scholarly journals Machine learning–based prediction of health outcomes in pediatric organ transplantation recipients

JAMIA Open ◽  
2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Michael O Killian ◽  
Seyedeh Neelufar Payrovnaziri ◽  
Dipankar Gupta ◽  
Dev Desai ◽  
Zhe He
Keyword(s):  
Machine Learning ◽  
Health Outcomes ◽  
Outcomes Research ◽  
Characteristic Curve ◽  
Organ Transplant ◽  
Support Vector ◽  
Solid Organ ◽  
Post Transplant ◽  
Transplant Outcomes ◽  
Pediatric Transplantation

Abstract Objectives Prediction of post-transplant health outcomes and identification of key factors remain important issues for pediatric transplant teams and researchers. Outcomes research has generally relied on general linear modeling or similar techniques offering limited predictive validity. Thus far, data-driven modeling and machine learning (ML) approaches have had limited application and success in pediatric transplant outcomes research. The purpose of the current study was to examine ML models predicting post-transplant hospitalization in a sample of pediatric kidney, liver, and heart transplant recipients from a large solid organ transplant program. Materials and Methods Various logistic regression, naive Bayes, support vector machine, and deep learning (DL) methods were used to predict 1-, 3-, and 5-year post-transplant hospitalization using patient and administrative data from a large pediatric organ transplant center. Results DL models generally outperformed traditional ML models across organtypes and prediction windows with area under the receiver operating characteristic curve values ranging from 0.750 to 0.851. Shapley additive explanations (SHAP) were used to increase the interpretability of DL model results. Various medical, patient, and social variables were identified as salient predictors across organ types. Discussion Results demonstrate the utility of DL modeling for health outcome prediction with pediatric patients, and its use represents an important development in the prediction of post-transplant outcomes in pediatric transplantation compared to prior research. Conclusion Results point to DL models as potentially useful tools in decision-support systems assisting physicians and transplant teams in identifying patients at a greater risk for poor post-transplant outcomes.

#74: Development of a Solid-Organ Transplant-Specific Antibiogram in a Tertiary Pediatric Hospital in Canada

2021 ◽  
Vol 10 (Supplement_1) ◽  
pp. S1-S1
Author(s):  
T Kitano ◽  
M Science ◽  
N Nalli ◽  
K Timberlake ◽  
U Allen ◽  
...  
Keyword(s):  
Treatment Guidelines ◽  
Organ Transplant ◽  
Solid Organ Transplant ◽  
Lower Sensitivity ◽  
Solid Organ ◽  
Pediatric Hospital ◽  
Post Transplant ◽  
Significant Difference ◽  
Organ Specific ◽  
Wide Population

Abstract Background Solid-organ transplant (SOT) patients are more vulnerable to infections by antimicrobial-resistant organisms (AROs) because of their hospital exposure, compromised immune systems, and antimicrobial exposure. Therefore, it may be useful for transplant facilities to create transplant-specific antibiograms to direct empirical antimicrobial regimens and monitor trends in antimicrobial resistance. Methods SOT (i.e., lung, liver, renal, and heart) antibiograms were created using antimicrobial susceptibility data on isolates from 2012 to 2018 at The Hospital for Sick Children, a tertiary pediatric hospital and transplant center in Toronto, Ontario. The Clinical Laboratory Standards Institute (CLSI) guidelines were followed to generate the antibiograms. The first clinical isolate of a species from a patient in each year was included irrespective of body site; duplicates were eliminated and surveillance cultures were excluded. Results from 2 years of data were pooled on a rolling basis to achieve an adequate sample size in both SOT and hospital-wide antibiogram. The SOT antibiogram was then compared with the hospital-wide antibiogram of the compatible 2 pooled years from 2012 to 2018. For subgroup analyses in the SOT population, organ-specific antibiograms and transplant timing-specific antibiograms (pretransplant, post-transplant <1 year, and post-transplant ≥1 year) between transplant and sample collection dates were analyzed. All proportions were compared using the χ 2 test. Results The top 5 organisms in one (2 year) analysis period of the SOT antibiogram were Escherichia coli (n = 29), Staphylococcus aureus (n = 28), Pseudomonas aeruginosa (n = 20), Enterobacter cloacae complex (n = 18), and Klebsiella pneumoniae (n = 17). For E.coli, susceptibility in the SOT antibiogram was significantly lower than those in the hospital-wide antibiogram in 2017/2018 for ampicillin (27% vs. 48%; P = 0.015), piperacillin/tazobactam (55% vs. 87%; P < 0.001), cefotaxime (59% vs. 88%; P < 0.001), ciprofloxacin (71% vs. 87%; P = 0.007) and cotrimoxazole (41% vs. 69%; P < 0.001), but not significantly different for gentamicin (94% vs. 91%; P = 0.490), tobramycin (88% vs. 90%; P = 0.701) and amikacin (100% vs. 99%; P = 0.558). These findings were consistent throughout the study period in E.coli. There was no statistically significant difference between the SOT and hospital-wide antibiograms for other organisms. There were no significant differences in susceptibility between organ-specific antibiograms or transplant timing-specific antibiograms in 2012–2018. Conclusions We found that E.coli from the SOT population had a significantly lower sensitivity to all antimicrobials, except aminoglycosides, compared with those from the hospital-wide population. Other organisms had similar susceptibility to the hospital-wide population. Developing a SOT antibiogram will assist in revising and improving empiric treatment guidelines for this population.

