scholarly journals PRM222 - STUDY OF THE SEVERITY OF VASO-OCCLUSIVE CRISIS FOR PATIENT SUFFERING FROM SICKLE CELL DISEASE IN FRANCE USING A MACHINE LEARNING APPROACH ON THE FRENCH MEDICAL INFORMATION SYSTEM DATABASE

2018 ◽  
Vol 21 ◽  
pp. S394
Author(s):  
E Duteil ◽  
R Lorenzi ◽  
A Pagniez ◽  
L Lamarsalle
2019 ◽  
Author(s):  
Akram Mohammed ◽  
Pradeep S. B. Podila ◽  
Robert L. Davis ◽  
Kenneth I. Ataga ◽  
Jane S. Hankins ◽  
...  

AbstractBackgroundSickle 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 earlier identification and treatment, and potentially reduce mortality. We tested the hypothesis that machine learning physiomarkers could predict the development of organ dysfunction in an adult sample of patients with SCD admitted to intensive care units.Methods and FindingsWe studied 63 sequential SCD patients with 163 patient encounters, mean age 33.0±11.0 years, admitted to intensive care units, some of whom (6.7%) had pre-existing cardiovascular or kidney disease. A subset of these patient encounters (37; 23%) met sequential organ failure assessment (SOFA) criteria. The site of organ failure included: central nervous system (32), cardiovascular (11), renal (10), liver (7), respiratory (5) and coagulation (2) systems. Most (81.5%) of the patient encounters who experienced organ failure had single organ failure. The other 126 SCD patient encounters served as controls. A set of signal processing features (such as fast fourier transform, energy, continuous wavelet transform, etc.) derived from heart rate, blood pressure, and respiratory rate were identified to distinguish patients with SCD who developed acute physiological deterioration leading to organ failure, from SCD patients who did not meet the criteria. A random forest model accurately predicted organ failure up to six hours prior to onset, with a five-fold cross-validation accuracy of 94.57% (average sensitivity and specificity of 90.24% and 98.9% respectively).ConclusionsThis study demonstrates the viability of using machine learning to predict acute physiological deterioration heralded 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.


2020 ◽  
Vol 192 (1) ◽  
pp. 158-170
Author(s):  
Arisha Patel ◽  
Kyra Gan ◽  
Andrew A. Li ◽  
Jeremy Weiss ◽  
Mehdi Nouraie ◽  
...  

Blood ◽  
2013 ◽  
Vol 122 (21) ◽  
pp. 1698-1698 ◽  
Author(s):  
Ram Kalpatthi ◽  
Brian R Lee ◽  
Gerald M Woods ◽  
Jignesh Dalal

