Incorporating Integrated Diagnostics into Precision Oncology Care Proceedings of a Workshop (2024) / Chapter Skim
Currently Skimming:
Proceedings of a Workshop
Proceedings of a Workshop
Pages 1-88
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 1... ...
No uniform strategy currently exists, however, to develop, validate, implement, and use integrated diagnostics in cancer care. The National Cancer Policy Forum, in collaboration with the Computer Science and Telecommunications Board and the Board on Human–Systems Integration of the National Academies of Sciences, Engineering, and Medicine, hosted a public workshop on incorporating integrated diagnostics into precision oncology care on March 6 and 7, 2023.
|
From page 2... ...
Speaker presentations and the workshop webcast are archived online.2 OVERVIEW OF THE CURRENT STATUS OF AND VISION FOR INTEGRATED DIAGNOSTICS An Evolving Integrated Data Science Approach to Personalized Oncology Care There is currently no consensus definition of integrated diagnostics, said Kojo Elenitoba-Johnson, inaugural chair of the department of pathology and laboratory medicine and James Ewing Alumni Chair of Pathology at MSK. He referred to Hricak's working definition as "the convergence of imaging, pathology, and laboratory testing, supplemented by advanced information technology, which has enormous potential for revolutionizing the diagnosis and therapeutic management of many diseases, including cancer." 2 See https://www.nationalacademies.org/event/03-06-2023/incorporating-integrated diagnostics-into-precision-oncology-care-a-workshop (accessed May 26, 2023)
|
From page 3... ...
in precision oncology, many clinicians still hesitate to do so in practice. (Choudhury, Elenitoba-Johnson, Krestin, Oyer)
|
From page 4... ...
(Osterman) • Patient-centric user interfaces for integrated diagnostics are needed, using design principles to prioritize the most important information for patient care and actions to consider.
|
From page 5... ...
• Most patients with cancer receive their care in community settings, and disparities in access to high-quality care and new technolo gies persist in many communities outside the catchment area of National Cancer Institute–designated cancer centers or other major academic centers. (Brawley, Oyer, Shulman)
|
From page 6... ...
• Recruit more data scientists to cancer research and care to enhance efficient translation of scientific and technological advances in patient care.
|
From page 7... ...
(Brawley) • Leverage new digital technologies to increase the capacity and effectiveness of the cancer care workforce and improve patient experience and outcomes.
|
From page 8... ...
Access to data from integrated diagnostics can facilitate shared decision making among patients and their clinicians and promote health equity by enabling personalized precision cancer care, she said. For personalized treatment, Elenitoba-Johnson said that no single entity or clinical domain has all the tools or expertise necessary to measure, abstract, and interpret all the necessary data.
|
From page 9... ...
PREPUBLICATION COPY -- Uncorrected Proofs FIGURE 1 Integrated data science approach to personalized treatment. SOURCES: Kojo Elenitoba-Johnson and Hedvig Hricak presentations, March 6, 2023, and N
|
From page 10... ...
. Elenitoba-Johnson explained that MSK provides every patient with a personalized, comprehensive diagnostic assessment based on their MSK-IMPACT tumor testing, which includes "information about actionable mutations that are prognostically relevant." An Expanding Role for AI Elenitoba-Johnson shared several examples of how AI is being leveraged to enhance the capabilities of integrated diagnostics in precision oncology care.
|
From page 11... ...
program.6 Areas of focus include creating "flagship datasets" that are ethically sourced and adhere to the FAIR (findable, accessible, interoperable, and reusable) principles.7 Implementation Challenges Hricak mentioned the exponential growth in diagnostic testing, but noted that testing tends to be siloed, which presents significant challenges for oncology clinicians in assimilating and interpreting the disparate diagnostic data for patient care.
|
From page 12... ...
. Although both integrated diagnostics and clinical decision support tools are used with the goal of reducing medical errors, integrated diagnostics specifically focus on diagnostic errors (NASEM, 2015)
|
From page 13... ...