scholarly journals Does Post-Transplant Cytomegalovirus Increase the Risk of Invasive Aspergillosis in Solid Organ Transplant Recipients? A Systematic Review and Meta-Analysis

2021 ◽  
Vol 7 (5) ◽  
pp. 327
Author(s):  
Nipat Chuleerarux ◽  
Achitpol Thongkam ◽  
Kasama Manothummetha ◽  
Saman Nematollahi ◽  
Veronica Dioverti-Prono ◽  
...  
Keyword(s):  
Systematic Review ◽  
Invasive Aspergillosis ◽  
Meta Analysis ◽  
Organ Transplant ◽  
Solid Organ Transplant ◽  
Effect Estimate ◽  
Solid Organ ◽  
Post Transplant ◽  
Cmv Disease ◽  
The Impact

Background: Cytomegalovirus (CMV) and invasive aspergillosis (IA) cause high morbidity and mortality in solid organ transplant (SOT) recipients. There are conflicting data with respect to the impact of CMV on IA development in SOT recipients. Methods: A literature search was conducted from existence through to 2 April 2021 using MEDLINE, Embase, and ISI Web of Science databases. This review contained observational studies including cross-sectional, prospective cohort, retrospective cohort, and case-control studies that reported SOT recipients with post-transplant CMV (exposure) and without post-transplant CMV (non-exposure) who developed or did not develop subsequent IA. A random-effects model was used to calculate the pooled effect estimate. Results: A total of 16 studies were included for systematic review and meta-analysis. There were 5437 SOT patients included in the study, with 449 SOT recipients developing post-transplant IA. Post-transplant CMV significantly increased the risk of subsequent IA with pORs of 3.31 (2.34, 4.69), I2 = 30%. Subgroup analyses showed that CMV increased the risk of IA development regardless of the study period (before and after 2003), types of organ transplantation (intra-thoracic and intra-abdominal transplantation), and timing after transplant (early vs. late IA development). Further analyses by CMV definitions showed CMV disease/syndrome increased the risk of IA development, but asymptomatic CMV viremia/infection did not increase the risk of IA. Conclusions: Post-transplant CMV, particularly CMV disease/syndrome, significantly increased the risks of IA, which highlights the importance of CMV prevention strategies in SOT recipients. Further studies are needed to understand the impact of programmatic fungal surveillance or antifungal prophylaxis to prevent this fungal-after-viral phenomenon.

scholarly journals Machine learning for identification of surgeries with high risks of cancellation

2018 ◽  
Vol 26 (1) ◽  
pp. 141-155 ◽  
Author(s):  
Li Luo ◽  
Fengyi Zhang ◽  
Yao Yao ◽  
RenRong Gong ◽  
Martina Fu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Predictive Value ◽  
Operating Characteristic ◽  
Sampling Methods ◽  
Characteristic Curve ◽  
Support Vector ◽  
Chi Square ◽  
Stable Performance ◽  
Operating Characteristic Curve

