Representing and utilizing clinical textual data for real world studies: An OHDSI approach.

Clinical documentation in electronic health records contains crucial narratives and details about patients and their care. Natural language processing (NLP) can unlock the information conveyed in clinical notes and reports, and thus plays a critical role in real-world studies. The NLP Working Group at the Observational Health Data Sciences and Informatics (OHDSI) consortium was established to develop methods and tools to promote the use of textual data and NLP in real-world observational studies. In this paper, we describe a framework for representing and utilizing textual data in real-world evidence generation, including representations of information from clinical text in the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM), the workflow and tools that were developed to extract, transform and load (ETL) data from clinical notes into tables in OMOP CDM, as well as current applications and specific use cases of the proposed OHDSI NLP solution at large consortia and individual institutions with English textual data. Challenges faced and lessons learned during the process are also discussed to provide valuable insights for researchers who are planning to implement NLP solutions in real-world studies.

HemOnc: A new standard vocabulary for chemotherapy regimen representation in the OMOP common data model.

Systematic application of observational data to the understanding of impacts of cancer treatments requires detailed information models allowing meaningful comparisons between treatment regimens. Unfortunately, details of systemic therapies are scarce in registries and data warehouses, primarily due to the complex nature of the protocols and a lack of standardization. Since 2011, we have been creating a curated and semi-structured website of chemotherapy regimens, HemOnc.org. In coordination with the Observational Health Data Sciences and Informatics (OHDSI) Oncology Subgroup, we have transformed a substantial subset of this content into the OMOP common data model, with bindings to multiple external vocabularies, e.g., RxNorm and the National Cancer Institute Thesaurus. Currently, there are >73,000 concepts and >177,000 relationships in the full vocabulary. Content related to the definition and composition of chemotherapy regimens has been released within the ATHENA tool (athena.ohdsi.org) for widespread utilization by the OHDSI membership. Here, we describe the rationale, data model, and initial contents of the HemOnc vocabulary along with several use cases for which it may be valuable.

The association of phosphodiesterase-5 inhibitors with the biochemical recurrence-free and overall survival of patients with prostate cancer following radical prostatectomy.

PURPOSE: To determine whether phosphodiesterase-5 inhibitor documentation is associated with biochemical relapse-free and overall survival of patients with prostate cancer treated with radical prostatectomy. MATERIALS AND METHODS: We undertook a retrospective cohort analysis of 3,100 patients with prostate cancer treated with radical prostatectomy between 2003 and 2015. The patients were categorized as a phosphodiesterase- 5- inhibitor user or non-user. The biochemical relapse-free and overall survival at 5-years and 10-years were determined. RESULTS: Of the patients, 1,372 reported phosphodiesterase-5 inhibitor documentation, and 1,728 did not. The biochemical recurrence-free survival for non-users at 5- and 10-years follow-up was 87.6% and 85.3%, respectively, and the overall survival at these time intervals was 97.9% and 94.5%. The biochemical recurrence-free survival for phosphodiesterase-5 inhibitor users was 94.3% and 93.2% at 5- and 10-years follow-up, respectively, and overall survival was 99.2% and 95.8% at these intervals. The hazard ratio for biochemical recurrence-free survival was 0.44 (CI 0.34-0.56) and for overall survival was 0.65 (CI 0.45-0.94). On the multivariate analysis, phosphodiesterase-5 inhibitor documentation was associated with a lower risk of biochemical recurrence and death when corrected for the other variables. Age at surgery and Gleason scores >8 was associated with a higher risk of death. Higher pathological stage, higher Gleason score, presence of lymph node metastases, and nonwhite race were associated with a higher risk of recurrence. CONCLUSION: This retrospective analysis revealed a significant association of postoperative phosphodiesterase-5 inhibitor documentation with biochemical recurrence-free- and overall survival in patients with localized prostate cancer treated with radical prostatectomy. Larger scale studies are warranted to investigate the clinical significance of this association.

Outcomes of Cancer Patients with COVID-19 in a Hospital System in the Chicago Metropolitan Area.

Patients with a history of malignancy have been shown to be at an increased risk of COVID-19-related morbidity and mortality. Poorer clinical outcomes in that patient population are likely due to the underlying systemic illness, comorbidities, and the cytotoxic and immunosuppressive anti-tumor treatments they are subjected to. We identified 416 cancer patients with SARS-CoV-2 infection being managed for their malignancy at Northwestern Medicine in Chicago, Illinois, between March and July of 2020. Seventy-five (18.0%) patients died due to COVID-related complications. Older age (>60), male gender, and current treatment with immunotherapy were associated with shorter overall survival. Laboratory findings showed that higher platelet counts, ALC, and hemoglobin were protective against critical illness and death from COVID-19. Conversely, elevated inflammatory markers such as ferritin, d-dimer, procalcitonin, CRP, and LDH led to worse clinical outcomes. Our findings suggest that a thorough clinical and laboratory assessment of infected patients with cancer might help identify a more vulnerable population and implement more aggressive proactive strategies.

