Citations

PURPOSE The Fast Healthcare Interoperability Resources (FHIR) is emerging as a next-generation standards framework developed by HL7 for exchanging electronic health care data. The modeling capability of FHIR in standardizing cancer data has been gaining increasing attention by the cancer research informatics community. However, few studies have been conducted to examine the capability of FHIR in electronic data capture (EDC) applications for effective cancer clinical trials. The objective of this study was to design, develop, and evaluate an FHIR-based method that enables the automation of the case report forms (CRFs) population for cancer clinical trials using real-world electronic health records (EHRs). MATERIALS AND METHODS We developed an FHIR-based computational pipeline of EDC with a case study for modeling colorectal cancer trials. We first leveraged an existing FHIR-based cancer profile to represent EHR data of patients with colorectal cancer, and then we used the FHIR Questionnaire and QuestionnaireResponse resources to represent the CRFs and their data population. To test the accuracy of and overall quality of the computational pipeline, we used synoptic reports of 287 Mayo Clinic patients with colorectal cancer from 2013 to 2019 with standard measures of precision, recall, and F1 score. RESULTS Using the computational pipeline, a total of 1,037 synoptic reports were successfully converted as the instances of the FHIR-based cancer profile. The average accuracy for converting all data elements (excluding tumor perforation) of the cancer profile was 0.99, using 200 randomly selected records. The average F1 score for populating nine questions of the CRFs in a real-world colorectal cancer trial was 0.95, using 100 randomly selected records. CONCLUSION We demonstrated that it is feasible to populate CRFs with EHR data in an automated manner with satisfactory performance. The outcome of the study provides helpful insight into future directions in implementing FHIR-based EDC applications for modern cancer clinical trials.

Background: The focus of most existing phenotyping algorithms based on electronic health record (EHR) data has been to accurately identify cases and non-cases of specific diseases. However, a more challenging task is to accurately identify disease incidence, as identifying the first occurrence of disease is more important for efficient and valid clinical and epidemiological research. Moreover, stroke is a challenging phenotype due to diagnosis difficulty and common miscoding. This task generally requires utilization of multiple types of EHR data (e.g., diagnoses and procedure codes, unstructured clinical notes) and a more robust algorithm integrating both natural language processing and machine learning. In this study, we developed and validated an EHR-based classifier to accurately identify stroke incidence among a cohort of atrial fibrillation (AF) patients Methods: We developed a stroke phenotyping algorithm using International Classification of Diseases, Ninth Revision (ICD-9) codes, Current Procedural Terminology (CPT) codes, and expert-provided keywords as model features. Structured data was extracted from Rochester Epidemiology Project (REP) database. Natural Language Processing (NLP) was used to extract and validate keyword occurrence in clinical notes. A window of ±30 days was considered when including/excluding keywords/codes into the input vector. Frequencies of keywords/codes were used as input feature sets for model training. Multiple competing models were trained using various combinations of feature sets and two machine learning algorithms: logistic regression and random forest. Training data were provided by two nurse abstractors and included validated stroke incidences from a previously established atrial fibrillation cohort. Precision, recall, and F-score of the algorithm were calculated to assess and compare model performances. Results: Among 4,914 patients with atrial fibrillation, 1,773 patients were screened. 3,141 patients had no stroke-related codes or keywords and were presumed to be free of stroke during follow-up. Among the screened patients, 740 had validated strokes and 1,033 did not have a stroke based on review of the EHR by trained nurse abstractors. The best performing stroke incidence phenotyping classifier utilized Keywords+ICD-9+CPT features using a random forest classifier, achieving a precision of 0.942, recall of 0.943, and F-score of 0.943. Conclusion: In conclusion, we developed and validated a stroke algorithm that performed well for identifying stroke incidence in an enriched population (AF cohort), which extends beyond the typical binary case/non-case stroke identification problem. Future work will involve testing the generalizability of this algorithm in a general population.

