexametaphosphate) with it. The kaolin clay tile possess sufficient impact strength (failure point is 852â¯mm for 19â¯mm steel ball) and flexural strength of ~25â¯N/mm2, which is suitable for wall applications. The 10.3â¯mm and 14.7â¯mm thick red mud:BaSO4:kaolin clay tile possess the attenuation equivalent to 2â¯mm and 2.3â¯mm lead at 125 kVp and 140 kVp, respectively. No heavy elements were found to leach out except chromium and arsenic from the sintered tiles. However, the leaching of Cr (0.6 ppm) and As (0.015 ppm) was found to be well below the permissible limit. These tiles can be used in the X-ray diagnosis, CT scanner, bone densitometry, and cath labs instead of toxic lead sheet and thereby to protect the operating personnel, public, and environment from radiation hazards.
Subject(s)
Aluminum Oxide , Hazardous Waste , Ceramics , Industrial Waste/analysis , Iron , RadiographyABSTRACT
The materials used in electrical and electronic applications have great importance and broader applications, but they have severe electromagnetic interference (EMI). These materials have extensive applications in broadcasting, medical industries, research, defence sectors, communication and similar fields. The EMI can be addressed by using effective EMI shielding materials. This review presents a detailed, comprehensive description for making electromagnetic interference shielding material by recycling various wastes. It starts with highlighting the overview of electromagnetic interference shielding (EMI) and its theoretical aspects. It provides a comprehensive and detailed understanding of recent trends in the novel approaches towards fabricating EMI shielding from industrial waste, agricultural waste and other miscellaneous wastes. This paper critically reviews the works related to the recycling of wastes like red mud (waste from the aluminium refining industry), ground tyre rubber, tea waste (biowaste) from tea industries, bagasse (waste from sugar cane industry), peanut and hazelnut shells (agricultural waste), waste tissue paper and polyethylene and other miscellaneous wastes like hydrocarbon carbon black and ash for the fabrication of highly effective electromagnetic (EM) interference shielding materials. Highly effective results have been reported using red mud showing maximum efficiency of 51.4 dB in X-band range, various agricultural waste displaying reflection loss of up to - 87.117 dB (in the range 0.01 to 20 GHz) and miscellaneous waste giving EMI SE of 80 dB in X-band frequency. A separate section is dedicated to emphasizing future work and recommendations.
Subject(s)
Electromagnetic Fields , RecyclingABSTRACT
We announce the complete genome sequences of 12 severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) sublineage B.1.617.2 strains (Delta variant) obtained from nasopharyngeal and oropharyngeal swab samples from 12 pediatric patients in Chittagong, Bangladesh, displaying COVID-19 symptoms. Oxford Nanopore MinION sequencing technology was used to generate the genomic sequences.
ABSTRACT
We present an interpretable machine learning algorithm called 'eARDS' for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88-0.90), sensitivity of 0.77 (95% CI = 0.75-0.78), specificity 0.85 (95% CI = 085-0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81-0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO2), standard deviation of the systolic blood pressure (SBP), O2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18-40) (AUROC = 0.93 [0.92-0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81-0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.
Subject(s)
COVID-19 , Machine Learning , Models, Biological , Respiratory Distress Syndrome , SARS-CoV-2/metabolism , Adolescent , Adult , Aged , Aged, 80 and over , COVID-19/blood , COVID-19/complications , COVID-19/diagnosis , COVID-19/physiopathology , Critical Illness , Female , Humans , Male , Medical Records Systems, Computerized , Middle Aged , Oxygen/blood , Respiratory Distress Syndrome/blood , Respiratory Distress Syndrome/diagnosis , Respiratory Distress Syndrome/etiology , Respiratory Distress Syndrome/physiopathology , Respiratory Rate , Risk FactorsABSTRACT
Transplant glomerulopathy develops through multiple mechanisms, including donor-specific antibodies, T cells and innate immunity. This study investigates circulating small RNA profiles in serum samples of kidney transplant recipients with biopsy-proven transplant glomerulopathy. Among total small RNA population, miRNAs were the most abundant species in the serum of kidney transplant patients. In addition, fragments arising from mature tRNA and rRNA were detected. Most of the tRNA fragments were generated from 5' ends of mature tRNA and mainly from two parental tRNAs: tRNA-Gly and tRNA-Glu. Moreover, transplant patients with transplant glomerulopathy displayed a novel tRNA fragments signature. Gene expression analysis from allograft tissues demonstrated changes in canonical pathways related to immune activation such as iCos-iCosL signaling pathway in T helper cells, Th1 and Th2 activation pathway, and dendritic cell maturation. mRNA targets of down-regulated miRNAs such as miR-1224-5p, miR-4508, miR-320, miR-378a from serum were globally upregulated in tissue. Integration of serum miRNA profiles with tissue gene expression showed that changes in serum miRNAs support the role of T-cell mediated mechanisms in ongoing allograft injury.