Surgery cancellations waste scarce operative resources and hinder patients’ access to operative services. In this study, the Wilcoxon and chi-square tests were used for predictor selection, and three machine learning models – random forest, support vector machine, and XGBoost – were used for the identification of surgeries with high risks of cancellation. The optimal performances of the identification models were as follows: sensitivity − 0.615; specificity − 0.957; positive predictive value − 0.454; negative predictive value − 0.904; accuracy − 0.647; and area under the receiver operating characteristic curve − 0.682. Of the three models, the random forest model achieved the best performance. Thus, the effective identification of surgeries with high risks of cancellation is feasible with stable performance. Models and sampling methods significantly affect the performance of identification. This study is a new application of machine learning for the identification of surgeries with high risks of cancellation and facilitation of surgery resource management.

scholarly journals COVID-19 and solid organ transplant outcomes

2020 ◽  
Vol 35 (8) ◽  
pp. 1444-1446
Author(s):  
Vinay Nair ◽  
Nicholas Jandovitz ◽  
Kenar D Jhaveri ◽  
Ernesto Molmenti
Keyword(s):  
Organ Transplant ◽  
Solid Organ Transplant ◽  
Solid Organ ◽  
Transplant Outcomes

scholarly journals The role of TGF-β1 gene polymorphisms in the development of post-transplant complications

2021 ◽  
Vol 23 (3) ◽  
pp. 180-185
Author(s):  
R. M. Kurabekova ◽  
O. E. Gichkun ◽  
S. V. Meshcheryakov ◽  
O. P. Shevchenko
Keyword(s):  
Transforming Growth Factor Beta ◽  
Graft Rejection ◽  
Gene Polymorphisms ◽  
Transforming Growth Factor ◽  
Meta Analysis ◽  
Organ Transplant ◽  
Solid Organ ◽  
Post Transplant ◽  
Transplant Complications ◽  
Tgf Β1

Transforming growth factor beta 1 (TGF-β1) is an immunosuppressive and profibrogenic cytokine capable of influencing the development of graft rejection and graft fibrosis in solid organ recipients. The TGF-β gene has a significant polymorphism that may cause individual protein expression levels and be associated with post-organ transplant complications. It is believed that three TGFB1 polymorphic variants (rs1800469, rs1800470 and rs1800471) may be associated with the development of graft rejection, graft fibrosis and chronic dysfunction of a heart, liver or kidney transplant. A review of current literature presents the results of studies on the relationship between TGF-β1 gene polymorphisms and post-transplant complications in solid organ recipients. The findings of various studies of TGF-β1 gene polymorphism in solid organ recipients are not always unambiguous, and their results are often difficult to generalize even with the help of meta-analysis. Samples included in studies vary in terms of ethnicity, gender, age, and underlying medical conditions, while results are highly dependent on sample structure or latent relatedness. Currently available data suggest that TGFB1 polymorphism may determine a predisposition to the development of graft rejection, graft fibrosis and graft dysfunction in solid organ recipients, but this is not conclusive and requires further, larger studies.

scholarly journals Dynamic Detection of Delayed Cerebral Ischemia Using Machine Learning

2020 ◽  
Author(s):  
Murad Megjhani ◽  
Kalijah Terilli ◽  
Ayham Alkhachroum ◽  
David J. Roh ◽  
Sachin Agarwal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cerebral Ischemia ◽  
Characteristic Curve ◽  
Delayed Cerebral Ischemia ◽  
Risk Scores ◽  
Support Vector ◽  
Model Parameters ◽  
Learning Approaches ◽  
Physiologic Data ◽  
Over Time

AbstractObjectiveTo develop a machine learning based tool, using routine vital signs, to assess delayed cerebral ischemia (DCI) risk over time.MethodsIn this retrospective analysis, physiologic data for 540 consecutive acute subarachnoid hemorrhage patients were collected and annotated as part of a prospective observational cohort study between May 2006 and December 2014. Patients were excluded if (i) no physiologic data was available, (ii) they expired prior to the DCI onset window (< post bleed day 3) or (iii) early angiographic vasospasm was detected on admitting angiogram. DCI was prospectively labeled by consensus of treating physicians. Occurrence of DCI was classified using various machine learning approaches including logistic regression, random forest, support vector machine (linear and kernel), and an ensemble classifier, trained on vitals and subject characteristic features. Hourly risk scores were generated as the posterior probability at time t. We performed five-fold nested cross validation to tune the model parameters and to report the accuracy. All classifiers were evaluated for good discrimination using the area under the receiver operating characteristic curve (AU-ROC) and confusion matrices.ResultsOf 310 patients included in our final analysis, 101 (32.6%) patients developed DCI. We achieved maximal classification of 0.81 [0.75-0.82] AU-ROC. We also predicted 74.7 % of all DCI events 12 hours before typical clinical detection with a ratio of 3 true alerts for every 2 false alerts.ConclusionA data-driven machine learning based detection tool offered hourly assessments of DCI risk and incorporated new physiologic information over time.