Introduction The lack of effective, consistent, reproducible and efficient asthma ascertainment methods results in inconsistent asthma cohorts and study results for clinical trials or other studies. We aimed to assess whether application of expert artificial intelligence (AI)-based natural language processing (NLP) algorithms for two existing asthma criteria to electronic health records of a paediatric population systematically identifies childhood asthma and its subgroups with distinctive characteristics. Methods Using the 1997–2007 Olmsted County Birth Cohort, we applied validated NLP algorithms for Predetermined Asthma Criteria (NLP-PAC) as well as Asthma Predictive Index (NLP-API). We categorised subjects into four groups (both criteria positive (NLP-PAC+/NLP-API+); PAC positive only (NLP-PAC+ only); API positive only (NLP-API+ only); and both criteria negative (NLP-PAC−/NLP-API−)) and characterised them. Results were replicated in unsupervised cluster analysis for asthmatics and a random sample of 300 children using laboratory and pulmonary function tests (PFTs). Results Of the 8196 subjects (51% male, 80% white), we identified 1614 (20%), NLP-PAC+/NLP-API+; 954 (12%), NLP-PAC+ only; 105 (1%), NLP-API+ only; and 5523 (67%), NLP-PAC−/NLP-API−. Asthmatic children classified as NLP-PAC+/NLP-API+ showed earlier onset asthma, more Th2-high profile, poorer lung function, higher asthma exacerbation and higher risk of asthma-associated comorbidities compared with other groups. These results were consistent with those based on unsupervised cluster analysis and lab and PFT data of a random sample of study subjects. Conclusion Expert AI-based NLP algorithms for two asthma criteria systematically identify childhood asthma with distinctive characteristics. This approach may improve precision, reproducibility, consistency and efficiency of large-scale clinical studies for asthma and enable population management.

Abstract Objective The study sought to determine the dependence of the Electronic Medical Records and Genomics (eMERGE) rheumatoid arthritis (RA) algorithm on both RA and electronic health record (EHR) duration. Materials and Methods Using a population-based cohort from the Mayo Clinic Biobank, we identified 497 patients with at least 1 RA diagnosis code. RA case status was manually determined using validated criteria for RA. RA duration was defined as time from first RA code to the index date of biobank enrollment. To simulate EHR duration, various years of EHR lookback were applied, starting at the index date and going backward. Model performance was determined by sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve (AUC). Results The eMERGE algorithm performed well in this cohort, with overall sensitivity 53%, specificity 99%, positive predictive value 97%, negative predictive value 74%, and AUC 76%. Among patients with RA duration <2 years, sensitivity and AUC were only 9% and 54%, respectively, but increased to 71% and 85% among patients with RA duration >10 years. Longer EHR lookback also improved model performance up to a threshold of 10 years, in which sensitivity reached 52% and AUC 75%. However, optimal EHR lookback varied by RA duration; an EHR lookback of 3 years was best able to identify recently diagnosed RA cases. Conclusions eMERGE algorithm performance improves with longer RA duration as well as EHR duration up to 10 years, though shorter EHR lookback can improve identification of recently diagnosed RA cases.

