Search tips
Search criteria

Results 1-4 (4)

Clipboard (0)

Select a Filter Below

Year of Publication
Document Types
1.  Relational Machine Learning for Electronic Health Record-Driven Phenotyping 
Electronic health records (EHR) offer medical and pharmacogenomics research unprecedented opportunities to identify and classify patients at risk. EHRs are collections of highly inter-dependent records that include biological, anatomical, physiological, and behavioral observations. They comprise a patient’s clinical phenome, where each patient has thousands of date-stamped records distributed across many relational tables. Development of EHR computer-based phenotyping algorithms require time and medical insight from clinical experts, who most often can only review a small patient subset representative of the total EHR records, to identify phenotype features. In this research we evaluate whether relational machine learning (ML) using Inductive Logic Programming (ILP) can contribute to addressing these issues as a viable approach for EHR-based phenotyping.
Two relational learning ILP approaches and three well-known WEKA (Waikato Environment for Knowledge Analysis) implementations of non-relational approaches (PART, J48, and JRIP) were used to develop models for nine phenotypes. International Classification of Diseases, Ninth Revision (ICD-9) coded EHR data were used to select training cohorts for the development of each phenotypic model. Accuracy, precision, recall, F-Measure, and Area Under the Receiver Operating Characteristic (AUROC) curve statistics were measured for each phenotypic model based on independent manually verified test cohorts. A two-sided binomial distribution test (sign test) compared the five ML approaches across phenotypes for statistical significance.
We developed an approach to automatically label training examples using ICD-9 diagnosis codes for the ML approaches being evaluated. Nine phenotypic models for each MLapproach were evaluated, resulting in better overall model performance in AUROC using ILP when compared to PART (p=0.039), J48 (p=0.003) and JRIP (p=0.003).
ILP has the potential to improve phenotyping by independently delivering clinically expert interpretable rules for phenotype definitions, or intuitive phenotypes to assist experts.
Relational learning using ILP offers a viable approach to EHR-driven phenotyping.
PMCID: PMC4261015  PMID: 25048351
Machine learning; Electronic health record; Inductive logic programming; Phenotyping; Relational learning
2.  A Pharmacogenetic versus a Clinical Algorithm for Warfarin Dosing 
The New England journal of medicine  2013;369(24):2283-2293.
The clinical utility of genotype-guided (pharmacogenetically based) dosing of warfarin has been tested only in small clinical trials or observational studies, with equivocal results.
We randomly assigned 1015 patients to receive doses of warfarin during the first 5 days of therapy that were determined according to a dosing algorithm that included both clinical variables and genotype data or to one that included clinical variables only. All patients and clinicians were unaware of the dose of warfarin during the first 4 weeks of therapy. The primary outcome was the percentage of time that the international normalized ratio (INR) was in the therapeutic range from day 4 or 5 through day 28 of therapy.
At 4 weeks, the mean percentage of time in the therapeutic range was 45.2% in the genotype-guided group and 45.4% in the clinically guided group (adjusted mean difference, [genotype-guided group minus clinically guided group], −0.2; 95% confidence interval, −3.4 to 3.1; P=0.91). There also was no significant between-group difference among patients with a predicted dose difference between the two algorithms of 1 mg per day or more. There was, however, a significant interaction between dosing strategy and race (P=0.003). Among black patients, the mean percentage of time in the therapeutic range was less in the genotype-guided group than in the clinically guided group. The rates of the combined outcome of any INR of 4 or more, major bleeding, or thromboembolism did not differ significantly according to dosing strategy.
Genotype-guided dosing of warfarin did not improve anticoagulation control during the first 4 weeks of therapy. (Funded by the National Heart, Lung, and Blood Institute and others; COAG number, NCT00839657.)
PMCID: PMC3942158  PMID: 24251361
3.  Pharmacogenetic Warfarin Dose Refinements Remain Significantly Influenced by Genetic Factors after One Week of Therapy 
Thrombosis and Haemostasis  2011;107(2):232-240.
By guiding initial warfarin dose, pharmacogenetic (PGx) algorithms may improve the safety of warfarin initiation. However, once INR response is known, the contribution of PGx to dose refinements is uncertain. This study sought to develop and validate clinical and PGx dosing algorithms for warfarin dose refinement on days 6–11 after therapy initiation.
Materials and Methods
An international sample of 2,022 patients at 13 medical centers on 3 continents provided clinical, INR, and genetic data at treatment days 6–11 to predict therapeutic warfarin dose. Independent derivation and retrospective validation samples were composed by randomly dividing the population (80%/20%). Prior warfarin doses were weighted by their expected effect on S-warfarin concentrations using an exponential-decay pharmacokinetic model. The INR divided by that “effective” dose constituted a treatment response index.
Treatment response index, age, amiodarone, body surface area, warfarin indication, and target INR were associated with dose in the derivation sample. A clinical algorithm based on these factors was remarkably accurate: in the retrospective validation cohort its R2 was 61.2% and median absolute error (MAE) was 5.0 mg/week. Accuracy and safety was confirmed in a prospective cohort (N=43). CYP2C9 variants and VKORC1-1639 G→A were significant dose predictors in both the derivation and validation samples. In the retrospective validation cohort, the PGx algorithm had: R2= 69.1% (P<0.05 vs. clinical algorithm), MAE= 4.7 mg/week.
A pharmacogenetic warfarin dose-refinement algorithm based on clinical, INR, and genetic factors can explain at least 69.1% of therapeutic warfarin dose variability after about one week of therapy.
PMCID: PMC3292349  PMID: 22186998
warfarin; VKORC1; CYP2C9; pharmacogenetic
4.  Necrotizing Fasciitis Due to a Methicillin-Sensitive Staphylococcus aureus Isolate Harboring an Enterotoxin Gene Cluster▿  
Journal of Clinical Microbiology  2006;45(2):668-671.
Benign papular eruption on the left leg of a 72-year-old diabetic man developed into rapidly spreading necrotizing fasciitis despite antimicrobial therapy and surgical debridements. This led to eventual amputation to control the infection. The etiological agent was a Staphylococcus aureus isolate harboring the enterotoxin gene cluster seg, sei, sem, sen, and seo but lacked all common toxin genes, including Panton-Valentine leukocidin.
PMCID: PMC1829043  PMID: 17166962

Results 1-4 (4)