Development trends and knowledge framework of artificial intelligence (AI) applications in oncology by years: a bibliometric analysis from 1992 to 2022

PURPOSE

Oncology is the primary field in medicine with a high rate of artificial intelligence (AI) use. Thus, this study aimed to investigate the trends of AI in oncology, evaluating the bibliographic characteristics of articles. We evaluated the related research on the knowledge framework of Artificial Intelligence (AI) applications in Oncology through bibliometrics analysis and explored the research hotspots and current status from 1992 to 2022.

METHODS

The research employed a scientometric methodology and leveraged scientific visualization tools such as Bibliometrix R Package Software, VOSviewer, and Litmaps for comprehensive data analysis. Scientific AI-related publications in oncology were retrieved from the Web of Science (WoS) and InCites from 1992 to 2022.

RESULTS

A total of 7,815 articles authored by 35,098 authors and published in 1,492 journals were included in the final analysis. The most prolific authors were Esteva A (citaition = 5,821) and Gillies RJ (citaition = 4288). The most active institutions were the Chinese Academy of Science and Harward University. The leading journals were Frontiers ın Oncology and Scientific Reports. The most Frequent Author Keywords are "machine learning", "deep learning," "radiomics", "breast cancer", "melanoma" and "artificial intelligence," which are the research hotspots in this field. A total of 10,866 Authors' keywords were investigated. The average number of citations per document is 23. After 2015, the number of publications proliferated.

CONCLUSION

The investigation of Artificial Intelligence (AI) applications in the field of Oncology is still in its early phases especially for genomics, proteomics, and clinicomics, with extensive studies focused on biology, diagnosis, treatment, and cancer risk assessment. This bibliometric analysis offered valuable perspectives into AI's role in Oncology research, shedding light on emerging research paths. Notably, a significant portion of these publications originated from developed nations. These findings could prove beneficial for both researchers and policymakers seeking to navigate this field.

Leveraging e-health for enhanced cancer care service models in middle-income contexts: Qualitative insights from oncology care providers

Background

Global cancer research has predominantly favoured high-income countries (HICs). The unique challenges in low- and middle-income countries (LMICs) demand tailored research approaches, accentuated further by the disparities highlighted during the COVID-19 pandemic.

Aim and objectives

This research endeavoured to dissect the intricacies of cancer care in LMICs, with Jordan serving as a case study. Specifically, the study aimed to conduct an in-depth analysis of the prevailing cancer care model and assess the transformative potential of eHealth technologies in bolstering cancer care delivery.

Methods

Utilising a qualitative methodology, in-depth semi-structured interviews with oncology healthcare professionals were executed. Data underwent inductive thematic analysis as per Braun and Clarke's guidelines.

Results

From the analysed data, two dominant themes surfaced. Firstly, "The current state of cancer care delivery" was subdivided into three distinct subthemes. Secondly, "Opportunities for enhanced care delivery via e-health" underscored the urgency of digital health reforms.

Conclusion

The need to restrategise cancer care in LMICs is highlighted by this study, using the Jordanian healthcare context as a reference. The transformative potential of e-health initiatives has been illustrated. However, the relevance of this study might be limited by its region-specific approach. Future research is deemed essential for deeper exploration into the integration of digital health within traditional oncology settings across diverse LMICs, emphasising the significance of telemedicine in digital-assisted care delivery reforms.

Use of Tokens to Unlock Greater Data Sharing in Health Care

This Viewpoint discusses the use of privacy-preserving record linkage, a token-based record linkage system, as a promising avenue for building a data infrastructure system that bridges isolated data.

Inferring cancer disease response from radiology reports using large language models with data augmentation and prompting

OBJECTIVE

To assess large language models on their ability to accurately infer cancer disease response from free-text radiology reports.

MATERIALS AND METHODS

We assembled 10 602 computed tomography reports from cancer patients seen at a single institution. All reports were classified into: no evidence of disease, partial response, stable disease, or progressive disease. We applied transformer models, a bidirectional long short-term memory model, a convolutional neural network model, and conventional machine learning methods to this task. Data augmentation using sentence permutation with consistency loss as well as prompt-based fine-tuning were used on the best-performing models. Models were validated on a hold-out test set and an external validation set based on Response Evaluation Criteria in Solid Tumors (RECIST) classifications.

