skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia
Title: An Interpretable Machine Learning Framework for Rare Disease: A Case Study to Stratify Infection Risk in Pediatric Leukemia
Background: Datasets on rare diseases, like pediatric acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL), have small sample sizes that hinder machine learning (ML). The objective was to develop an interpretable ML framework to elucidate actionable insights from small tabular rare disease datasets. Methods: The comprehensive framework employed optimized data imputation and sampling, supervised and unsupervised learning, and literature-based discovery (LBD). The framework was deployed to assess treatment-related infection in pediatric AML and ALL. Results: An interpretable decision tree classified the risk of infection as either “high risk” or “low risk” in pediatric ALL (n = 580) and AML (n = 132) with accuracy of ∼79%. Interpretable regression models predicted the discrete number of developed infections with a mean absolute error (MAE) of 2.26 for bacterial infections and an MAE of 1.29 for viral infections. Features that best explained the development of infection were the chemotherapy regimen, cancer cells in the central nervous system at initial diagnosis, chemotherapy course, leukemia type, Down syndrome, race, and National Cancer Institute risk classification. Finally, SemNet 2.0, an open-source LBD software that links relationships from 33+ million PubMed articles, identified additional features for the prediction of infection, like glucose, iron, neutropenia-reducing growth factors, and systemic lupus erythematosus (SLE). Conclusions: The developed ML framework enabled state-of-the-art, interpretable predictions using rare disease tabular datasets. ML model performance baselines were successfully produced to predict infection in pediatric AML and ALL.  more » « less
Award ID(s):
1944247
PAR ID:
10502310
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Journal of Clinical Medicine
Volume:
13
Issue:
6
ISSN:
2077-0383
Page Range / eLocation ID:
1788
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, PLOS ONE)
    Baysal, Mehmet (Ed.)
    Acute myeloid leukemia (AML) is an aggressive and lethal cancer of the blood, which leads to the death of over 11,000 patients in the United States each year. Research on identifying, characterizing, and treating AML is crucial in the fight against this deadly disease. Recent studies have examined the role of CLEC11A in cancer, including AML. However, there have been conflicting reports related to tumor progression and survival. Because survival is based on a variety of factors, including classification of the tumor, genetic risk factors, and demographics, it is imperative that we determine what role CLEC11A may have in cancer survival. Therefore, utilizing data from the Genomic Data Commons, we analyzed CLEC11A methylation in 108 AML patients compared to FAB classification, cytogenetic risk factors, age, race, and gender. Our results show statistically significant correlations between methylation of CLEC11A and FAB classification as well as poor genetic risk factors. However, no difference was observed in CLEC11A methylation when compared to demographic data. Our results, matched with a known biological function of CLEC11A in early hematopoiesis, indicate that CLEC11A may be an important marker for AML diagnosis and prognosis and provide relevant data in the ongoing search for novel therapeutics to improve AML survival. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Cancers)
    Survival of pediatric AML remains poor despite maximized myelosuppressive therapy. The pneumocystis jiroveci pneumonia (PJP)-treating medication atovaquone (AQ) suppresses oxidative phosphorylation (OXPHOS) and reduces AML burden in patient-derived xenograft (PDX) mouse models, making it an ideal concomitant AML therapy. Poor palatability and limited product formulations have historically limited routine use of AQ in pediatric AML patients. Patients with de novo AML were enrolled at two hospitals. Daily AQ at established PJP dosing was combined with standard AML therapy, based on the Medical Research Council backbone. AQ compliance, adverse events (AEs), ease of administration score (scale: 1 (very difficult)-5 (very easy)) and blood/marrow pharmacokinetics (PK) were collected during Induction 1. Correlative studies assessed AQ-induced apoptosis and effects on OXPHOS. PDX models were treated with AQ. A total of 26 patients enrolled (ages 7.2 months–19.7 years, median 12 years); 24 were evaluable. A total of 14 (58%) and 19 (79%) evaluable patients achieved plasma concentrations above the known anti-leukemia concentration (>10 µM) by day 11 and at the end of Induction, respectively. Seven (29%) patients achieved adequate concentrations for PJP prophylaxis (>40 µM). Mean ease of administration score was 3.8. Correlative studies with AQ in patient samples demonstrated robust apoptosis, OXPHOS suppression, and prolonged survival in PDX models. Combining AQ with chemotherapy for AML appears feasible and safe in pediatric patients during Induction 1 and shows single-agent anti-leukemic effects in PDX models. AQ appears to be an ideal concomitant AML therapeutic but may require intra-patient dose adjustment to achieve concentrations sufficient for PJP prophylaxis. 