Background: Mutations in isocitrate dehydrogenase 1 (IDH1) occur in ~3% of individuals with myelodysplastic syndrome (MDS) and have been associated with increased transformation to acute myeloid leukemia (AML). Ivosidenib (AG-120) is an oral, potent, targeted inhibitor of the mutant isocitrate dehydrogenase 1 enzyme (mIDH1) and is approved in the US for the treatment of newly diagnosed AML with a susceptible IDH1 mutation in patients ≥75 years of age or who have comorbidities that preclude the use of intensive induction chemotherapy, and in adult patients with relapsed or refractory (R/R) AML. The first-in-human, phase 1 dose escalation and expansion study of ivosidenib (NCT02074839) enrolled adults with mIDH1 advanced hematologic malignancies, including R/R MDS, and the study is ongoing. In the initial phase of the study (DiNardo et al. N Engl J Med 2018), the 12 patients with R/R MDS received 500 mg ivosidenib once daily and were characterized as follows: 75% were male, median age was 72.5 years (range 52-78), and 42% were ≥75 years of age; median number of prior therapies was 1 (range 1-3). Adverse events (AEs) of any grade, irrespective of causality, occurring in ≥20% of the 12 patients were diarrhea, fatigue, back pain, rash (n=4 each, 33.3%), anemia, urinary tract infection, decreased appetite, hypokalemia, arthralgia, dyspnea, pruritus, and hypotension (n=3 each, 25.0%). No AEs led to permanent discontinuation of treatment. Response was assessed according to International Working Group 2006 criteria for MDS. According to investigators, five of 12 patients achieved complete remission (CR) (41.7%; 95% CI 15.2%, 72.3%); median duration of CR was not estimable for these patients (95% CI 2.8 months, not estimable). Nine of 12 patients were transfusion independent for at least 56 days during study treatment. Mutation clearance was observed in one of the 5 CR patients. Here we report the design of a new sub-study of this trial, which is being undertaken to further assess the safety, tolerability, and clinical activity of treatment with ivosidenib in patients with R/R MDS. Methods: This sub-study is evaluating the safety, tolerability, pharmacokinetics, pharmacodynamics, and clinical activity of ivosidenib. Adults with R/R MDS with an IDH1 mutation will be enrolled in the MDS sub-study. These individuals must have R/R disease after treatment with standard agents indicated for MDS. Eligible patients must have a platelet count of ≥20,000/μL, and adequate hepatic function (total bilirubin ≤1.5 × upper limit of normal [ULN]; aspartate aminotransferase, alanine aminotransferase, and alkaline phosphatase ≤3.0 × ULN) and renal function (serum creatinine ≤2.0 × ULN or creatinine clearance >40 mL/min). Additional key inclusion criteria are bone marrow blasts >5% and/or transfusion dependence. Ivosidenib is to be administered at a dose of 500 mg once daily orally on Days 1 to 28 of 28-day cycles. The addition of the MDS sub-study to this phase 1 clinical study in patients with hematological malignancies will provide additional insights into the use of ivosidenib for the treatment of mIDH1 R/R MDS. Disclosures Foran: Agios: Honoraria, Research Funding. DiNardo:notable labs: Membership on an entity's Board of Directors or advisory committees; medimmune: Honoraria; daiichi sankyo: Honoraria; abbvie: Consultancy, Honoraria; agios: Consultancy, Honoraria; jazz: Honoraria; celgene: Consultancy, Honoraria; syros: Honoraria. Watts:Takeda: Research Funding; Celgene: Membership on an entity's Board of Directors or advisory committees; Pfizer: Membership on an entity's Board of Directors or advisory committees; Jazz Pharmaceuticals: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau. Stein:Agios: Consultancy, Membership on an entity's Board of Directors or advisory committees; Astellas Pharma US, Inc: Membership on an entity's Board of Directors or advisory committees; Celgene Corporation: Membership on an entity's Board of Directors or advisory committees; Daiichi Sankyo, Inc.: Membership on an entity's Board of Directors or advisory committees; Bioline: Membership on an entity's Board of Directors or