. Osterman suggested that rates of structured staging at many cancer centers are even lower.
|
From page 14... ...
The HL7 reporting standards have been widely adopted by genomic testing laboratories, EHR vendors, and health care systems, Osterman said, and the number of institutions receiving genomic data from vendors in structured format continues to increase. Achieving interoperability means these data also are available for other diagnostic uses (e.g., clinical decision support, recommending clinical trials, population health)
|
From page 15... ...
. Larry Shulman, professor of medicine and director of the Center for Global Cancer Medicine at the University of Pennsylvania Abramson Cancer Center, emphasized the importance of structuring patient-reported outcomes and the clinician's overall assessment of a patient for inclusion in integrated diagnostics.
|
From page 16... ...
. EFFORTS TO DEVELOP, IMPLEMENT, AND USE INTEGRATED DIAGNOSTICS Representatives from academic medical centers, industry, and large health care organizations shared their perspectives and lessons learned from efforts to develop, implement, and use integrated diagnostics in clinical practice.
|
From page 17... ...
Referring clinicians expressed concerns about ceding control of diagnostic decision making for their patients. Krestin explained that Erasmus MC began by implementing integrated diagnostics for several complex diseases for which the institution expected particular benefit -- for patients and the health care system.
|
From page 18... ...
, and integrating it at the relevant laboratory. As an example of implementing integrated diagnostics in practice, Lennerz described the testing approach to determine eligibility for targeted therapy among patients with lung cancer.
|
From page 19... ...
Lennerz summarized that integrated diagnostics at CID value "indi viduals and interactions over processes and tools, sustainability over quick wins, specific journeys rather than general application, payer operations in addition to innovation-driven funding streams, [and] patient centricity rather than solely a scholarly exercise." Integrated Diagnostics as the Fourth Revolution in Pathology Manuel Salto-Tellez, professor of integrative pathology at the Institute for Cancer Research, London (ICR)
|
From page 20... ...
. Salto-Tellez shared that the Royal Marsden Hospital and ICR have jointly launched the Integrated Discovery and Diagnostics initiative, which merges genomic, histologic, radiologic, and clinical data, health care economics data, and research and development data from clinical trials.
|
From page 21... ...
"Diagnostics is critical to precision medicine," Schnall concluded, and "closer integration of radiology and pathology will improve the diagnostic process." Integrated Diagnostics for Earlier Detection of Cancer Garry Gold, Stanford Medicine Professor of Radiology and Biomedical Imaging and chair of the Department of Radiology at Stanford University, discussed the wide-ranging applications of integrated diagnostic approaches to early detection of cancer, when treatment is more likely to be successful. Gold first described several studies by the late Sam Gambhir, a founder of the Canary Center at Stanford for Cancer Early Detection and pioneer in the integration of radiation and pathology.
|
From page 22... ...
Achieving the Vision of Integrated Diagnostics Several panelists discussed potential actions that could help realize the vision of integrated diagnostics in precision cancer care. "It's early days in integrated diagnostics," Salto-Tellez said, with a need for "significant and specific investment in this area." Lennerz encouraged an increased focus on regulatory science and actively engaging with regulators on issues related to practical implementation (e.g., the data and performance metrics needed for radiologists to fully integrate AI)
|
From page 23... ...
The results of self-supervised learning would need to feed into a harmonized user interface, which Comaniciu referred to as a "diagnostic cockpit," with access to clinical information, the results of AI analyses, advanced data visualization, actionable reporting, and research and innovation. Comaniciu pointed out that structuring data has been the general approach to managing complex clinical data so it can be integrated.
|
From page 24... ...
Comaniciu presented several examples of AI-powered diagnostics for oncology, such as cancer risk prediction, brain tumor analysis and metastasis digitation and tracking, lung cancer screening via chest CT, assessment of pulmonary lesions via chest X-ray, breast cancer screening, prostate MRI, and analysis of cardiotoxicity. He also highlighted AI tumor fingerprinting, an approach under development to create a digital biopsy of molecular changes in tumors by integrating digital pathology, proteomic, metabolomics, and genomic profiling.
|
From page 25... ...
are also fed back to radiology, pathology, and omics functions and used to update population health and probability data. The vision for integrated diagnostics, Kronander said, is "faster and b etter diagnosis, improved patient care, built in feedback loops [for]
|
From page 26... ...
