Objective Phenotyping patients using electronic health record (EHR) data conventionally requires labeled cases and controls. Assigning labels requires manual medical chart review and therefore is labor intensive. For some phenotypes, identifying gold-standard controls is prohibitive. We developed an accurate EHR phenotyping approach that does not require labeled controls. Materials and Methods Our framework relies on a random subset of cases, which can be specified using an anchor variable that has excellent positive predictive value and sensitivity independent of predictors. We proposed a maximum likelihood approach that efficiently leverages data from the specified cases and unlabeled patients to develop logistic regression phenotyping models, and compare model performance with existing algorithms. Results Our method outperformed the existing algorithms on predictive accuracy in Monte Carlo simulation studies, application to identify hypertension patients with hypokalemia requiring oral supplementation using a simulated anchor, and application to identify primary aldosteronism patients using real-world cases and anchor variables. Our method additionally generated consistent estimates of 2 important parameters, phenotype prevalence and the proportion of true cases that are labeled. Discussion Upon identification of an anchor variable that is scalable and transferable to different practices, our approach should facilitate development of scalable, transferable, and practice-specific phenotyping models. Conclusions Our proposed approach enables accurate semiautomated EHR phenotyping with minimal manual labeling and therefore should greatly facilitate EHR clinical decision support and research.
Introduction: Apparent treatment resistant hypertension (aTRH) affects 10-20% of hypertensive adults and increases risk of cardiovascular events and mortality. Fewer than half of these patients have true resistant hypertension. The majority experience pseudo-resistant hypertension due to inadequate medication adherence, white coat hypertension, and secondary causes of hypertension. We hypothesize that electronic health records can be leveraged to identify aTRH patients who would benefit from targeted counseling, medication reconciliation, and screening for secondary causes of hypertension. Methods: We studied electronic health record (EHR) data from 395 hypertensive adults in our primary care population who received longitudinal care between 2007 and 2017. Patients who met the 2008 AHA definition of resistant hypertension by chart review were considered to have aTRH. We also included 100 patients identified by heuristics targeting secondary hypertension. We extracted from the EHR demographics, vitals, laboratory results, diagnosis codes, and medications. Results outside of physiologic range were excluded and median imputation was used to handle missing data. Random forest model performance was assessed by 5-fold cross validation. Model discrimination was evaluated at an estimated positive predictive value of 75%. Results: The prevalence of aTRH in our randomly selected and full cohorts was 20.3% (n=295) and 25.8% (n=395), respectively. In cross-validation, the random forest model demonstrated a median sensitivity of 65% (IQR: 60% - 65%) and a median AUROC of 0.92 (IQR: 0.90 - 0.92). The most influential variables were related to the prescription of three or more hypertension medications; number of days on diuretics, angiotensin-converting enzyme inhibitors, or angiotensin II receptor blockers; systolic blood pressure measurements; and hypertension or diabetes diagnosis codes. Conclusion: EHR data can be used to accurately identify patients with aTRH. We expect the implementation of a clinical decision support system leveraging such models could lead to the improved care for aTRH patients.
ObjectiveElectronic health records (EHRs) can improve patient care by enabling systematic identification of patients for targeted decision support. But, this requires scalable learning of computable phenotypes. To this end, we developed the feature engineering automation tool (FEAT) and assessed it in targeting screening for the under-diagnosed, under-treated disease primary aldosteronism.Materials and MethodsWe selected 1199 subjects receiving longitudinal care in one health system between 2007 and 2017 and classified them for hypertension (N=608), hypertension with unexplained hypokalemia (N=172), and apparent treatment-resistant hypertension (N=176) by chart review. We derived 331 features from EHR encounters, diagnoses, laboratories, medications, vitals, and notes. We modified FEAT to encourage model parsimony and compared its models’ performance and interpretability to that of expert-curated heuristics and conventional machine learning.ResultsFEAT models trained to replicate expert-curated heuristics had higher AUPRC scores than all other models (p < 0.001) except random forests and were smaller than all other models (p < 1e-6) except decision trees. FEAT models trained to predict chart review phenotypes exhibited similar AUPRC scores to penalized logistic regression while being substantially simpler than all other models (p < 1e-6). For treatment-resistant hypertension, FEAT learned a six-feature, clinically intuitive model that demonstrated an adjusted PPV of 0.73 and sensitivity of 0.54 in testing.DiscussionFEAT learns computable phenotypes that approach the performance of expert-curated heuristics and conventional machine learning without sacrificing interpretability.ConclusionBy constructing accurate and interpretable computable phenotypes at scale, FEAT has the potential to facilitate widespread, systematic clinical decision support.