advisory committees; Genentech: Membership on an entity's Board of Directors or advisory committees; Novartis: Membership on an entity's Board of Directors or advisory committees; PTC Therapeutics: Membership on an entity's Board of Directors or advisory committees; Syros: Membership on an entity's Board of Directors or advisory committees. De Botton:Daiichi Sankyo: Consultancy; Astellas: Consultancy; Bayer: Consultancy; AbbVie: Consultancy; Syros: Consultancy; Forma: Consultancy, Research Funding; Janssen: Consultancy; Novartis: Consultancy; Pfizer: Consultancy; Servier: Consultancy; Pierre Fabre: Consultancy; Celgene: Consultancy, Speakers Bureau; Agios: Consultancy, Research Funding. Fathi:Amphivena, Kite, Jazz, NewLink Genetics,: Honoraria; Agios, Astellas, Celgene, Daiichi Sankyo, Novartis, Takeda, Amphivena, Kite, Forty Seven,Trovagene, NewLink genetics, Jazz, Abbvie, and PTC Therapeutics: Consultancy. Stein:Stemline: Speakers Bureau; Amgen: Consultancy, Speakers Bureau; Celgene: Speakers Bureau. Stone:AbbVie, Actinium, Agios, Argenx, Arog, Astellas, AstraZeneca, Biolinerx, Celgene, Cornerstone Biopharma, Fujifilm, Jazz Pharmaceuticals, Amgen, Ono, Orsenix, Otsuka, Merck, Novartis, Pfizer, Sumitomo, Trovagene: Consultancy; Argenx, Celgene, Takeda Oncology: Other: Data and Safety Monitoring Board/Committee: ; Novartis, Agios, Arog: Research Funding. Patel:France Foundation: Honoraria; Celgene: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Dava Oncology: Honoraria. Tallman:UpToDate: Patents & Royalties; Daiichi-Sankyo: Consultancy, Membership on an entity's Board of Directors or advisory committees; BioLineRx: Consultancy, Membership on an entity's Board of Directors or advisory committees; Rigel: Consultancy, Membership on an entity's Board of Directors or advisory committees; Jazz Pharmaceuticals: Consultancy, Membership on an entity's Board of Directors or advisory committees; Cellerant: Research Funding; Abbvie: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Delta Fly Pharma: Consultancy, Membership on an entity's Board of Directors or advisory committees; Nohla: Consultancy, Membership on an entity's Board of Directors or advisory committees; ADC Therapeutics: Research Funding; Tetraphase: Consultancy, Membership on an entity's Board of Directors or advisory committees; Orsenix: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding; Biosight: Research Funding; Oncolyze: Consultancy, Membership on an entity's Board of Directors or advisory committees; KAHR: Consultancy, Membership on an entity's Board of Directors or advisory committees. Choe:Agios: Employment, Equity Ownership; Agios: Employment, Equity Ownership. Wang:Agios: Employment, Equity Ownership. Zhang:Agios: Employment, Equity Ownership; Agios: Employment, Equity Ownership. Fan:Agios: Employment, Equity Ownership. Yen:Agios: Employment, Equity Ownership. Oluyadi:Agios: Employment, Equity Ownership. Winkler:Agios: Employment. Hickman:Agios: Employment, Equity Ownership. Agresta:Agios: Employment, Equity Ownership. Liu:Agios: Employment, Equity Ownership. Wu:Agios: Employment, Equity Ownership. Attar:Aprea Therapeutics: Employment; Agios: Employment, Equity Ownership. Kantarjian:Astex: Research Funding; Takeda: Honoraria; Actinium: Honoraria, Membership on an entity's Board of Directors or advisory committees; Immunogen: Research Funding; AbbVie: Honoraria, Research Funding; Jazz Pharma: Research Funding; Agios: Honoraria, Research Funding; Ariad: Research Funding; Amgen: Honoraria, Research Funding; Cyclacel: Research Funding; BMS: Research Funding; Daiichi-Sankyo: Research Funding; Novartis: Research Funding; Pfizer: Honoraria, Research Funding. OffLabel Disclosure: Ivosidenib (AG-120) is an IDH1 inhibitor indicated for the treatment of AML with a susceptible IDH1 mutation as detected by an FDA-approved test in: 1) adult patients with newly-diagnosed AML who are more than 75 years old or who have comorbidities that preclude use of intensive induction chemotherapy and 2) adult patients with relapsed or refractory AML. It is being evaluated in clinical trials for mutant IDH1 advanced hematologic malignancies.

