Dataset Information

Integrated digital pathology at scale: A solution for clinical diagnostics and cancer research at a large academic medical center.

ABSTRACT:

Objective

Broad adoption of digital pathology (DP) is still lacking, and examples for DP connecting diagnostic, research, and educational use cases are missing. We blueprint a holistic DP solution at a large academic medical center ubiquitously integrated into clinical workflows; researchapplications including molecular, genetic, and tissue databases; and educational processes.

Materials and methods

We built a vendor-agnostic, integrated viewer for reviewing, annotating, sharing, and quality assurance of digital slides in a clinical or research context. It is the first homegrown viewer cleared by New York State provisional approval in 2020 for primary diagnosis and remote sign-out during the COVID-19 (coronavirus disease 2019) pandemic. We further introduce an interconnected Honest Broker for BioInformatics Technology (HoBBIT) to systematically compile and share large-scale DP research datasets including anonymized images, redacted pathology reports, and clinical data of patients with consent.

Results

The solution has been operationally used over 3 years by 926 pathologists and researchers evaluating 288 903 digital slides. A total of 51% of these were reviewed within 1 month after scanning. Seamless integration of the viewer into 4 hospital systems clearly increases the adoption of DP. HoBBIT directly impacts the translation of knowledge in pathology into effective new health measures, including artificial intelligence-driven detection models for prostate cancer, basal cell carcinoma, and breast cancer metastases, developed and validated on thousands of cases.

Conclusions

We highlight major challenges and lessons learned when going digital to provide orientation for other pathologists. Building interconnected solutions will not only increase adoption of DP, but also facilitate next-generation computational pathology at scale for enhanced cancer research.

SUBMITTER: Schuffler PJ

PROVIDER: S-EPMC8344580 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Electronic medical records (EMRs) contain a wealth of information that can support data-driven decision making in health care policy design and service planning. Although research using EMRs has become increasingly prevalent, challenges such as coding inconsistency, data validity, and lack of suitable measures in important domains still hinder the progress. OBJECTIVE:The objective of this study was to design a structured way to process records in administrative EMR systems for health services research and assess validity in selected areas. METHODS:On the basis of a local hospital EMR system in Singapore, we developed a structured framework for EMR data processing, including standardization and phenotyping of diagnosis codes, construction of cohort with multilevel views, and generation of variables and proxy measures to supplement primary data. Disease complexity was estimated by Charlson Comorbidity Index (CCI) and Polypharmacy Score (PPS), whereas socioeconomic status (SES) was estimated by housing type. Validity of modified diagnosis codes and derived measures were investigated. RESULTS:Visit-level (N=7,778,761) and patient-level records (n=549,109) were generated. The International Classification of Diseases, Tenth Revision, Australian Modification (ICD-10-AM) codes were standardized to the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) with a mapping rate of 87.1%. In all, 97.4% of the ICD-9-CM codes were phenotyped successfully using Clinical Classification Software by Agency for Healthcare Research and Quality. Diagnosis codes that underwent modification (truncation or zero addition) in standardization and phenotyping procedures had the modification validated by physicians, with validity rates of more than 90%. Disease complexity measures (CCI and PPS) and SES were found to be valid and robust after a correlation analysis and a multivariate regression analysis. CCI and PPS were correlated with each other and positively correlated with health care utilization measures. Larger housing type was associated with lower government subsidies received, suggesting association with higher SES. Profile of constructed cohorts showed differences in disease prevalence, disease complexity, and health care utilization in those aged above 65 years and those aged 65 years or younger. CONCLUSIONS:The framework proposed in this study would be useful for other researchers working with EMR data for health services research. Further analyses would be needed to better understand differences observed in the cohorts.

Project description:BackgroundIt is important to monitor the scope of clinical research of all types, to involve participants of all ages and subgroups in studies that are appropriate to their condition, and to ensure equal access and broad validity of the findings.ObjectiveWe conducted a review of clinical research performed at New York University with the following objectives: (1) to determine the utility of institutional administrative data to characterize clinical research activity; (2) to assess the inclusion of special populations; and (3) to determine if the type, initiation, and completion of the study differed by age.MethodsData for all studies that were institutional review board-approved between January 1, 2014, and November 2, 2016, were obtained from the research navigator system, which was launched in November 2013. One module provided details about the study protocol, and another module provided the characteristics of individual participants. Research studies were classified as observational or interventional. Descriptive statistics were used to assess the characteristics of clinical studies across the lifespan, by type, and over time.ResultsA total of 22%-24% of studies included children (minimum age <18 years) and 4%-5% focused exclusively on pediatrics. Similarly, 64%-72% of studies included older patients (maximum age >65 years) but only 5%-12% focused exclusively on geriatrics. Approximately 85% of the studies included both male and female participants. Of the remaining studies, those open only to girls or women were approximately 3 times as common as those confined to boys or men. A total of 56%-58% of projects focused on nonvulnerable patients. Among the special populations studied, children (12%-15%) were the most common. Noninterventional trial types included research on human data sets (24%), observational research (22%), survey research (16%), and biospecimen research (8%). The percentage of projects designed to test an intervention in a vulnerable population increased from 17% in 2014 to 21% in 2015.ConclusionsPediatric participants were the special population that was most often studied based on the number of registered projects that included children and adolescents. However, they were much less likely to be successfully enrolled in research studies compared with adults older than 65 years. Only 20% of the studies were interventional, and 20%-35% of participants in this category were from vulnerable populations. More studies are exclusively devoted to women's health issues compared with men's health issues.

Project description:BackgroundOne of the most difficult aspects of conducting clinical research is the ability to successfully recruit participants. Pediatric clinical research presents unique recruitment challenges that relate to the need for parental consent on behalf of a minor, child assent, and school attendance. Yet, this has been less well studied. We conducted a survey of investigators performing human subjects research in a single large academic pediatric hospital to better understand characteristics of studies with successful recruitment.MethodsWe conducted a web-based survey from September 2011 to December 2011 of all principal investigators with an Institutional Review Board approved human subjects protocol at Boston Children's Hospital, a pediatric Academic Medical Center. The survey captured various characteristics of the protocols including study design, staffing, resources, and investigator experience and training as well as respondents' perceived barriers and facilitators to recruitment. We used chi square tests and Mantel-Haenszel test for linear trend to examine the relationship between selected predictor variables and the binary outcome of successful vs. unsuccessful recruitment and multivariable logistic regression analyses to examine the simultaneous influence of potential predictors on each outcome.ResultsAmong the 349 eligible investigators, 52% responded to the survey, and 181 with valid data were included in the analyses. Two-thirds of the 87 protocols closed to enrollment reached 80% or more of their target enrollment, whereas, only one-third of the 94 protocols actively recruiting were meeting 80% of their target. Recruitment method appeared to be the only significant and independent factor associated with achieving 80% or more of target enrollment in closed to enrollment protocols. Closed to enrollment protocols that used recruitment in person were 4.55 times (95% CI 1.30 to 15.93; p = 0.02) more likely to achieve 80% or more of their target enrollment when compared to those that used other recruitment methods. Other potentially modifiable factors such as number of study visits, study duration and investigator experience were suggestive of being meaningfully related to recruitment.ConclusionRecruiting in person may promote reaching an acceptable target enrollment in pediatric as well as adult clinical research. Future research is needed on larger and more diverse samples to gain a better understanding of how the characteristics and qualifications of the individuals who conduct recruitment influence participant enrollment as well as how best to approach patient and families for their participation.