    more » « less
  3. ; ; ; ; ; ; (, Integrative Biology)
    Abstract The recurrence of cancer following chemotherapy treatment is a major cause of death across solid and hematologic cancers. In B-cell acute lymphoblastic leukemia (B-ALL), relapse after initial chemotherapy treatment leads to poor patient outcomes. Here we test the hypothesis that chemotherapy-treated versus control B-ALL cells can be characterized based on cellular physical phenotypes. To quantify physical phenotypes of chemotherapy-treated leukemia cells, we use cells derived from B-ALL patients that are treated for 7 days with a standard multidrug chemotherapy regimen of vincristine, dexamethasone, and L-asparaginase (VDL). We conduct physical phenotyping of VDL-treated versus control cells by tracking the sequential deformations of single cells as they flow through a series of micron-scale constrictions in a microfluidic device; we call this method Quantitative Cyclical Deformability Cytometry. Using automated image analysis, we extract time-dependent features of deforming cells including cell size and transit time (TT) with single-cell resolution. Our findings show that VDL-treated B-ALL cells have faster TTs and transit velocity than control cells, indicating that VDL-treated cells are more deformable. We then test how effectively physical phenotypes can predict the presence of VDL-treated cells in mixed populations of VDL-treated and control cells using machine learning approaches. We find that TT measurements across a series of sequential constrictions can enhance the classification accuracy of VDL-treated cells in mixed populations using a variety of classifiers. Our findings suggest the predictive power of cell physical phenotyping as a complementary prognostic tool to detect the presence of cells that survive chemotherapy treatment. Ultimately such complementary physical phenotyping approaches could guide treatment strategies and therapeutic interventions. Insight box Cancer cells that survive chemotherapy treatment are major contributors to patient relapse, but the ability to predict recurrence remains a challenge. Here we investigate the physical properties of leukemia cells that survive treatment with chemotherapy drugs by deforming individual cells through a series of micron-scale constrictions in a microfluidic channel. Our findings reveal that leukemia cells that survive chemotherapy treatment are more deformable than control cells. We further show that machine learning algorithms applied to physical phenotyping data can predict the presence of cells that survive chemotherapy treatment in a mixed population. Such an integrated approach using physical phenotyping and machine learning could be valuable to guide patient treatments. 
    more » « less
  4. ; ; ; ; (, Pediatric Transplantation)
    Abstract BackgroundWe hypothesized that alemtuzumab use is safe in pediatric kidney transplant recipients (KTRs) with equivalent long‐term outcomes compared to other induction agents. MethodsUsing pediatric kidney transplant recipient data in the UNOS database between January 1, 2000, and June 30, 2022, multivariate logistic regression, multivariable Cox regression, and survival analyses were utilized to estimate the likelihoods of 1st‐year and all‐time hospitalizations, acute rejection, CMV infection, delayed graft function (DGF), graft loss, and patient mortality among recipients of three common induction regimens (ATG, alemtuzumab, and basiliximab). ResultsThere were no differences in acute rejection or graft failure among induction or maintenance regimens. Basiliximab was associated with lower odds of DGF in deceased donor recipients (OR 0.77 [0.60–0.99],p = .04). Mortality was increased in patients treated with steroid‐containing maintenance (HR 1.3 [1.005–1.7]p = .045). Alemtuzumab induction correlated with less risk of CMV infection than ATG (OR 0.76 [0.59–0.99],p = .039). Steroid‐containing maintenance conferred lower rate of PTLD compared to steroid‐free maintenance (HR 0.59 [0.4–0.8]p = .001). Alemtuzumab was associated with less risk of hospitalization within 1 year (OR 0.79 [0.67–0.95]p = .012) and 5 years (HR 0.54 [0.46–0.65]p < .001) of transplantation. Steroid maintenance also decreased 5 years hospitalization risk (HR 0.78 [0.69–0.89]p < .001). ConclusionsPediatric KTRs may be safely treated with alemtuzumab induction without increased risk of acute rejection, DGF, graft loss, or patient mortality. The decreased risk of CMV infections and lower hospitalization rates compared to other agents make alemtuzumab an attractive choice for induction in pediatric KTRs, especially in those who cannot tolerate ATG. 
    more » « less
  5. ; ; ; (, Journal of Personalized Medicine)
    null (Ed.)
    FLT3-mutant acute myeloid leukemia (AML) is an aggressive form of leukemia with poor prognosis. Treatment with FLT3 inhibitors frequently produces a clinical response, but the disease nevertheless often recurs. Recent studies have revealed system-wide gene expression changes in FLT3-mutant AML cell lines in response to drug treatment. Here we sought a systems-level understanding of how these cells mediate these drug-induced changes. Using RNAseq data from AML cells with an internal tandem duplication FLT3 mutation (FLT3-ITD) under six drug treatment conditions including quizartinib and dexamethasone, we identified seven distinct gene programs representing diverse biological processes involved in AML drug-induced changes. Based on the literature knowledge about genes from these modules, along with public gene regulatory network databases, we constructed a network of FLT3-ITD AML. Applying the BooleaBayes algorithm to this network and the RNAseq data, we created a probabilistic, data-driven dynamical model of acquired resistance to these drugs. Analysis of this model reveals several interventions that may disrupt targeted parts of the system-wide drug response. We anticipate co-targeting these points may result in synergistic treatments that can overcome resistance and prevent eventual recurrence. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email