Subject(s)
Cell-Free Nucleic Acids/blood , Graft Rejection/blood , Kidney Diseases/blood , Kidney Transplantation , MicroRNAs/blood , RNA, Transfer, Gly/blood , Adult , Aged , Female , Humans , Male , Middle Aged , Th1 Cells/metabolism , Th2 Cells/metabolismABSTRACT
A complicated clinical course for critically ill patients admitted to the intensive care unit (ICU) usually includes multiorgan dysfunction and subsequent death. Owing to the heterogeneity, complexity, and unpredictability of the disease progression, ICU patient care is challenging. Identifying the predictors of complicated courses and subsequent mortality at the early stages of the disease and recognizing the trajectory of the disease from the vast array of longitudinal quantitative clinical data is difficult. Therefore, we attempted to perform a meta-analysis of previously published gene expression datasets to identify novel early biomarkers and train the artificial intelligence systems to recognize the disease trajectories and subsequent clinical outcomes. Using the gene expression profile of peripheral blood cells obtained within 24 h of pediatric ICU (PICU) admission and numerous clinical data from 228 septic patients from pediatric ICU, we identified 20 differentially expressed genes predictive of complicated course outcomes and developed a new machine learning model. After 5-fold cross-validation with 10 iterations, the overall mean area under the curve reached 0.82. Using a subset of the same set of genes, we further achieved an overall area under the curve of 0.72, 0.96, 0.83, and 0.82, respectively, on four independent external validation sets. This model was highly effective in identifying the clinical trajectories of the patients and mortality. Artificial intelligence systems identified eight out of twenty novel genetic markers (SDC4, CLEC5A, TCN1, MS4A3, HCAR3, OLAH, PLCB1, and NLRP1) that help predict sepsis severity or mortality. While these genes have been previously associated with sepsis mortality, in this work, we show that these genes are also implicated in complex disease courses, even among survivors. The discovery of eight novel genetic biomarkers related to the overactive innate immune system, including neutrophil function, and a new predictive machine learning method provides options to effectively recognize sepsis trajectories, modify real-time treatment options, improve prognosis, and patient survival.
Subject(s)
Disease Susceptibility , Leukocytes/immunology , Leukocytes/metabolism , Machine Learning , Sepsis/epidemiology , Sepsis/etiology , Transcriptome , Biomarkers , Chromosome Mapping , Computational Biology/methods , Critical Care , Databases, Genetic , Gene Expression Profiling/methods , Hospital Mortality , Humans , Intensive Care Units , ROC Curve , Reproducibility of Results , Sepsis/mortality , Time FactorsABSTRACT
Early detection of sepsis can be life-saving. Machine learning models have shown great promise in early sepsis prediction when applied to patient physiological data in real-time. However, these existing models often under-perform in terms of positive predictive value, an important metric in clinical settings. This is especially the case when the models are applied to data with less than 50% sepsis prevalence, reflective of the incidence rate of sepsis on the floor or in the ICU. In this study, we develop HeMA, a hierarchically enriched machine learning approach for managing false alarms in real time, and conduct a case study for early sepsis prediction. Specifically, we develop a two-stage framework, where a first stage machine learning model is paired with statistical tests, particularly Kolmogorov-Smirnov tests, in the second stage, to predict whether a patient would develop sepsis. Compared with machine learning models alone, the framework results in an increase in specificity and positive predictive value, without compromising F1 score. In particular, the framework shows improved performance when applied to data with 50% and 25% sepsis prevalence, collected from a large hospital system in the US, resulting in up to 18% and 7% increase in specificity and positive predictive value, respectively. Despite the significant improvements observed, and although F1 score is not negatively affected, because of the up to 6% decrease in sensitivity, further improvements and pilot studies may be necessary before deploying the framework in a clinical setting. Finally, external validation conducted using a publicly available dataset produces similar results, validating that the proposed framework is generalizable.
Subject(s)
Machine Learning , Sepsis , Early Diagnosis , Humans , Predictive Value of Tests , Sepsis/diagnosis , Sepsis/epidemiologyABSTRACT
BACKGROUND: Sepsis is a life-threatening condition with high mortality rates. Early detection and treatment are critical to improving outcomes. Our primary objective was to develop artificial intelligence capable of predicting sepsis earlier using a minimal set of streaming physiological data in real time. METHODS AND FINDINGS: A total of 29,552 adult patients were admitted to the intensive care unit across five regional hospitals in Memphis, Tenn, over 18 months from January 2017 to July 2018. From these, 5,958 patients were selected after filtering for continuous (minute-by-minute) physiological data availability. A total of 617 (10.4%) patients were identified as sepsis cases, using the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria. Physiomarkers, a set of signal processing features, were derived from five physiological data streams including heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from the bedside monitors. A support vector machine classifier was used for classification. The model accurately predicted sepsis up to a mean and 95% confidence interval of 17.4â±â0.22âh before sepsis onset, with an average test accuracy of 83.0% (average sensitivity, specificity, and area under the receiver operating characteristics curve of 0.757, 0.902, and 0.781, respectively). CONCLUSIONS: This study demonstrates that salient physiomarkers derived from continuous bedside monitoring are temporally and differentially expressed in septic patients. Using this information, minimalistic artificial intelligence models can be developed to predict sepsis earlier in critically ill patients.