Statin use and risk of prostate cancer biochemical recurrence after radical prostatectomy.

BACKGROUND: Multiple studies have investigated the role of statins in prostate cancer (CaP), the leading cause of cancer related death in men. Retrospective cohort studies investigating the correlation between statin use and biochemical recurrence free (BCRF) survival in men with CaP have been inconclusive. OBJECTIVES: In the largest reported surgical cohort to date, we investigated the effect of statin therapy on BCRF and overall survival in patients with CaP who have undergone radical prostatectomy (RP). PATIENTS AND METHODS: We performed a retrospective analysis of men (n = 3,088) participating in the NCI funded Specialized Program of Research Excellence (SPORE) in CaP at Northwestern University (NM) in Chicago, Illinois. Patients were treated with RP between 2002 and 2015. Patients in the statin users group received treatment within 2 years prior to or subsequent to RP. Wilcoxon rank-sum and Fisher's exact tests were used to compare age, race, Gleason score, clinical staging, and pathological stage between statin users and nonstatin users. RESULTS: The analysis identified 1,222 statin users and 1,865 nonusers (mean age 71 years, 92% Caucasian). After a median follow-up time of 49.0 months, the 5-year BCRF survival rate was 93.3% (95% confidence interval [CI]: 91.9-94.8%) among statin users and 88.6% (95% CI: 87.1%-90%) among nonusers (log-rank P< 0.001). After 10 years, the progression-free survival (PFS) was 91.7% (95% CI: 90.1%-93.3%) among statin users and 86.5% (95% CI: 84.4%-88.2%) among nonusers (log-rank P< 0.001). CONCLUSIONS: Extended follow-up data in this large surgical cohort show statin use improves BCRF but not overall survival in RP patients.

Development and evaluation of a new fully automatic motion detection and correction technique in cardiac SPECT imaging.

BACKGROUND: In cardiac SPECT perfusion imaging, motion correction of the data is critical to the minimization of motion introduced artifacts in the reconstructed images. Software-based (data-driven) motion correction techniques are the most convenient and economical approaches to fulfill this purpose. However, the accuracy is significantly affected by how the data complexities, such as activity overlap, non-uniform tissue attenuation, and noise are handled. METHODS: We developed STASYS, a new, fully automatic technique, for motion detection and correction in cardiac SPECT. We evaluated the performance of STASYS by comparing its effectiveness of motion correcting patient studies with the current industry standard software (Cedars-Sinai MoCo) through blind readings by two readers independently. RESULTS: For 204 patient studies from multiple clinical sites, the first reader identified (1) 69 studies with medium to large axial motion, of which STASYS perfectly or significantly corrected 86.9% and MoCo 72.5%; and (2) 20 studies with medium to large lateral motion, of which STASYS perfectly or significantly corrected 80.0% and MoCo 60.0%. The second reader identified (1) 84 studies with medium to large axial motion, of which STASYS perfectly or significantly corrected 82.2% and MoCo 76.2%; and (2) 34 studies with medium to large lateral motion, of which STASYS perfectly or significantly corrected 58.9% and MoCo 50.0%. CONCLUSIONS: We developed a fully automatic software-based motion correction technique, STASYS, for cardiac SPECT. Clinical studies showed that STASYS was effective and corrected a larger percent of cardiac SPECT studies than the current industrial standard software.

Standardized Observational Cancer Research Using the OMOP CDM Oncology Module.

Observational research in cancer requires substantially more detail than most other therapeutic areas. Cancer conditions are defined through histology, affected anatomical structures, staging and grading, and biomarkers, and are treated with complex therapies. Here, we show a new cancer module as part of the OMOP CDM, allowing manual and automated abstraction and standardized analytics. We tested the model in EHR and registry data against a number of typical use cases.

Generation of "virtual" control groups for single arm prostate cancer adjuvant trials.

It is difficult to construct a control group for trials of adjuvant therapy (Rx) of prostate cancer after radical prostatectomy (RP) due to ethical issues and patient acceptance. We utilized 8 curve-fitting models to estimate the time to 60%, 65%, … 95% chance of progression free survival (PFS) based on the data derived from Kattan post-RP nomogram. The 8 models were systematically applied to a training set of 153 post-RP cases without adjuvant Rx to develop 8 subsets of cases (reference case sets) whose observed PFS times were most accurately predicted by each model. To prepare a virtual control group for a single-arm adjuvant Rx trial, we first select the optimal model for the trial cases based on the minimum weighted Euclidean distance between the trial case set and the reference case set in terms of clinical features, and then compare the virtual PFS times calculated by the optimum model with the observed PFSs of the trial cases by the logrank test. The method was validated using an independent dataset of 155 post-RP patients without adjuvant Rx. We then applied the method to patients on a Phase II trial of adjuvant chemo-hormonal Rx post RP, which indicated that the adjuvant Rx is highly effective in prolonging PFS after RP in patients at high risk for prostate cancer recurrence. The method can accurately generate control groups for single-arm, post-RP adjuvant Rx trials for prostate cancer, facilitating development of new therapeutic strategies.