Abstract Objective To design, develop, and evaluate a scalable clinical data normalization pipeline for standardizing unstructured electronic health record (EHR) data leveraging the HL7 Fast Healthcare Interoperability Resources (FHIR) specification. Methods We established an FHIR-based clinical data normalization pipeline known as NLP2FHIR that mainly comprises: (1) a module for a core natural language processing (NLP) engine with an FHIR-based type system; (2) a module for integrating structured data; and (3) a module for content normalization. We evaluated the FHIR modeling capability focusing on core clinical resources such as Condition, Procedure, MedicationStatement (including Medication), and FamilyMemberHistory using Mayo Clinic’s unstructured EHR data. We constructed a gold standard reusing annotation corpora from previous NLP projects. Results A total of 30 mapping rules, 62 normalization rules, and 11 NLP-specific FHIR extensions were created and implemented in the NLP2FHIR pipeline. The elements that need to integrate structured data from each clinical resource were identified. The performance of unstructured data modeling achieved F scores ranging from 0.69 to 0.99 for various FHIR element representations (0.69–0.99 for Condition; 0.75–0.84 for Procedure; 0.71–0.99 for MedicationStatement; and 0.75–0.95 for FamilyMemberHistory). Conclusion We demonstrated that the NLP2FHIR pipeline is feasible for modeling unstructured EHR data and integrating structured elements into the model. The outcomes of this work provide standards-based tools of clinical data normalization that is indispensable for enabling portable EHR-driven phenotyping and large-scale data analytics, as well as useful insights for future developments of the FHIR specifications with regard to handling unstructured clinical data.

Abstract BACKGROUND: Recurrent mutations in isocitrate dehydrogenase 1 (IDH1) are observed in approximately 4% of patients with myelodysplastic syndrome (MDS) and have been linked with increased transformation to acute myeloid leukemia. Ivosidenib (AG-120), an oral, potent, targeted, small-molecule inhibitor of the mutant IDH1 protein (mIDH1), is a therapeutic candidate for the treatment of patients with mIDH1 MDS. Through inhibition of mIDH1, ivosidenib suppresses the production of the oncometabolite 2-hydroxyglutarate (2-HG), leading to clinical responses via differentiation of malignant cells. AIM: To report safety and efficacy data from patients with relapsed or refractory (R/R) MDS enrolled in the first-in-human, phase 1, dose escalation and expansion study of ivosidenib in patients with mIDH1 advanced hematologic malignancies (NCT02074839). METHODS: This ongoing study is evaluating the safety, maximum tolerated dose (MTD), pharmacokinetics, pharmacodynamics, and clinical activity of ivosidenib. Trial enrollment was completed on 08May2017. In dose escalation, patients received single-agent ivosidenib orally once daily (QD) or twice daily in 28-day cycles. The MTD was not reached and 500 mg QD was selected as the dose to be tested in expansion. Expansion Arm 3 enrolled patients with mIDH1 advanced hematologic malignancies, including MDS. The overall response rate (ORR) for MDS was defined as complete remission (CR) + partial remission + marrow CR. Exploratory biomarker assessments included baseline co-occurring mutations (next-generation sequencing panel for hematologic malignancies) and mIDH1 variant allele frequency (VAF) in bone marrow mononuclear cells (BEAMing Digital PCR; lower limit of detection for mIDH1, 0.02-0.04%). Here, we present safety and efficacy data for patients with MDS in expansion Arm 3 and in dose escalation whose starting dose was 500 mg QD. RESULTS: In all, 258 patients (78 in dose escalation, 180 in expansion) received ivosidenib, including 12 patients with MDS (9 from expansion and 3 from escalation) whose starting dose was 500 mg QD. Baseline characteristics for these 12 patients were: 9 men/3 women; median age, 72.5 