RESULTS

The best-performing model was the GatorTron transformer which achieved an accuracy of 0.8916 on the test set and 0.8919 on the RECIST validation set. Data augmentation further improved the accuracy to 0.8976. Prompt-based fine-tuning did not further improve accuracy but was able to reduce the number of training reports to 500 while still achieving good performance.

DISCUSSION

These models could be used by researchers to derive progression-free survival in large datasets. It may also serve as a decision support tool by providing clinicians an automated second opinion of disease response.

CONCLUSIONS

Large clinical language models demonstrate potential to infer cancer disease response from radiology reports at scale. Data augmentation techniques are useful to further improve performance. Prompt-based fine-tuning can significantly reduce the size of the training dataset.

The design and evaluation of hybrid controlled trials that leverage external data and randomization

Patient-level data from completed clinical studies or electronic health records can be used in the design and analysis of clinical trials. However, these external data can bias the evaluation of the experimental treatment when the statistical design does not appropriately account for potential confounders. In this work, we introduce a hybrid clinical trial design that combines the use of external control datasets and randomization to experimental and control arms, with the aim of producing efficient inference on the experimental treatment effects. Our analysis of the hybrid trial design includes scenarios where the distributions of measured and unmeasured prognostic patient characteristics differ across studies. Using simulations and datasets from clinical studies in extensive-stage small cell lung cancer and glioblastoma, we illustrate the potential advantages of hybrid trial designs compared to externally controlled trials and randomized trial designs.

Patient-level external control data from prior clinical studies or electronic health records can be used in the design and analysis of clinical trials. Here the authors report a hybrid trial design combining the use of external control data and randomization to test experimental treatments, using small cell lung cancer and glioblastoma datasets as examples.

An Approach to Solving the Complex Clinicogenomic Data Landscape in Precision Oncology: Learnings From the Design of WAYFIND-R, a Global Precision Oncology Registry

Precision oncology, where patients are given therapies based on their genomic profile and disease trajectory, is rapidly evolving to become a pivotal part of cancer management, supported by regulatory approvals of biomarker-matched targeted therapies and cancer immunotherapies. However, next-generation sequencing (NGS)-based technologies have revealed an increasing number of molecular-based cancer subtypes with rare patient populations, leading to difficulties in executing/recruiting for traditional clinical trials. Therefore, approval of novel therapeutics based on traditional interventional studies may be difficult and time consuming, with delayed access to innovative therapies. Real-world data (RWD) that describe the patient journey in routine clinical practice can help elucidate the clinical utility of NGS-based genomic profiling, multidisciplinary case discussions, and targeted therapies. We describe key learnings from the setup of WAYFIND-R (NCT04529122), a first-of-its-kind global cancer registry collecting RWD from patients with solid tumors who have undergone NGS-based genomic profiling. The meaning of 'generalizability' and 'high quality' for RWD across different geographic areas was revisited, together with patient recruitment processes, and data sharing and privacy. Inspired by these learnings, WAYFIND-R's design will help physicians discuss patient treatment plans with their colleagues, improve understanding of the impact of treatment decisions/cancer care processes on patient outcomes, and provide a platform to support the design and conduct of further clinical/epidemiologic research. WAYFIND-R demonstrates user-friendly, electronic case report forms, standardized collection of molecular tumor board-based decisions, and a dashboard providing investigators with access to local cohort-level data and the ability to interact with colleagues or search the entire registry to find rare populations. Overall, WAYFIND-R will inform on best practice for NGS-based treatment decisions by clinicians, foster global collaborations between cancer centers and enable robust conclusions regarding outcome data to be drawn, improve understanding of disparities in patients' access to advanced diagnostics and therapies, and ultimately drive advances in precision oncology.

Patient Experiences, Trust, and Preferences for Health Data Sharing

PURPOSE

Scholars have examined patients' attitudes toward secondary use of routinely collected clinical data for research and quality improvement. Evidence suggests that trust in health care organizations and physicians is critical. Less is known about experiences that shape trust and how they influence data sharing preferences.

MATERIALS AND METHODS

To explore learning health care system (LHS) ethics, democratic deliberations were hosted from June 2017 to May 2018. A total of 217 patients with cancer participated in facilitated group discussion. Transcripts were coded independently. Finalized codes were organized into themes using interpretive description and thematic analysis. Two previous analyses reported on patient preferences for consent and data use; this final analysis focuses on the influence of personal lived experiences of the health care system, including interactions with providers and insurers, on trust and preferences for data sharing.

