William T. Lester

PURPOSE: The rapid growth of biomedical data ecosystems has catalyzed research for oncology and precision medicine. We leverage federal cloud-based precision medicine databases and tools to better understand the current landscape of precision medicine and genomic testing for patients with cancer.METHODS: Retrospective observational study of genomic testing for patients with cancer in the National Institutes of Health All of Us Research Program, with the cancer cohort defined as having at least two documented or reported cancer diagnoses.RESULTS: There were 5,678 (1.8%) All of Us participants in the cancer cohort, with a significant difference between cancer status by age category, sex, race, and ethnicity ( P < .001 for all). There were 295 (5.2%) patients with cancer who received genomic testing compared with 6,734 (2.2%) of noncancer patients, with 752 genomic tests commonly focused on gene mutations (primarily pharmacogenomics), molecular pathology, or clinical cytogenetic reports.CONCLUSION: Although not yet ubiquitous, diverse clinical genomic analyses in oncology can set the stage to grow the practice of precision medicine by integrating research patient data repositories, cancer data ecosystems, and biomedical informatics.

PURPOSE Cloud computing has led to dramatic growth in the volume, variety, and velocity of cancer data. However, cloud platforms and services present new challenges for cancer research, particularly in understanding the practical tradeoffs between cloud performance, cost, and complexity. The goal of this study was to describe the practical challenges when using a cloud-based service to improve the cancer clinical trial matching process. METHODS We collected information for all interventional cancer clinical trials from ClinicalTrials.gov and used the Google Cloud Healthcare Natural Language Application Programming Interface (API) to analyze clinical trial Title and Eligibility Criteria text. An informatics pipeline leveraging interoperability standards summarized the distribution of cancer clinical trials, genes, laboratory tests, and medications extracted from cloud-based entity analysis. RESULTS There were a total of 38,851 cancer-related clinical trials found in this study, with the distribution of cancer categories extracted from Title text significantly different than in ClinicalTrials.gov (P < .001). Cloud-based entity analysis of clinical trial criteria identified a total of 949 genes, 1,782 laboratory tests, 2,086 medications, and 4,902 National Cancer Institute Thesaurus terms, with estimated detection accuracies ranging from 12.8% to 89.9%. A total of 77,702 API calls processed an estimated 167,179 text records, which took a total of 1,979 processing-minutes (33.0 processing-hours), or approximately 1.5 seconds per API call. CONCLUSION Current general-purpose cloud health care tools-like the Google service in this study-should not be used for automated clinical trial matching unless they can perform effective extraction and classification of the clinical, genetic, and medication concepts central to precision oncology research. A strong understanding of the practical aspects of cloud computing will help researchers effectively navigate the vast data ecosystems in cancer research.

Background Precision medicine involves three major innovations currently taking place in healthcare: electronic health records, genomics and big data. A major challenge for healthcare providers is, however, understanding the readiness for the practical application of initiatives like precision medicine. Objective To better understand the current state and challenges of precision medicine interoperability using a national genetic testing registry (GTR) as a starting point, placed in the context of established interoperability formats. Methods We performed an exploratory analysis of the National Institutes of Health GTR. Relevant standards included Health Level Seven International Version 3 Implementation Guide for Family History, the Human Genome Organization Gene Nomenclature Committee (HGNC) database and Systematised Nomenclature of Medicine – Clinical Terms (SNOMED CT). We analysed the distribution of genetic testing laboratories, genetic test characteristics and standardised genome/clinical code mappings, stratified by laboratory setting. Results There were a total of 25,472 genetic tests from 240 laboratories testing for approximately 3,632 distinct genes. Most tests focused on diagnosis, mutation confirmation and/or the risk assessment of germline mutations that could be passed to offspring. Genes were successfully mapped to all HGNC identifiers, but less than half of tests were mapped to SNOMED CT codes, highlighting significant gaps when linking genetic tests to standardised clinical codes that explain the medical motivations behind test ordering. Conclusion While precision medicine could potentially transform healthcare, successful practical and clinical applications will first require the comprehensive and responsible adoption of interoperable standards, terminologies and formats across all aspects of the precision medicine pipeline.

Data to support improved patient outcomes from clinical decision-support systems (CDSSs) are lacking in HIV care. To test the efficacy of a CDSS in improving HIV outcomes in an outpatient clinic. Randomized, controlled trial. (ClinicalTrials.gov registration number: NCT00678600) Massachusetts General Hospital HIV Clinic. HIV care providers and their patients. Computer alerts were generated for virologic failure (HIV RNA level >400 copies/mL after a previous HIV RNA level ≤400 copies/mL), evidence of suboptimal follow-up, and 11 abnormal laboratory test results. Providers received interactive computer alerts, facilitating appointment rescheduling and repeated laboratory testing, for half of their patients and static alerts for the other half. The primary end point was change in CD4 cell count. Other end points included time to clinical event, 6-month suboptimal follow-up, and severe laboratory toxicity. Thirty-three HIV care providers followed 1011 patients with HIV. In the intervention group, the mean increase in CD4 cell count was greater (0.0053 vs. 0.0032 × 10⁹ cells/L per month; difference, 0.0021 × 10⁹ cells/L per month [95% CI, 0.0001 to 0.004]; P = 0.040) and the rate of 6-month suboptimal follow-up was lower (20.6 vs. 30.1 events per 100 patient-years; P = 0.022) than those in the control group. Median time to next scheduled appointment was shorter in the intervention group than in the control group after a suboptimal follow-up alert (1.71 vs. 3.48 months; P < 0.001) and after a toxicity alert (2.79 vs. >6 months; P = 0.072). More than 90% of providers supported adopting the CDSS as part of standard care. This was a 1-year informatics study conducted at a single hospital subspecialty clinic. A CDSS using interactive provider alerts improved CD4 cell counts and clinic follow-up for patients with HIV. Wider implementation of such systems can provide important clinical benefits. National Institute of Allergy and Infectious Diseases.