Machine learning (ML) models trained for triggering clinical decision support (CDS) are typically either accurate or interpretable but not both. Scaling CDS to the panoply of clinical use cases while mitigating risks to patients will require many ML models be intuitively interpretable for clinicians. To this end, we adapted a symbolic regression method, coined the feature engineering automation tool (FEAT), to train concise and accurate models from high-dimensional electronic health record (EHR) data. We first present an in-depth application of FEAT to classify hypertension, hypertension with unexplained hypokalemia, and apparent treatment-resistant hypertension (aTRH) using EHR data for 1200 subjects receiving longitudinal care in a large healthcare system. FEAT models trained to predict phenotypes adjudicated by chart review had equivalent or higher discriminative performance (p < 0.001) and were at least three times smaller (p < 1 × 10−6) than other potentially interpretable models. For aTRH, FEAT generated a six-feature, highly discriminative (positive predictive value = 0.70, sensitivity = 0.62), and clinically intuitive model. To assess the generalizability of the approach, we tested FEAT on 25 benchmark clinical phenotyping tasks using the MIMIC-III critical care database. Under comparable dimensionality constraints, FEAT’s models exhibited higher area under the receiver-operating curve scores than penalized linear models across tasks (p < 6 × 10−6). In summary, FEAT can train EHR prediction models that are both intuitively interpretable and accurate, which should facilitate safe and effective scaling of ML-triggered CDS to the panoply of potential clinical use cases and healthcare practices.
Less than 10 mm port-site herniation is a rare complication after laparoscopic surgery. We report a case of complicated herniation through the 5-mm suprapubic trocar port site. CASE REPORT: A 58-year old obese male was admitted due to intestinal obstruction. He has undergone the laparoscopic appendicectomy 1 year ago. On examination, abdomen was bloated and roughly 10 cm size mass was palpable on the suprapubic area. Plane radiogram of the abdomen showed signs of intestinal obstruction. Since conservative treatment was ineffective, the patient was operated on. The laparotomy revealed a protrusion of a part of right large intestine and greater omentum into the subcutaneous space through the abdominal wall defect. There was a dilatation of intestines proximally incarcerated colon. It was released and a part of omentum was resected. The peritoneum and fascia-muscular defect was closed by interrupted vicryl sutures. CONCLUSION: Acute herniation through a 5 mm size most lateral trocar port site is a rare complication of laparoscopic surgery requiring prompt differential diagnosis.