26 HEALTH GRID Real-Time Prescription Benefits National Telehealth Providers Specialty Home Health Dental Life Insurance Pharmacy Employer Health Standalone Specialties Home Infusions Hospice Behavioral Health Social Care Retail Clinics Long Term Care Specialty Diagnostics Long Term Acute Care Life Sciences Outpatient Inpatient PREPUBLICATION COPY -- Uncorrected Proofs Rehab Urgent Care Payers FIGURE 2 Examples of where patient data are generated across the health grid. SOURCE: Nick Trentadue presentation, March 6, 2023.
|
From page 27... ...
Trentadue emphasized that for integrated diagnostics to optimize the power of data, the information should be discrete and actionable and follow standards that enable interoperability and support bidirectional flow among the care team, regardless of data system: this ensures that "the right person, at the right time, has all the appropriate information for diagnosis as well as for treatment." Trentadue also emphasized the importance of ontology21 when developing ML models, because a lack of clear ontology could lead to unexpected outcomes from the models, and actionable decision support, in which diagnosticians, treating clinicians, and patients have the information they need, readily available, to support decision making. Integrating Patient Goals and Treatment Outcomes Data Aanand Naik, professor and the Nancy & Vincent Guinee Chair of eriatrics at the University of Texas Health Science Center, Houston, School G of Public Health and Consortium on Aging, highlighted the need to incorporate patient goals and health outcomes (including the potential for adverse effects)
|
From page 28... ...
Kronander noted the ongoing research on explainable AI,22 emphasizing that AI should not be fully independent; humans need to be in the loop to identify instances when AI does not work. Perspectives from Large Health Care Organizations Precision Oncology in VA Medical Centers Gil Alterovitz, director of the National AI Institute (NAII)
|
From page 29... ...
, or find appropriate clinical trials based on information in their medical record.24 In closing, he said that the VA is looking for opportunities to leverage its data gathering and analysis capacity in collaborations that advance the development and use of AI in precision cancer care. Precision Oncology at University of California Health Atul Butte, the Priscilla Chan and Mark Zuckerberg Distinguished Professor and director of the Baker Computational Health Sciences Institute at the University of California, San Francisco, and chief data scientist for University of California Health (UCH)
|
From page 30... ...
More than 100,000 patients with cancer receive care at a UCH comprehensive cancer center each year, noted Butte. The same UC-wide data warehouse contains demographic, information, including information on a patient's cancer diagnosis, insurance coverage and social risk, and more than 32,000 cancer genomic reports.
|
From page 31... ...
Converting unstructured to structured data remains a challenge, but there is potential role for AI. Other challenges noted by Butte include ongoing resistance to cross-campus clinical trials despite incentives and central IRBs and a lack of precision cancer care options for patients.
|
From page 32... ...
This cycle results in iterative improvement to the care delivery system. Levy described Rush University's experience implementing a learning health care system for breast cancer risk management to address the challenges of evidence generation for breast cancer screening.
|
From page 33... ...
• Risk assessment guidelines • Risk based supplemental • Risk assessment questionnaire screening guidelines and calculation • Risk management guidelines • Risk reporting and follow up recommendations in mammogram reports • Navigator for high-risk patients • High-risk breast clinic including genetic results documentation • Uptake of guidelines • Referral workflows • Automated calculation of cancer detection rates for supplemental screening and risk group sub-analysis PREPUBLICATION COPY -- Uncorrected Proofs FIGURE 3 Implementation of a breast cancer risk management learning system. SOURCE: Mia Levy presentation, March 6, 2023.
|
From page 34... ...