RESULTS

Qualitative analysis identified four domains of patients' lived experiences raised in the context of the policy discussions: (1) the quality of care received, (2) the impact of health care costs, (3) the transparency and communication displayed by a provider or an insurer to the patient, and (4) the extent to which care coordination was hindered or facilitated by the interchange between a provider and an insurer. Patients discussed their trust in health care decision makers and their opinions about LHS data sharing.

CONCLUSION

Additional resources, infrastructure, regulations, and practice innovations are needed to improve patients' experiences with and trust in the health care system. Those who seek to build LHSs may also need to consider improvement in other aspects of care delivery.

The use of external control data for predictions and futility interim analyses in clinical trials

BACKGROUND

External control (EC) data from completed clinical trials and electronic health records can be valuable for the design and analysis of future clinical trials. We discuss the use of EC data for early stopping decisions in randomized clinical trials (RCTs).

METHODS

We specify interim analyses (IAs) approaches for RCTs, which allow investigators to integrate external data into early futility stopping decisions. IAs utilize predictions based on early data from the RCT, possibly combined with external data. These predictions at IAs express the probability that the trial will generate significant evidence of positive treatment effects. The trial is discontinued if this predictive probability becomes smaller than a prespecified threshold. We quantify efficiency gains and risks associated with the integration of external data into interim decisions. We then analyze a collection of glioblastoma (GBM) data sets, to investigate if the balance of efficiency gains and risks justify the integration of external data into the IAs of future GBM RCTs.

RESULTS

Our analyses illustrate the importance of accounting for potential differences between the distributions of prognostic variables in the RCT and in the external data to effectively leverage external data for interim decisions. Using GBM data sets, we estimate that the integration of external data increases the probability of early stopping of ineffective experimental treatments by up to 25% compared to IAs that do not leverage external data. Additionally, we observe a reduction of the probability of early discontinuation for effective experimental treatments, which improves the RCT power.

CONCLUSION

Leveraging external data for IAs in RCTs can support early stopping decisions and reduce the number of enrolled patients when the experimental treatment is ineffective.

College of American Pathologists Cancer Protocols: From Optimizing Cancer Patient Care to Facilitating Interoperable Reporting and Downstream Data Use

The College of American Pathologists Cancer Protocols have offered guidance to pathologists for standard cancer pathology reporting for more than 35 years. The adoption of computer readable versions of these protocols by electronic health record and laboratory information system (LIS) vendors has provided a mechanism for pathologists to report within their LIS workflow, in addition to enabling standardized structured data capture and reporting to downstream consumers of these data such as the cancer surveillance community. This paper reviews the history of the Cancer Protocols and electronic Cancer Checklists, outlines the current use of these critically important cancer case reporting tools, and examines future directions, including plans to help improve the integration of the Cancer Protocols into clinical, public health, research, and other workflows.

KMDATA: a curated database of reconstructed individual patient-level data from 153 oncology clinical trials

We created a database of reconstructed patient-level data from published clinical trials that includes multiple time-to-event outcomes such as overall survival and progression-free survival. Outcomes were extracted from Kaplan–Meier (KM) curves reported in 153 oncology Phase III clinical trial publications identified through a PubMed search of clinical trials in breast, lung, prostate and colorectal cancer, published between 2014 and 2016. For each trial that met our search criteria, we curated study-level information and digitized all reported KM curves with the software Digitizelt. We then used the digitized KM survival curves to estimate (possibly censored) patient-level time-to-event outcomes. Collections of time-to-event datasets from completed trials can be used to support the choice of appropriate trial designs for future clinical studies. Patient-level data allow investigators to tailor clinical trial designs to diseases and classes of treatments. Patient-level data also allow investigators to estimate the operating characteristics (e.g. power and type I error rate) of candidate statistical designs and methods.

