Victor Castro

Mr. Victor Castro


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2021 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
Chuan HongChuan Hong
Chuan Hong
EREverett Rush
Everett Rush
Molei LiuMolei Liu
Molei Liu
DZDoudou Zhou
Doudou Zhou
JSJiehuan Sun
Jiehuan Sun
VPVa Million Veteran Program
Va Million Veteran Program
The increasing availability of electronic health record (EHR) systems has created enormous potential for translational research. However, it is difficult to know all the relevant codes related to a phenotype due to the large number of codes available. Traditional data mining approaches often require the use of patient-level data, which hinders the ability to share data across institutions. In this project, we demonstrate that multi-center large-scale code embeddings can be used to efficiently identify relevant features related to a disease of interest. We constructed large-scale code embeddings for a wide range of codified concepts from EHRs from two large medical centers. We developed knowledge extraction via sparse embedding regression (KESER) for feature selection and integrative network analysis. We evaluated the quality of the code embeddings and assessed the performance of KESER in feature selection for eight diseases. Besides, we developed an integrated clinical knowledge map combining embedding data from both institutions. The features selected by KESER were comprehensive compared to lists of codified data generated by domain experts. Features identified via KESER resulted in comparable performance to those built upon features selected manually or with patient-level data. The knowledge map created using an integrative analysis identified disease-disease and disease-drug pairs more accurately compared to those identified using single institution data. Analysis of code embeddings via KESER can effectively reveal clinical knowledge and infer relatedness among codified concepts. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data.

21 August 2015 in Neuropsychopharmacology
Verified
Journal Article
Open access
PDF file
VCVictor Castro
Victor Castro
ARAshlee M Roberson
Ashlee M Roberson
TMThomas H McCoy
Thomas H McCoy
AWAnna Wiste
Anna Wiste
ACAndrew Cagan
Andrew Cagan
RPRoy H Perlis
Roy H Perlis
Although lithium preparations remain first-line treatment for bipolar disorder, risk for development of renal insufficiency may discourage their use. Estimating such risk could allow more informed decisions and facilitate development of prevention strategies. We utilized electronic health records from a large New England health-care system between 2006 and 2013 to identify patients aged 18 years or older with a lithium prescription. Renal insufficiency was identified using the presence of renal failure by ICD9 code or laboratory-confirmed glomerular filtration rate below 60 ml/min. Logistic regression was used to build a predictive model in a random two-thirds of the cohort, which was tested in the remaining one-third. Risks associated with aspects of pharmacotherapy were also examined in the full cohort. We identified 1445 adult lithium-treated patients with renal insufficiency, matched by risk set sampling 1 : 3 with 4306 lithium-exposed patients without renal insufficiency. In regression models, features associated with risk included older age, female sex, history of smoking, history of hypertension, overall burden of medical comorbidity, and diagnosis of schizophrenia or schizoaffective disorder (p<0.01 for all contrasts). The model yielded an area under the ROC curve exceeding 0.81 in an independent testing set, with 74% of renal insufficiency cases among the top two risk quintiles. Use of lithium more than once daily, lithium levels greater than 0.6 mEq/l, and use of first-generation antipsychotics were independently associated with risk. These results suggest the possibility of stratifying risk for renal failure among lithium-treated patients. Once-daily lithium dosing and maintaining lower lithium levels where possible may represent strategies for reducing risk.

Verified
Journal Article
Open access
PDF file
NBNatalie Boutin
Natalie Boutin
KMKathleen Mathieu
Kathleen Mathieu
AHAlison G. Hoffnagle
Alison G. Hoffnagle
NANicole Allen
Nicole Allen
VCVictor Castro
Victor Castro
JSJordan Smoller
Jordan Smoller
The purpose of this study is to characterize the potential benefits and challenges of electronic informed consent (eIC) as a strategy for rapidly expanding the reach of large biobanks while reducing costs and potentially enhancing participant engagement. The Partners HealthCare Biobank (Partners Biobank) implemented eIC tools and processes to complement traditional recruitment strategies in June 2014. Since then, the Partners Biobank has rigorously collected and tracked a variety of metrics relating to this novel recruitment method. From June 2014 through January 2016, the Partners Biobank sent email invitations to 184,387 patients at Massachusetts General Hospital and Brigham and Women’s Hospital. During the same time period, 7078 patients provided their consent via eIC. The rate of consent of emailed patients was 3.5%, and the rate of consent of patients who log into the eIC website at Partners Biobank was 30%. Banking of biospecimens linked to electronic health records has become a critical element of genomic research and a foundation for the NIH’s Precision Medicine Initiative (PMI). eIC is a feasible and potentially game-changing strategy for these large research studies that depend on patient recruitment.