62yr old female, known diabetic and hypertension, Post CABG presented with hard, mobile, swelling of size 2×3 cm in upper outer quadrant with Right axillary lymph node enlargement size 1×1 cm diagnosed as Right breast cancer with lymph node enlargement. FNAC of Swelling over right breast shows smear positive for malignancy, Ductal carcinoma of Right breast
Although deferasirox use is established in clinical practice for iron overload, there have been a spate of case reports describing hematologic improvement attributed to use of this agent in myelodysplastic syndrome (MDS) patients (Guariglia et al, Leuk Res, 2011, 35 (5), 566-570). In addition, a post-hoc analysis was conducted assessing hematologic improvement in patients enrolled on the Evaluation of Patients' Iron Chelation with Exjade (EPIC) trial of deferasirox chelation therapy in low or intermediate-1 risk MDS. Erythroid, platelet, and neutrophil responses were observed in 21.5%, 13.0%, and 22.0% of 341 patients after a median of 109, 169, and 226 days, respectively (Gattermann, N et al, Haematologica, 2012, 97 (9), 1364-1371). There has even been a case report of a patient with acute monocytic leukemia who achieved a complete remission after deferasirox therapy (Fukushima et al, Anticancer Res, 2011, 31 (5) 1741-1744). Preclinical data has suggested potential mechanisms for hematologic improvement, including modulation of reactive oxygen species and activating the MAP kinase pathway (Callens et al, J Exp Med, 2010, 37 (4), 731-750), increased labile plasma iron leading to reactive oxygen species induction (Naka K et al, Antiox Redox Signal, 2008, 10 (11) 1883-1894), or inhibition of nuclear factor Kappa B (Messa et al, Haematologica, 95 (8) 1308-1316). Given these intriguing findings, we performed a single-center, investigator-initiated pilot study of deferasirox in MDS International Prognostic Scoring System (IPSS) 1.5 or greater, intolerant of or with lack of response to hypomethylating agents, and acute myeloid leukemia (AML), either relapsed or refractory after treatment with a non-intensive regimen or newly diagnosed and not appropriate candidates for induction chemotherapy. As an inclusion criterion, baseline serum ferritin was > or = to 500 ng/mL. Prior therapy with iron chelating agents within the last 6 months was an exclusion criterion. Current therapy for AML or MDS, including hydroxyurea to control leukocytosis, was prohibited. Thirteen patients consented to the study. There was one screen failure and one patient withdrew from the study after one day. Eleven patients received deferasirox at an initial dose of 10 mg/kg/day which was increased to 20 mg/kg/day if tolerating well. Three of 11 patients (27%) responded. One of the three responding patients achieved red blood cell (RBC) transfusion independence (no RBC transfusions for 6 weeks before death related to infectious complications), one improved bone marrow blasts from 57% to 30% after one month of therapy and the third patient improved bone marrow blasts from 13% to 8% after one month of therapy. The patient who achieved RBC transfusion independence did not achieve any other measures of response. The two patients who responded in the bone marrow did not achieve a concomitant hematologic response. Of the 8 non-responding patients, one patient had stable disease and was on study for one year. One patient withdrew in the setting of neutropenic fever and mild transaminitis that was possibly attributable to deferasirox and was terminated from the study. One patient withdrew from the study due to personal choice and the remaining 5 patients came off study in the setting of complications from progressive disease. Study drug was generally well tolerated. Grade 3 adverse events (AEs) included three patients with elevated creatinine (27%) and 2 patients with diarrhea (18%). One responding patient had a lower gastrointestinal bleed that was possibly attributable to deferasirox and was terminated from the study for this reason. One patient had grade 4 dry mouth immediately after drinking deferasirox slurry that resolved by 30 minutes after ingestion. No other significant AEs occurred that were possibly attributable to deferasirox. In conclusion, deferasirox was generally well tolerated and showed modest activity as a single agent in higher risk MDS or non-proliferative acute myeloid leukemia. Further study of deferasirox in the phase II setting as monotherapy or in combination with other therapies such as hypomethylating agents (HMAs) or HMAs in combination with venetoclax is probably warranted. Disclosures Frey: Novartis: Research Funding. Carroll:Astellas Pharmaceuticals: Research Funding; Incyte: Research Funding; Janssen Pharmaceuticals: Consultancy. Luger:Agios: Honoraria; Ariad: Research Funding; Biosight: Research Funding; Celgene: Research Funding; Cyslacel: Research Funding; Daichi Sankyo: Honoraria; Genetech: Research Funding; Jazz: Honoraria; Kura: Research Funding; Onconova: Research Funding; Pfizer: Honoraria; Seattle Genetics: Research Funding. OffLabel Disclosure: Presentation will discuss the off-label use of Exjade (deferasirox) as therapy for higher risk MDS or AML. Deferasirox on-label use is for iron chelation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.