Database URL: https://10.6084/m9.figshare.14642247.v1

A prognostic information system for real-time personalized care: Lessons for embedded researchers

Embedded researchers could play a central role in developing tools to personalize care using electronic medical records (EMRs). However, few studies have described the steps involved in developing such tools, or evaluated the key factors in success and failure. This case study describes how we used an EMR-derived data warehouse to develop a prototype informatics tool to help oncologists counsel patients with pancreatic cancer about their prognosis. The tool generated real-time prognostic information based on tumor type and stage, age, comorbidity status and lab tests. Our multidisciplinary team included embedded researchers, application developers, user experience experts, and an oncologist leader.This prototype succeeded in establishing proof of principle, but did not reach adoption into actual practice. In pilot testing, oncologists succeeded in generating prognostic information in real time. A few found it helpful in patient encounters, but all identified critical areas for further development before implementation. Generalizable lessons included the need to (1) include a wide range of potential use cases and stakeholders when selecting use cases for such tools; (2) develop talking points for clinicians to explain results from predictive tools to patients; (3) develop ways to reduce lag time between events and data availability; and (4) keep the options presented in the user interface very simple. This case demonstrates that embedded researchers can lead collaborations using EMR-derived data to create systems for real-time personalized patient counseling, and highlights challenges that such teams can anticipate.

Towards a Responsible Transition to Learning Healthcare Systems in Precision Medicine: Ethical Points to Consider

Learning healthcare systems have recently emerged as a strategy to continuously use experiences and outcomes of clinical care for research purposes in precision medicine. Although it is known that learning healthcare transitions in general raise important ethical challenges, the ethical ramifications of such transitions in the specific context of precision medicine have not extensively been discussed. Here, we describe three levers that institutions can pull to advance learning healthcare systems in precision medicine: (1) changing testing of individual variability (such as genes); (2) changing prescription of treatments on the basis of (genomic) test results; and/or (3) changing the handling of data that link variability and treatment to clinical outcomes. Subsequently, we evaluate how patients can be affected if one of these levers are pulled: (1) patients are tested for different or more factors than before the transformation, (2) patients receive different treatments than before the transformation and/or (3) patients’ data obtained through clinical care are used, or used more extensively, for research purposes. Based on an analysis of the aforementioned mechanisms and how these potentially affect patients, we analyze why learning healthcare systems in precision medicine need a different ethical approach and discuss crucial points to consider regarding this approach.

Comparison of an oncology clinical decision-support system's recommendations with actual treatment decisions

OBJECTIVE

IBM(R) Watson for Oncology (WfO) is a clinical decision-support system (CDSS) that provides evidence-informed therapeutic options to cancer-treating clinicians. A panel of experienced oncologists compared CDSS treatment options to treatment decisions made by clinicians to characterize the quality of CDSS therapeutic options and decisions made in practice.

METHODS

This study included patients treated between 1/2017 and 7/2018 for breast, colon, lung, and rectal cancers at Bumrungrad International Hospital (BIH), Thailand. Treatments selected by clinicians were paired with therapeutic options presented by the CDSS and coded to mask the origin of options presented. The panel rated the acceptability of each treatment in the pair by consensus, with acceptability defined as compliant with BIH's institutional practices. Descriptive statistics characterized the study population and treatment-decision evaluations by cancer type and stage.

RESULTS

Nearly 60% (187) of 313 treatment pairs for breast, lung, colon, and rectal cancers were identical or equally acceptable, with 70% (219) of WfO therapeutic options identical to, or acceptable alternatives to, BIH therapy. In 30% of cases (94), 1 or both treatment options were rated as unacceptable. Of 32 cases where both WfO and BIH options were acceptable, WfO was preferred in 18 cases and BIH in 14 cases. Colorectal cancers exhibited the highest proportion of identical or equally acceptable treatments; stage IV cancers demonstrated the lowest.

CONCLUSION

This study demonstrates that a system designed in the US to support, rather than replace, cancer-treating clinicians provides therapeutic options which are generally consistent with recommendations from oncologists outside the US.

Standardizing Chemotherapy Regimen Nomenclature: A Proposal and Evaluation of the HemOnc and National Cancer Institute Thesaurus Regimen Content

PURPOSE

Due to decades of nonstandardized approaches to the naming of chemotherapy regimens, representation in electronic health records and secondary systems is highly variable. This hampers efforts to understand patterns of chemotherapy usage at the population level. In this article, we describe a proposal for rules to standardize the nomenclature of chemotherapy regimens and illustrate applications of these rules.

METHODS

Through our experience with building HemOnc.org, which has been under construction since 2011, we formulated a set of guidelines and recommendations for the standard representation of chemotherapy regimen names. We then performed a mapping between the HemOnc and National Cancer Institute Thesaurus vocabulary’s regimens and evaluated conformance with the naming conventions. Finally, we assembled a database of acronyms and names for multiple myeloma regimens to illustrate the scope of the problem.