She highlighted the use of screening test order sets that a clinician selects based on patient characteristics, including breast cancer risk factors, such as breast density and genetics. The next steps in the diagnostic pathway are driven by the breast imaging center, she said.
|
From page 35... ...
This data void presents a challenge for precision diagnostics developers looking to take products to scale in clinical care. Verily is working to develop an evidence generation infrastructure with better continuous data collection after approval, closing the data gap between data collected during clinical research and data collected as part of clinical care.
|
From page 36... ...
Opportunities to Leverage EHRs for Clinical Evidence Generation Diagnostic testing affects all aspects of medical care, from screening and diagnosis to selection of treatment, follow-up, and surveillance, explained Neal Meropol, vice president of Research Oncology at Flatiron Health and chair of 28 The Eastern Cooperative Oncology Group performance status scale helps define a patient's overall ability to function after treatment. The Karnofsky Performance Status scale seeks to determine a patient's impairment after treatment.
|
From page 37... ...
Meropol reviewed a few of the challenges to evidence generation for integrated diagnostics. Generally, the level of investment in evidence generation for diagnostics is lower than for drugs.
|
From page 38... ...
. Meropol described a case study in which Flatiron Health and collabora tors used centralized, intentional EHR-based data collection and processing to support a prospective, observational study among patients with non-small cell lung cancer.31 Circulating tumor DNA was obtained at prespecified time points to generate a dataset of integrated evidence that included genomic data, clinical data, and digital pathology, he said.
|
From page 39... ...
PREPUBLICATION COPY -- Uncorrected Proofs FIGURE 4 Integrated real-world evidence generation platform. SOURCES: Neal Meropol presentation March 6, 2023 (Bourla and Meropol, 2021)
|
From page 40... ...
, Howard Hughes Medical Institute investigator and Marie-Josée and Henry R Kravis Chair in the Human Oncology and Pathogenesis Program at MSK, discussed lessons for evidence generation from his experience with AACR's Project GENIE.32 The project was launched in 2015, following an agreement among eight cancer centers to aggregate their genomic and clinical data in a public registry.
|
From page 41... ...
Sawyers showed data on checkpoint inhibitor treatment for patients with lung cancer, which demonstrated that determining PFS using PRISSMM is comparable to doing so with the RECIST criteria, which assess disease status based on imaging data. Sawyers shared several examples of how Project GENIE data are being used, such as to generate external control cohorts for rare disease research (Scharpf et al., 2022; Smyth et al., 2020)
|
From page 42... ...
Mark Stewart, vice president of science policy at Friends of Cancer Research, raised the issue of variability in the performance of different diagnostic assays with the same intended use and how that might affect harmonization and interpretability of data from different institutions. Levy responded that Project GENIE datasets include data from different assays, and the ability to ask a particular question will be limited by whether a gene was included in particular assays.
|
From page 43... ...
DESIGN AND USE OF INTEGRATED DIAGNOSTICS To realize the potential of integrated diagnostics for precision oncology care, many speakers noted that institutions will need to consider implementation of appropriate tools and technologies to ensure clinician adoption. A range of design and use challenges were discussed, and many speakers highlighted potential solutions to promote acceptance and uptake of integrated diagnostics.
|
From page 44... ...
Thai noted the patient privacy and data security concerns associated with ML and described several types of adversarial attacks that can occur in AI design. The training phase can have "poisoning" of the training data with data intended to alter model performance.
|
From page 45... ...
Through the DMT approach, physicians with expertise in clinical pathology, genetics, radiology, anatomic pathology, and history and physical exam are able to integrate all relevant diagnostic and clinical data to provide the order ing clinician with a diagnostic testing strategy and provide an interpretation of the test results. Laposata said the DMT approach has been implemented at UTMB for testing associated with coagulation, toxicology, autoimmunity, complex transfusions, pharmacogenomics, anemia, liver disease, COVID-19 infection, and others.
|
From page 46... ...