Objectives:To assess the ability of a health information technology system to facilitate population-based breast cancer screening. Study Design: Cohort study with 2-year follow-up after a 1-year cluster randomized trial. Methods: Study population was women 42 to 69 years old receiving care within a 12-practice primary care network. The management informatics system (1) identified women overdue for mammograms, (2) connected them to primary care providers using a web-based tool, (3) created automatically generated outreach letters for patients specified by providers, (4) monitored for subsequent mammography scheduling and completion, and (5) provided practice delegates with a list of women remaining unscreened for reminder phone calls. Eligible women overdue for a mammogram during a 1-year study period included those overdue at study start (prevalent cohort) and those who became overdue during follow-up (incident cohort).The main outcome measure was mammography completion rates over 3 years. Results: Among 32,688 eligible women, 9795 (30%) were overdue for screening (4487 intervention, 5308 control). Intervention patients were somewhat younger, more likely to be non-Hispanic white, and more likely to have health insurance compared with control patients. Adjusted completion rates in the prevalent cohort In = 6697) were significantly higher among intervention patients after 3 years (51.7% vs 45.8%; P = .0021. For patients in the incident cohort (n = 3098), adjusted completion rates after 2 years were 53.8% versus 48.7%, respectively (P = .052). Conclusions: Population-based informatics systems can enable sustained increases in mammography screening rates beyond rates seen with office-based visit reminders. (Am J Manag Care. 2012;18(12):821-829)

Usability testing is a key step in the successful design of new technologies and tools, ensuring that heterogeneous populations will be able to interact easily with innovative applications. While usability testing methods of productivity tools (e.g., text editors, spreadsheets, or management tools) are varied, widely available, and valuable, analyzing the usability of games, especially educational “serious” games, presents unique usability challenges. Because games are fundamentally different than general productivity tools, “traditional” usability instruments valid for productivity applications may fall short when used for serious games. In this work we present a methodology especially designed to facilitate usability testing for serious games, taking into account the specific needs of such applications and resulting in a systematically produced list of suggested improvements from large amounts of recorded gameplay data. This methodology was applied to a case study for a medical educational game, MasterMed, intended to improve patients’ medication knowledge. We present the results from this methodology applied to MasterMed and a summary of the central lessons learned that are likely useful for researchers who aim to tune and improve their own serious games before releasing them for the general public.

Objective To characterize important patterns of genetic testing behavior and reporting in modern electronic medical records (EMRs) at the institutional level. Materials and methods Retrospective observational study using EMR data of all 10 715 patients who received genetic testing by physicians trained in a primary care specialty or subspecialty at an academic medical center between January 1, 2008 and December 31, 2010. Results Patients had a mean±SD age of 38.3±15.8 years (median 36.1, IQR 30.0–43.8). The proportion of female subjects in the study population was larger than in the general patient population (77.2% vs 55.0%, pConclusions In this study, genetic tests were often ordered by a diverse group of physicians for women of childbearing age being evaluated for diseases that may affect potential offspring. EMRs currently serve primarily as a storage warehouse for textual reports that could potentially be transformed into meaningful structured data for next-generation clinical decision support. Further studies are needed to address the design, development, and implementation of EMRs capable of managing the critical genetic health information challenges of the future.

In exploring an approach to decision support based on information extracted from a clinical database, we developed mortality prediction models of intensive care unit (ICU) patients who had acute kidney injury (AKI) and compared them against the Simplified Acute Physiology Score (SAPS). We used MIMIC, a public de‐identified database of ICU patients admitted to Beth Israel Deaconess Medical Center, and identified 1400 patients with an ICD9 diagnosis of AKI and who had an ICU stay ≥3 days. Multivariate regression models were built using the SAPS variables from the first 72 hours of ICU admission. All the models developed on the training set performed better than SAPS (AUC = 0.64, Hosmer‐Lemeshow p <0.001) on an unseen test set; the best model had an AUC = 0.74 and Hosmer‐Lemeshow p = 0.53. These findings suggest that local customized modeling might provide more accurate predictions. This could be the first step towards an envisioned individualized point‐of‐care probabilistic modeling using one′s clinical database.

Information technology offers the promise, as yet unfulfilled, of delivering efficient, evidence-based health care.

Health care information technology can be a means to improve quality and efficiency in the primary care setting. However, merely applying technology