26 February 2016 in Journal of Personalized Medicine
Verified
Journal Article
Open access
PDF file
VGVivian Gainer
Vivian Gainer
ACAndrew Cagan
Andrew Cagan
VCVictor Castro
Victor Castro
SDStacey Duey
Stacey Duey
BGBhaswati Ghosh
Bhaswati Ghosh
SMShawn N. Murphy
Shawn N. Murphy
We have designed a Biobank Portal that lets researchers request Biobank samples and genotypic data, query associated electronic health records, and design and download datasets containing de-identified attributes about consented Biobank subjects. This do-it-yourself functionality puts a wide variety and volume of data at the fingertips of investigators, allowing them to create custom datasets for their clinical and genomic research from complex phenotypic data and quickly obtain corresponding samples and genomic data. The Biobank Portal is built upon the i2b2 infrastructure [1] and uses an open-source web client that is available to faculty members and other investigators behind an institutional firewall. Built-in privacy measures [2] ensure that the data in the Portal are utilized only according to the processes to which the patients have given consent.

29 October 2015 in Reproductive Biology and Endocrinology
Verified
Journal Article
Open access
PDF file
VCVictor Castro
Victor Castro
YSYuanyuan Shen
Yuanyuan Shen
SYSheng Yu
Sheng Yu
SFSean Finan
Sean Finan
CPCindy Ta Pau
Cindy Ta Pau
CWCorrine K. Welt
Corrine K. Welt
Polycystic ovary syndrome (PCOS) is a heterogeneous disorder because of the variable criteria used for diagnosis. Therefore, International Classification of Diseases 9 (ICD-9) codes may not accurately capture the diagnostic criteria necessary for large scale PCOS identification. We hypothesized that use of electronic medical records text and data would more specifically capture PCOS subjects. Subjects with PCOS were identified in the Partners Healthcare Research Patients Data Registry by searching for the term “polycystic ovary syndrome” using natural language processing (n = 24,930). A training subset of 199 identified charts was reviewed and categorized based on likelihood of a true Rotterdam PCOS diagnosis, i.e. two out of three of the following: irregular menstrual cycles, hyperandrogenism and/or polycystic ovary morphology. Data from the history, physical exam, laboratory and radiology results were codified and extracted from notes of definite PCOS subjects. Thirty-two terms were used to build an algorithm for identifying definite PCOS cases and applied to the rest of the dataset. The positive predictive value cutoff was set at 76.8 % to maximize the number of subjects available for study. A true positive predictive value for the algorithm was calculated after review of 100 charts from subjects identified as definite PCOS cases with at least two documented Rotterdam criteria. The positive predictive value was compared to that calculated using 200 charts identified using the ICD-9 code for PCOS (256.4; n = 13,670). In addition, a cohort of previously recruited PCOS subjects was submitted for algorithm validation. Chart review demonstrated that 64 % were confirmed as definitely PCOS using the algorithm, with a 9 % false positive rate. 66 % of subjects identified by ICD-9 code for PCOS could be confirmed as definitely PCOS, with an 8.5 % false positive rate. There was no significant difference in the positive predictive values using the two methods (p = 0.2). However, the number of charts that had insufficient confirmatory data was lower using the algorithm (5 % vs 11 %; p < 0.04). Of 477 subjects with PCOS recruited and examined individually and present in the database as patients, 451 were found within the algorithm dataset. Extraction of text parameters along with codified data improves the confidence in PCOS patient cohorts identified using the electronic medical record. However, the positive predictive value was not significantly different when using ICD-9 codes or the specific algorithm. Further studies are needed to determine the positive predictive value of the two methods in additional electronic medical record datasets.

21 July 2022 in Journal of Biomedical Informatics
Verified
Journal Article
Open access
DZDoudou Zhou
Doudou Zhou
ZGZiming Gan
Ziming Gan
XSXu Shi
Xu Shi
APAlina Patwari
Alina Patwari
EREverett Rush
Everett Rush
TCTianxi Cai
Tianxi Cai
The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.