42 • OncoKB (a precision oncology knowledge base) 43 • Warren Alpert Center for Digital and Computational Pathology44 Shah said that the understanding of cancer biology is informed by experimental data on cancer progression and drug resistance, the tumor micro environment, cellular phenotypes, interactions among tumor cells and immune cells, and multiomics data.
|
From page 47... ...
Implementing Integrated Diagnostics into Precision Oncology Care David Dorr, chief research information officer and vice chair of Medical Informatics and Clinical Epidemiology at Oregon Health & Science University (OHSU) School of Medicine, defined health informatics as the science of the use of data, information, and knowledge to improve health.45 Dorr discussed ways in which the multidisciplinary field of health informatics 45 See https://amia.org/about-amia/why-informatics/informatics-research-and-practice (accessed January 25, 2024)
|
From page 48... ...
Dorr discussed the role of implementation science in promoting the uptake of integrated diagnostics and preventing unintended consequences. He mentioned the Consolidated Framework for Implementation Research as an example of one effective approach (Damschroder et al., 2022)
|
From page 49... ...
Researchers are working to identify vulnerable populations through risk stratification and tailor care to meet their needs. OHSU is "eager to implement advanced algorithms," he said, "but also cautious" given the pros, cons, and challenges for deploying deep learning methods in clinical care (Egger et al., 2022; NASEM, 2022)
|
From page 50... ...
but also noted the challenges of building structures for big data that can help facilitate patient care today and retrieval and use in the future, as tools and technologies advance. When working to create integrated systems, Robison concluded, it is important to "deeply understand the needs of the clinician" and structure systems that eliminate silos and "work with the cognitive flows that happen at that point of care." Trust and Acceptance of AI in Clinical Settings Despite the growing evidence supporting the use of AI in precision oncology to streamline the workflow, accelerate diagnosis, and improve the quality of patient care, many clinicians still hesitate to use it in practice, said Avishek Choudhury, assistant professor of Industrial and Management Systems Engineering at West Virginia University's Benjamin M
|
From page 51... ...
Given initial uptake in routine clinical care, feedback on patient outcomes and AI performance (e.g., ethics, privacy, generalizability) affect the evolution of trust.
|
From page 52... ...
Risk Communication and Decision Support Patient perception and understanding of health risks vary, said Mary Politi, professor in the Department of Surgery at Washington University School of Medicine. Clinician abilities to explain clinical uncertainty to their patients and manage patient care in the context of uncertainty can also vary.
|
From page 53... ...
Politi shared several examples of clinical decision support tools that employ these risk communication principles. One tool, to predict the risk of sentinel node metastasis in melanoma, is designed for the patient encounter.
|
From page 54... ...
The Observational Health Data Sciences and Informatics (OHDSI) 50 federated dataset, for example, includes data from 50 See https://www.ohdsi.org/ (accessed September 5, 2023)
|
From page 55... ...
Overcoming Design and Use Challenges Many speakers suggested potential opportunities for overcoming the challenges related to designing and using integrated diagnostics in precision cancer care. Robison, referencing the challenge of EHR organization of information by type (e.g., laboratory data are in one location, images are in another)
|
From page 56... ...
REGULATORY OVERSIGHT AND INSURANCE COVERAGE OF INTEGRATED DIAGNOSTICS Several speakers discussed the importance of achieving regulatory clearance or approval for clinical use and establishing coverage and reimbursement mechanisms for the adoption of integrated diagnostics. Pathways for Regulatory Review of Integrated Diagnostics Reena Philip, associate director for Biomarkers and Precision Oncology at the FDA Oncology Center of Excellence, provided an overview of the current FDA review framework for IVDs, radiological devices, and AI-based digital pathology and radiological devices.
|
From page 57... ...
clearance; and a colon cancer screening test or a companion diagnostic test52 would be Class III requiring premarket approval. 52 A companion diagnostic, usually an in vitro diagnostic, is a medical device that provides necessary information on how to use a drug or biologic product safely and effectively.
|
From page 58... ...
. 55 See https://paige.ai/ (accessed September 5, 2023)
|
From page 59... ...