scholarly journals Predicting lung adenocarcinoma disease progression using methylation-correlated blocks and ensemble machine learning classifiers

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e10884
Author(s):  
Xin Yu ◽  
Qian Yang ◽  
Dong Wang ◽  
Zhaoyang Li ◽  
Nianhang Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Adenocarcinoma ◽  
Cox Regression ◽  
Characteristic Curve ◽  
The Cancer Genome Atlas ◽  
Support Vector ◽  
Survival Prediction ◽  
Ensemble Model ◽  
Training Set ◽  
Cpg Sites

Applying the knowledge that methyltransferases and demethylases can modify adjacent cytosine-phosphorothioate-guanine (CpG) sites in the same DNA strand, we found that combining multiple CpGs into a single block may improve cancer diagnosis. However, survival prediction remains a challenge. In this study, we developed a pipeline named “stacked ensemble of machine learning models for methylation-correlated blocks” (EnMCB) that combined Cox regression, support vector regression (SVR), and elastic-net models to construct signatures based on DNA methylation-correlated blocks for lung adenocarcinoma (LUAD) survival prediction. We used methylation profiles from the Cancer Genome Atlas (TCGA) as the training set, and profiles from the Gene Expression Omnibus (GEO) as validation and testing sets. First, we partitioned the genome into blocks of tightly co-methylated CpG sites, which we termed methylation-correlated blocks (MCBs). After partitioning and feature selection, we observed different diagnostic capacities for predicting patient survival across the models. We combined the multiple models into a single stacking ensemble model. The stacking ensemble model based on the top-ranked block had the area under the receiver operating characteristic curve of 0.622 in the TCGA training set, 0.773 in the validation set, and 0.698 in the testing set. When stratified by clinicopathological risk factors, the risk score predicted by the top-ranked MCB was an independent prognostic factor. Our results showed that our pipeline was a reliable tool that may facilitate MCB selection and survival prediction.

The Impact of Health Literacy and Numeracy on Post-Transplantation Outcomes in Organ Transplant Recipients

2018 ◽  
Author(s):  
Mary Zhu
Keyword(s):  
Health Literacy ◽  
Clinical Outcomes ◽  
Self Efficacy ◽  
Organ Transplant ◽  
Solid Organ ◽  
Transplant Recipients ◽  
Limited Health Literacy ◽  
Health Numeracy ◽  
Post Transplant ◽  
Limited Health

Background: Patients referred for solid organ transplant with limited health literacy have been shown to be less likely to have access to transplantation. We examined the association between health literacy, health numeracy and post-transplant clinical outcomes (i.e. graft failure, non-adherence, readmissions, self-efficacy, or mortality). Methods: A search of Medline for publications during the period January 1946 to July 2016 that examined health literacy, numeracy, and outcomes of transplant recipients. Titles and abstracts were independently examined by three reviewers for exclusion, and the full-text was then reviewed for inclusion. Results: Of 247 citations, 12 met inclusion criteria including one review article and five randomized control trials (RCTs). Health literacy of recipients was measured using Newest Vital Sign (NVS) (n=2),  Short Test of Functional Health Literacy in Adults (STOHFLA) (n=2), Rapid Estimate of Adult Literacy in Medicine (REALM-T) (n=1), and other knowledge questionnaires (n=5). Level of formal education was also examined as an assay of health literacy (n=3). Post-transplant outcomes were assessed through medication adherence (n=4), skin cancer incidence (n=2), graft loss (n=1), recipient mortality (n=1), kidney function (n=1), health-related quality of life (n=1), and self-efficacy (n=1). Eleven citations found limited health literacy to be associated with adverse post-transplant clinical outcomes, and one citation found no association between health literacy and non-adherence. Health numeracy was not studied in any of the citations. Conclusion: Health literacy is negatively associated with adverse post-transplant clinical outcomes. Future studies should analyze the association between health numeracy and clinical outcomes after transplant.