Abstract Background Priapism is a known but largely understudied complication of sickle cell disease (SCD). The epidemiology of priapism in children and adolescents with SCD is not well characterized especially the pattern of hospitalization. Data are scarce about the role of blood transfusion and surgical therapies in the management of priapism in SCD. Recent expert opinion questions the efficacy of blood transfusion and recommends early urological interventions in these patients (Merritt et al. Can J Emerg Med 2006, Kato GJ. J Sex Med. 2012). As hospitalization consumes lots of economic resources, we studied the trend and outcome of hospitalization for priapism in children with SCD over the last decade. Methods We used the Pediatric Health Information System (PHIS), an electronic database of children's hospitals in the US. Patients ≤ 21 years of age with SCD from 33 hospitals from 2000-2011 were analyzed. SCD, priapism and all related conditions were identified by ICD-9 codes. We examined patient demographics, timing of hospitalizations, treatment details, RBC transfusion (simple and exchange transfusion), and urologic procedures (including aspiration and irrigation of corpus cavernosum, corpora cavernosa-corpus spongiosum shunt and corpora-saphenous shunt) and hospital charges. With the inherent skewness of the length of stay and cost data, we used non-parametric analysis when comparing summary statistics. Given the level of over-dispersion, a negative binomial model was used to determine adjusted length of stay and cost. A p-value <.05 was considered statistically significant. Results From 2000 to 2011, there were 7929 unique male pediatric patients with SCD identified. Among these 465 (5.9%) patients had a diagnosis of priapism and accounted for 1069 priapism related hospitalizations. Overall, the number of new sickle cell patients with priapism getting hospitalized remained stable (Figure 1A). The demographic and baseline characteristics of these patients are shown in Figure 1B. In 63% (673/1069) of the priapism related hospitalizations, patients received conservative treatment whereas blood transfusion, urologic procedures or both were performed in 25.2% (269/1069), 6.6% (71/1069) and 5.2% (56/1069) of the hospitalizations respectively. Five percent (51/1069) of priapism related hospitalizations required ICU care, 1% (15/1069) required mechanical ventilation and there was no in-hospital mortality. Average length of stay for priapism related hospitalization was 3.8 days. Multivariate regression analysis showed that the presence of VOC, ACS, blood transfusion, and urologic procedures were independently associated with increased length of stay and costs (Table 1). Multivariate analysis showed neither transfusion nor urologic procedures were associated with neurological complications observed during priapism related hospitalizations. Conclusions In our largest pediatric in-patient sickle cell cohort, the prevalence of priapism was 5.9%. New inpatient diagnoses of priapism among children with SCD remained constant overtime as previously reported in adult SCD population (Chrouser et al. Am J Surg 2011). Majority of our patients received conservative treatment and urologic procedures were utilized infrequently, again consistent with adult literature. Both blood transfusion and urologic procedures were associated with increased length of stay and costs but not with neurological complications. There is a strong need for prospective, multi-institutional trials to define the role of blood transfusions, surgical procedures and other novel therapies to improve the outcome. Disclosures: No relevant conflicts of interest to declare.


2016 ◽  
Vol 19 (7) ◽  
pp. A412
Author(s):  
Y Yazdanpanah ◽  
F Bonnet ◽  
L de Léotoing ◽  
L Finkielsztejn ◽  
G Chaize ◽  
...  

Author(s):  
Eliseos J. Mucaki ◽  
Ben C. Shirley ◽  
Peter K. Rogan

AbstractPurposeCombinations of expressed genes can discriminate radiation-exposed from normal control blood samples by machine learning based signatures (with 8 to 20% misclassification rates). These signatures can quantify therapeutically-relevant as well as accidental radiation exposures. The prodromal symptoms of Acute Radiation Syndrome (ARS) overlap some viral infections. We recently showed that these human radiation signatures produced unexpected false positive misclassification of Influenza and Dengue infected samples. The present study investigates these and other confounders, and then mitigates their effects on signature accuracy.MethodsThis study investigated recall by previous and novel radiation signatures independently derived from multiple Gene Expression Omnibus datasets on common and rare non-malignant blood disorders and blood-borne infections (thromboembolism, S. aureus bacteremia, malaria, sickle cell disease, polycythemia vera, and aplastic anemia). Normalized expression levels of signature genes are used as input to machine learning-based classifiers to predict radiation exposure in other hematological conditions.ResultsExcept for aplastic anemia, these blood-borne disorders modify the normal baseline expression values of genes present in radiation signatures, leading to false-positive misclassification of radiation exposures in 8 to 54% of individuals. Shared changes, predominantly in DNA damage response and apoptosis-related gene transcripts in radiation and confounding hematological conditions, compromise the utility of these signatures for radiation assessment. These confounding conditions (sickle cell disease, thromboembolism, S. aureus bacteremia, malaria) induce neutrophil extracellular traps, initiated by chromatin decondensation, DNA damage response and fragmentation followed by programmed cell death. Riboviral infections (for example, Influenza, Dengue fever) are proposed to deplete RNA binding proteins, inducing R-loops in chromatin which collide with replication forks resulting in DNA damage, and apoptosis. To mitigate the effects of confounders, we evaluated predicted radiation positive samples with novel gene expression signatures derived from radiation-responsive transcripts encoding secreted blood plasma proteins whose expression levels are unperturbed by these conditions.ConclusionsThis approach identifies and eliminates misclassified samples with underlying hematological or infectious conditions, leaving only samples with true radiation exposures. Diagnostic accuracy is significantly improved by selecting genes that maximize both sensitivity and specificity in the appropriate tissue using combinations of the best signatures for each of these classes of signatures.


Sign in / Sign up

Export Citation Format

Share Document