RESULTS

For the first use case, 242 of 527 (45.1%) of the regimen names differed. The schema was able to allocate a preferred source for 217 (89.4%) of these regimens. For the second use case, we expanded 130 multiple myeloma regimens to 1,138 unique regimen names and demonstrate ways in which the schema can collapse these into disambiguated, but abbreviated, regimen names.

CONCLUSION

To our knowledge, this is the first proposal to normalize chemotherapy regimen nomenclature. If our recommendations are adopted, we expect that the uniformity of treatment exposure representation in hematology/oncology will increase, which will enable large-scale efforts such as ASCO’s CancerLinQ to achieve better standardization.

OSIRIS: A Minimum Data Set for Data Sharing and Interoperability in Oncology

PURPOSE

Many institutions throughout the world have launched precision medicine initiatives in oncology, and a large amount of clinical and genomic data is being produced. Although there have been attempts at data sharing with the community, initiatives are still limited. In this context, a French task force composed of Integrated Cancer Research Sites (SIRICs), comprehensive cancer centers from the Unicancer network (one of Europe's largest cancer research organization), and university hospitals launched an initiative to improve and accelerate retrospective and prospective clinical and genomic data sharing in oncology.

MATERIALS AND METHODS

For 5 years, the OSIRIS group has worked on structuring data and identifying technical solutions for collecting and sharing them. The group used a multidisciplinary approach that included weekly scientific and technical meetings over several months to foster a national consensus on a minimal data set.

RESULTS

The resulting OSIRIS set and event-based data model, which is able to capture the disease course, was built with 67 clinical and 65 omics items. The group made it compatible with the HL7 Fast Healthcare Interoperability Resources (FHIR) format to maximize interoperability. The OSIRIS set was reviewed, approved by a National Plan Strategic Committee, and freely released to the community. A proof-of-concept study was carried out to put the OSIRIS set and Common Data Model into practice using a cohort of 300 patients.

CONCLUSION

Using a national and bottom-up approach, the OSIRIS group has defined a model including a minimal set of clinical and genomic data that can be used to accelerate data sharing produced in oncology. The model relies on clear and formally defined terminologies and, as such, may also benefit the larger international community.

Toward Modernization of Geriatric Oncology by Digital Health Technologies

The number of older adults with cancer is increasing. Over the past 3 decades, geriatric oncology research has focused on improving the assessment of frailty and fitness of older adults with cancer as well as methods of improving their outcomes. At the same time, advances in digital health technologies have opened new frontiers for reaching this goal. Digital health technologies encompass a variety of solutions, from electronic patient-reported outcomes (ePROs) to Big Data and wireless sensors. These solutions have the potential to further advance our understanding of patients' experiences during cancer treatment. Whereas the data on the feasibility and utility of such solutions in the care of older adults with cancer are limited, interest from digital health oncology researchers to further explore the benefits of these products is increasing. In this article, we describe the focus of geriatric oncology, the rationale behind the need to explore digital health technologies in this setting, and emerging data and ongoing studies, as well as provide guidelines for proper selection, implementation, and testing of digital health solutions in the context of geriatric oncology.

Governance of a Learning Health Care System for Oncology: Patient Recommendations

PURPOSE

The learning health care system (LHS) was designed to enable real-time learning and research by harnessing data generated during patients' clinical encounters. This novel approach begets ethical questions regarding the oversight of users and uses of patient data. Understanding patients' perspectives is vitally important.

MATERIALS AND METHODS

We conducted democratic deliberation sessions focused on CancerLinQ, a real-world LHS. Experts presented educational content, and then small group discussions were held to elicit viewpoints. The deliberations centered around whether policies should permit or deny certain users and uses of secondary data. De-identified transcripts of the discussions were examined by using thematic analysis.

RESULTS

Analysis identified two thematic clusters: expectations and concerns, which seemed to inform LHS governance recommendations. Participants expected to benefit from the LHS through the advancement of medical knowledge, which they hoped would improve treatments and the quality of their care. They were concerned that profit-driven users might manipulate the data in ways that could burden or exploit patients, hinder medical decisions, or compromise patient-provider communication. It was recommended that restricted access, user fees, and penalties should be imposed to prevent users, especially for-profit entities, from misusing data. Another suggestion was that patients should be notified of potential ethical issues and included on diverse, unbiased governing boards.

CONCLUSION

If patients are to trust and support LHS endeavors, their concerns about for-profit users must be addressed. The ethical implementation of such systems should consist of patient representation on governing boards, transparency, and strict oversight of for-profit users.