Influenza B Virus Infection in Pediatric Solid Organ Transplant Recipients

PEDIATRICS ◽  
1994 ◽  
Vol 94 (2) ◽  
pp. 225-229
Author(s):  
Teri Jo Mauch ◽  
Tim Myers ◽  
Clifford E. Kashtan ◽  
Susan Bratton ◽  
Elliot Krane ◽  
...  
Keyword(s):  
Virus Infection ◽  
Clinical Symptoms ◽  
Organ Transplant ◽  
Solid Organ Transplant ◽  
Influenza B Virus ◽  
Influenza B ◽  
Solid Organ ◽  
Normal Children ◽  
Post Transplant ◽  
B Virus

Objective. Influenza B virus causes epidemic infection in normal children, but only one case of infection in an immunocompromised solid organ transplant (SOT) recipient has been reported. Characterization of the clinical course of influenza B virus infection in pediatric SOT recipients may increase the utilization of preventive and therapeutic interventions by pediatricians caring for these immunocompromised children. Design. Retrospective chart review of patients whose respiratory viral cultures yielded influenza B from January 1989 through March 1992. Patients. Twelve pediatric SOT recipients with influenza B virus infection were identified. These included five renal, four hepatic, and three cardiac allograft recipients, ranging from 19 months to 17 years 9 months of age (median 6 years 2 months). The post-transplant interval ranged from 6 weeks to 4 years 6 months (average 26.7 months). No patient had been immunized against influenza. Exposure histories were documented for eight children; five of these occurred in the hospital. Results. Clinical symptoms included fever (12/12), respiratory (11/12), or gastrointestinal complaints (8/12). Five patients had neurologic involvement; one died of uncal herniation. Ten children were hospitalized (median duration, 3 days; range, 2 to 79 days). Two patients (post-transplant interval, 3 to 8 months) required mechanical ventilation, and one of these received aerosolized ribavirin. Three children had concurrent allograft rejection. Conclusions. Influenza B infection is potentially life-threatening in pediatric SOT recipients. We recommend annual immunization of pediatric SOT recipients, their household contacts, and health care workers. Prospective studies are needed to evaluate the efficacy of influenza vaccination in pediatric SOT recipients.

Abstract 15895: Machine Learning Algorithms to Predict Major Adverse Cardiovascular Events in Patients Undergoing Orthotopic Liver Transplantation: A Retrospective Cohort Study

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
vardhmaan jain ◽  
Vikram Sharma ◽  
Agam Bansal ◽  
Cerise Kleb ◽  
Chirag Sheth ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Cardiovascular Events ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Major Adverse Cardiovascular Events ◽  
Support Vector ◽  
Post Transplant ◽  
Extreme Gradient Boosting ◽  
All Cause Mortality

Background: Post-transplant major adverse cardiovascular events (MACE) are amongst the leading cause of death amongst orthotopic liver transplant(OLT) recipients. Despite years of guideline directed therapy, there are limited data on predictors of post-OLT MACE. We assessed if machine learning algorithms (MLA) can predict MACE and all-cause mortality in patients undergoing OLT. Methods: We tested three MLA: support vector machine, extreme gradient boosting(XG-Boost) and random forest with traditional logistic regression for prediction of MACE and all-cause mortality on a cohort of consecutive patients undergoing OLT at our center between 2008-2019. The cohort was randomly split into a training (80%) and testing (20%) cohort. Model performance was assessed using c-statistic or AUC. Results: We included 1,459 consecutive patients with mean ± SD age 54.2 ± 13.8 years, 32% female who underwent OLT. There were 199 (13.6%) MACE and 289 (20%) deaths at a mean follow up of 4.56 ± 3.3 years. The random forest MLA was the best performing model for predicting MACE [AUC:0.78, 95% CI: 0.70-0.85] as well as mortality [AUC:0.69, 95% CI: 0.61-0.76], with all models performing better when predicting MACE vs mortality. See Table and Figure. Conclusion: Random forest machine learning algorithms were more predictive and discriminative than traditional regression models for predicting major adverse cardiovascular events and all-cause mortality in patients undergoing OLT. Validation and subsequent incorporation of MLA in clinical decision making for OLT candidacy could help risk stratify patients for post-transplant adverse cardiovascular events.

Sign in / Sign up

Export Citation Format

Share Document