years (range, 52-78) and 42% were ≥75 years of age; median number of prior therapies, 1 (range, 1-3). As of 10Nov2017, 7 of 12 (58.3%) patients remained on treatment and 5 (41.7%) had discontinued (one for allogeneic stem cell transplantation). The median duration of exposure to ivosidenib was 11.0 months (range, 3.3-31.1). The most common adverse events (AEs) of any grade, irrespective of causality, occurring in ≥20% of the 12 patients were back pain (n=4, 33.3%) and anemia, decreased appetite, diarrhea, dyspnea, fatigue, hypokalemia, pruritus, and rash (n=3, 25.0% each). The majority of these AEs were grade 1-2 and reported as unrelated to treatment. No AEs led to permanent discontinuation of treatment. IDH differentiation syndrome (IDH-DS) was observed in 2 of 12 (16.7%) patients; the events were grade 1 and 2, respectively. Of the 12 patients with MDS receiving ivosidenib 500 mg QD, 5 achieved CR (41.7%; 95% CI 15.2%, 72.3%) and 6 achieved marrow CR (50.0%), resulting in an ORR of 91.7% (95% CI 61.5%, 99.8%). The median durations of CR and overall response were not estimable at the time of the data cutoff. The percentages of patients who remained in CR and response at 12 months were 60.0% and 61.4%, respectively. Among 5 patients who were transfusion dependent at baseline, 4 became transfusion independent for at least 56 days on treatment. Baseline co-occurring mutations and changes in mIDH1 VAF levels on ivosidenib therapy will be presented. CONCLUSION: In patients with mIDH1 R/R MDS, ivosidenib monotherapy was well tolerated and induced durable remissions and transfusion independence. These findings support the role of ivosidenib as an effective, oral, targeted treatment for patients with mIDH1 R/R MDS. Disclosures DiNardo: Karyopharm: Other: Advisory role; Medimmune: Other: Advisory role; Celgene: Other: Advisory role; Bayer: Other: Advisory role; Agios: Consultancy, Other: Advisory role; AbbVie: Consultancy, Other: Advisory role. Watts:Jazz Pharma: Consultancy, Speakers Bureau; Takeda: Research Funding. Stein:Celgene: Consultancy; Daiichi Sankyo: Consultancy; Agios: Consultancy; Pfizer: Consultancy; Novartis: Consultancy; Bayer: Consultancy. de Botton:Agios: Research Funding; Celgene: Honoraria, Research Funding. Fathi:Takeda: Consultancy, Honoraria; Jazz: Honoraria; Celgene: Consultancy, Honoraria, Research Funding; Boston Biomedical: Consultancy, Honoraria; Astellas: Honoraria; Seattle Genetics: Consultancy, Honoraria; Agios: Honoraria, Research Funding. Stein:Amgen: Speakers Bureau; Celgene: Speakers Bureau. Foran:Agios: Research Funding; Xencor, Inc.: Research Funding. Stone:AbbVie: Consultancy; Agios: Consultancy, Research Funding; Cornerstone: Consultancy; Orsenix: Consultancy; Fujifilm: Consultancy; Sumitomo: Consultancy; Pfizer: Consultancy; Celgene: Consultancy, Other: Data and Safety Monitoring Board, Steering Committee; Ono: Consultancy; Novartis: Consultancy, Research Funding; Otsuka: Consultancy; Jazz: Consultancy; Merck: Consultancy; Astellas: Consultancy; Arog: Consultancy, Research Funding; Argenx: Other: Data and Safety Monitoring Board; Amgen: Consultancy. Patel:France Foundation: Honoraria; Dava Oncology: Honoraria; Celgene: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau. Tallman:Cellerant: Research Funding; BioSight: Other: Advisory board; ADC Therapeutics: Research Funding; AbbVie: Research Funding; Daiichi-Sankyo: Other: Advisory board; AROG: Research Funding; Orsenix: Other: Advisory board. Choe:Agios: Employment, Equity Ownership. Wang:Agios: Employment, Equity Ownership. Zhang:Agios: Employment, Equity Ownership. Dai:Agios: Employment, Equity Ownership. Fan:Agios: Employment, Equity Ownership. Yen:Agios: Employment, Equity Ownership. Kapsalis:Agios: Employment, Equity Ownership. Hickman:Agios: Employment, Equity Ownership. Agresta:Agios: Employment, Equity Ownership. Liu:Agios: Employment, Equity Ownership. Wu:Agios: Employment, Equity Ownership, Patents & Royalties. Attar:Agios: Employment, Equity Ownership.