Subject(s)
Artificial Intelligence , Sepsis/physiopathology , Aged , Critical Illness , Female , Humans , Male , Middle Aged , Prognosis , Retrospective Studies , Time FactorsABSTRACT
Autonomic nervous system involvement precedes the motor features of Parkinson's disease (PD). Our goal was to develop a proof-of-concept model for identifying subjects at high risk of developing PD by analysis of cardiac electrical activity. We used standard 10-s electrocardiogram (ECG) recordings of 60 subjects from the Honolulu Asia Aging Study including 10 with prevalent PD, 25 with prodromal PD, and 25 controls who never developed PD. Various methods were implemented to extract features from ECGs including simple heart rate variability (HRV) metrics, commonly used signal processing methods, and a Probabilistic Symbolic Pattern Recognition (PSPR) method. Extracted features were analyzed via stepwise logistic regression to distinguish between prodromal cases and controls. Stepwise logistic regression selected four features from PSPR as predictors of PD. The final regression model built on the entire dataset provided an area under receiver operating characteristics curve (AUC) with 95% confidence interval of 0.90 [0.80, 0.99]. The five-fold cross-validation process produced an average AUC of 0.835 [0.831, 0.839]. We conclude that cardiac electrical activity provides important information about the likelihood of future PD not captured by classical HRV metrics. Machine learning applied to ECGs may help identify subjects at high risk of having prodromal PD.
Subject(s)
Electrocardiography , Parkinson Disease/diagnosis , Prodromal Symptoms , Aged , Aged, 80 and over , Asian , Case-Control Studies , Disease Progression , Hawaii , Heart Rate , Humans , Logistic Models , Machine Learning , Male , Middle Aged , Parkinson Disease/physiopathology , Pattern Recognition, Automated , Proof of Concept StudyABSTRACT
BACKGROUND: Sickle cell disease (SCD) is a genetic disorder of the red blood cells, resulting in multiple acute and chronic complications, including pain episodes, stroke, and kidney disease. Patients with SCD develop chronic organ dysfunction, which may progress to organ failure during disease exacerbations. Early detection of acute physiological deterioration leading to organ failure is not always attainable. Machine learning techniques that allow for prediction of organ failure may enable early identification and treatment and potentially reduce mortality. OBJECTIVE: The aim of this study was to test the hypothesis that machine learning physiomarkers can predict the development of organ dysfunction in a sample of adult patients with SCD admitted to intensive care units (ICUs). METHODS: We applied diverse machine learning methods, statistical methods, and data visualization techniques to develop classification models to distinguish SCD from controls. RESULTS: We studied 63 sequential SCD patients admitted to ICUs with 163 patient encounters (mean age 30.7 years, SD 9.8 years). A subset of these patient encounters, 22.7% (37/163), met the sequential organ failure assessment criteria. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast Fourier transform, energy, and continuous wavelet transform) derived from heart rate, blood pressure, and respiratory rate was identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure from patients with SCD who did not meet the criteria. A multilayer perceptron model accurately predicted organ failure up to 6 hours before onset, with an average sensitivity and specificity of 96% and 98%, respectively. CONCLUSIONS: This retrospective study demonstrated the viability of using machine learning to predict acute organ failure among hospitalized adults with SCD. The discovery of salient physiomarkers through machine learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.
Subject(s)
Anemia, Sickle Cell/complications , Critical Illness/epidemiology , Early Diagnosis , Machine Learning/standards , Multiple Organ Failure/etiology , Adult , Anemia, Sickle Cell/pathology , Female , Hospitalization , Humans , Intensive Care Units , Male , Multiple Organ Failure/pathology , Retrospective StudiesABSTRACT
Septic shock is a devastating health condition caused by uncontrolled sepsis. Advancements in high-throughput sequencing techniques have increased the number of potential genetic biomarkers under review. Multiple genetic markers and functional pathways play a part in development and progression of pediatric septic shock. We identified 53 differentially expressed pediatric septic shock biomarkers using gene expression data sampled from 181 patients admitted to the pediatric intensive care unit within the first 24 hours of their admission. The gene expression signatures showed discriminatory power between pediatric septic shock survivors and nonsurvivor types. Using functional enrichment analysis of differentially expressed genes, we validated the known genes and pathways in septic shock and identified the unexplored septic shock-related genes and functional groups. Differential gene expression analysis revealed the genes involved in the immune response, chemokine-mediated signaling, neutrophil chemotaxis, and chemokine activity and distinguished the septic shock survivor from non-survivor. The identification of the septic shock gene biomarkers may facilitate in septic shock diagnosis, treatment, and prognosis.
Subject(s)
Shock, Septic/diagnosis , Transcriptome/genetics , Biomarkers/analysis , Child , Child, Preschool , Cohort Studies , Down-Regulation/immunology , Female , Gene Expression Profiling , Humans , Infant , Infant, Newborn , Intensive Care Units, Pediatric/statistics & numerical data , Male , Prognosis , Shock, Septic/genetics , Shock, Septic/immunology , Shock, Septic/mortality , Up-Regulation/immunologyABSTRACT
PURPOSE: Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage. METHODS: A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset. RESULTS: The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset. CONCLUSIONS: The use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.