. 59 See https://www.fda.gov/news-events/press-announcements/fda-releases-artificial intelligencemachine-learning-action-plan (accessed January 25, 2024)
|
From page 60... ...
Although standard benefits generally include diagnostic testing and pathology imaging, diagnostics that incorporate AI might not be covered, and creating a new category for certain integrated diagnostics might be needed. • Coding.
|
From page 61... ...
. "If integrated diagnostics deliver greater value in cancer care, then adoption may be accelerated through value-based care models," Malin observed.
|
From page 62... ...
She described three novel algorithmic solutions used to develop two validated risk prediction models, Mirai and Sybil, to ensure the models are robust. Mirai uses a patient's screening mammogram to predict their risk of breast cancer within 5 years (Yala et al., 2021, 2022a, 2022b)
|
From page 63... ...
However, if a training dataset contains a minority population, the algorithm will attempt to optimize for the majority dataset, leading to underperformance on the minority dataset, Barzilay said. The solution, she said, was "forcing the algorithm to see the majority and minority … in the same way, learning the representation directly, so it eliminates unnecessary differences between them and focuses on improving accuracy across this population." Distributional Shift Detection Solution: Learning to Split for Automatic Bias Detection Barzilay said that another challenge is that the existence of bias in a training dataset is often unknown.
|
From page 64... ...
She noted that clinical trials in breast and lung cancer are underway to assess the extent to which an increase in predictive accuracy impacts longterm patient outcomes. Integrated Diagnostics in Community-Based Settings of Care Eighty-five percent of people in the United States receive their cancer care in community settings, said Randall Oyer, clinical professor of medicine at the Perelman School of Medicine and executive medical director of the Ann B
|
From page 65... ...
, Community Clinical Oncology Program in 1983, Medicare Modernization Act, NCORP in 2011, and now integrated diagnostics. Oyer emphasized the potential of integrated diagnostics to advance cancer care but said that "less than 15 percent of research is translated into practice," and translation can take 17 years on average (Jørgensen, 2022)
|
From page 66... ...
Oyer added that in order to ensure equity and representation, members of the cancer research community need to collaborate and build knowledge by collecting and sharing patient data, including the creation of a data bank, similar to the collection of tissue for a tissue bank. Oyer also offered several suggestions to facilitate equitable access to precision diagnosis and clinical trials that improve outcomes for every patient with cancer in every community, such as expanding the capacity and representativeness of the oncology workforce, including diagnosticians.
|
From page 67... ...
Subpar care can be a result of inaccessible, inadequate, or inappropriate screening, diagnostics, treatment, or therapy. These populations are also unlikely to have access to the newest tools and technologies in cancer care.
|
From page 68... ...
. Drawing from his experience as director of a cancer center in a community safety net hospital, Brawley said that implementing lung cancer screening in a resource-poor setting, for example, can result in increased wait times for CT scans, thereby worsening overall quality of care for all patients.
|
From page 69... ...
Shulman pointed out that most smaller hospitals in rural areas are not part of a hub-and-spoke or other network, and these hospitals often have the largest disparities in care. Drawing on Winn's comment about data deserts, Oyer and Shulman noted that said these rural areas are "deserts" outside of the catchment areas of NCI-designated cancer centers and called for a national effort to 70 See https://www.cancer.gov/publications/dictionaries/cancer-terms/def/tamoxifen citrate (accessed September 5, 2023)
|
From page 70... ...
CURRENT FEDERAL INITIATIVES IN PRECISION CANCER CARE Two keynote speakers discussed current initiatives at NCI and the Advanced Research Project Agency for Health (ARPA-H) to advance precision oncology care.
|
From page 71... ...
characteristics, Harris said. Data drawn from NCI-MATCH are being used to study, for example: • The distribution of correlates of health disparities across the NCI MATCH cohort; • The association of a patient's clinical status, diagnosis, and treatment history with correlates of health disparities; • Whether potentially modifiable risk factors, such as excess body weight or smoking, differ by correlates of health disparities; and • Whether there are any associations of correlates of health disparities with tumor molecular characteristics.
|
From page 72... ...