Harnessing data science to advance radiation oncology

Radiation oncology, a major treatment modality in the care of patients with malignant disease, is a technology‐ and computer‐intensive medical specialty. As such, it should lend itself ideally to data science methods, where computer science, statistics, and clinical knowledge are combined to advance state‐of‐the‐art care. Nevertheless, data science methods in radiation oncology research are still in their infancy and successful applications leading to improved patient care remain scarce. Here, we discuss data interoperability issues within and across organizational boundaries that hamper the introduction of big data and data science techniques in radiation oncology. At the semantic level, creating common underlying models and codification of the data, including the use of data elements with standardized definitions, an ontology, remains a work in progress. Methodological issues in data science and in the use of large population‐based health data registries are identified. We show that data science methods and big data cannot replace randomized clinical trials in comparative effectiveness research by reviewing a series of instances where the outcomes of big data analyses and randomized trials are at odds. We also discuss the modern wave of machine learning and artificial intelligence as represented by deep learning and convolutional neural networks. Finally, we identify promising research avenues and remain optimistic that the data sources in radiation oncology can be linked to yield important insights in the near future. We argue that data science will be a valuable complement to, but not a replacement of, the traditional hypothesis‐driven translational research chain and the randomized clinical trials that form the backbone of evidence‐based medicine.

Patient Preferences Regarding Informed Consent Models for Participation in a Learning Health Care System for Oncology

PURPOSE

The expansion of learning health care systems (LHSs) promises to bolster research and quality improvement endeavors. Stewards of patient data have a duty to respect the preferences of the patients from whom, and for whom, these data are being collected and consolidated.

METHODS

We conducted democratic deliberations with a diverse sample of 217 patients treated at 4 sites to assess views about LHSs, using the example of CancerLinQ, a real-world LHS, to stimulate discussion. In small group discussions, participants deliberated about different policies for how to provide information and to seek consent regarding the inclusion of patient data. These discussions were recorded, transcribed, and de-identified for thematic analysis.

RESULTS

Of participants, 67% were female, 61% were non-Hispanic Whites, and the mean age was 60 years. Patients' opinions about sharing their data illuminated 2 spectra: trust/distrust and individualism/collectivism. Positions on these spectra influenced the weight placed on 3 priorities: promoting societal altruism, ensuring respect for persons, and protecting themselves. In turn, consideration of these priorities seemed to inform preferences regarding patient choices and system transparency. Most advocated for a policy whereby patients would receive notification and have the opportunity to opt out of including their medical records in the LHS. Participants reasoned that such a policy would balance personal protections and societal welfare.

CONCLUSION

System transparency and patient choice are vital if patients are to feel respected and to trust LHS endeavors. Those responsible for LHS implementation should ensure that all patients receive an explanation of their options, together with standardized, understandable, comprehensive materials.

Toward a More Precise Future for Oncology

Prospective molecular characterization of cancer has enabled physicians to define the genomic changes of each patient's tumor in real time and select personalized therapies based on these detailed portraits. Despite the promise of such an approach, previously unrecognized biological and therapeutic complexity is emerging. Here, we synthesize lessons learned and discuss the steps required to extend the benefits of genome-driven oncology, including proposing strategies for improved drug design, more nuanced patient selection, and optimized use of available therapies. Finally, we suggest ways that next-generation genome-driven clinical trials can evolve to accelerate our understanding of cancer biology and improve patient outcomes.

Architecture and Implementation of a Clinical Research Data Warehouse for Prostate Cancer

Background

Electronic health record (EHR) based research in oncology can be limited by missing data and a lack of structured data elements. Clinical research data warehouses for specific cancer types can enable the creation of more robust research cohorts.

Methods

We linked data from the Stanford University EHR with the Stanford Cancer Institute Research Database (SCIRDB) and the California Cancer Registry (CCR) to create a research data warehouse for prostate cancer. The database was supplemented with information from clinical trials, natural language processing of clinical notes and surveys on patient-reported outcomes.

Results

11,898 unique prostate cancer patients were identified in the Stanford EHR, of which 3,936 were matched to the Stanford cancer registry and 6153 in the CCR. 7158 patients with EHR data and at least one of SCIRDB and CCR data were initially included in the warehouse.

Conclusions

A disease-specific clinical research data warehouse combining multiple data sources can facilitate secondary data use and enhance observational research in oncology.