. ARPA-H and Cancer Moonshot Susan Coller Monarez, deputy director of ARPA-H, provided a brief overview of the agency (see Box 5)
|
From page 73... ...
PROCEEDINGS OF A WORKSHOP 73 BOX 5 Overview of ARPA-H Features of ARPA-H • Independent federal research and development funding agency reporting to the Secretary of the U.S. Department of Health and Human Services and situated within the National Institutes of Health.
|
From page 74... ...
9. To ensure equitable access for all people, how will cost, acces sibility, and user experience be addressed?
|
From page 75... ...
Harris noted that NIH recently updated its data sharing policy77 and under the new policy, "all molecular data and clinical data must be shared at the end of the study." Data from NCI grantees and other NCI programs are accessible through the Cancer Research Data Commons.78 Monarez said ARPA-H is developing its data sharing policies, which will be in alignment with the Public Access Policy 77 See https://sharing.nih.gov/data-management-and-sharing-policy/about-data- management-and-sharing-policies/data-management-and-sharing-policy-overview#after (accessed January 31, 2024)
|
From page 76... ...
Hricak said other considerations highlighted by many speakers included improving interoperability of data systems across clinical disciplines; implementing data standards, synoptic operative reports, and a lexicon to convey the degree of diagnostic certainty; facilitating collaboration to transition image annotation and segmentation from manual to automated; fostering a culture of data sharing; restructuring reimbursement to cover the diagnosis versus diagnostic testing procedures; scaling up precision diagnostics to reach broader populations; and leveraging institutional governance to adopt integrated diagnostics within clinical care. Highlighting Insights from Academia, Industry, and Health Care Organizations Nancy Davidson, executive vice president for Clinical Affairs at the Fred Hutchinson Cancer Center and Raisbeck Endowed Chair for Collaborative Cancer Research at the University of Washington, highlighted perspectives from representatives of academic medical centers, industry, and large health care organizations.
|
From page 77... ...
Many speakers said that EHR data collected during routine care could be leveraged for pragmatic studies and suggested being more intentional about collecting EHR data for prospective clinical trials. Levy said that speakers highlighted the need for "significant investment in evidence generation for analytic validity, clinical validity, and clinical utility" to support regulatory review and implementation of integrated diagnostics in clinical practice.
|
From page 78... ...
In regard to insurance coverage, he noted "there seems to be a reticence … in paying for integrated diagnostics as a stand-alone component of medical care" and suggested that moving toward bundled payments for oncology care might partially address this issue. PREPUBLICATION COPY -- Uncorrected Proofs
|
From page 79... ...
Because most patients with cancer receive their care in the community, participants discussed the need for a hub-and-spoke system to better enable the equitable deployment of integrated diagnostics and the delivery of cancer care, and to build research on dissemination and implementation into product development, she summarized. Nilsen noted that workforce issues were raised, along with the importance of multidisciplinary teams in developing, implementing, and using integrated diagnostics.
|
From page 80... ...
2022b. Harnessing multimodal data integration to advance precision oncology.
|
From page 81... ...
2017. OncoKB: A precision oncology knowledge base.
|
From page 82... ...
2022. Supporting structured data capture for patients with cancer: An initiative of the University of Wisconsin Carbone Cancer Center Survivorship Program to Improve Capture of Malignant Diagnosis and Cancer Staging Data.
|
From page 83... ...
2022. Artificial intelligence for multimodal data integration in oncology.
|
From page 84... ...
2019. Developing and sustaining an effective and resilient oncology careforce.
|
From page 85... ...
paper-based decision support interventions. Journal of Evaluation in Clinical Practice 21(2)
|
From page 86... ...
2022. Multi-omic machine learning predictor of breast cancer therapy response.
|
From page 87... ...
2022. Developing and sustaining an effective and resilient oncology careforce: Opportunities for action.
|
From page 88... ...
2022b. Optimizing risk based breast cancer screening policies with reinforcement learning.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.