Search

PURPOSE: Digital technologies create opportunities for improving consenting processes in cancer care and research. Yet, little is known about the prevalence of electronic consenting, or e-consent, at US cancer care institutions. METHODS: We surveyed institutions in the National Comprehensive Cancer Network about their capabilities for clinical, research, and administrative e-consents; technologies used; telemedicine consents; multilingual support; evaluations; and opportunities and challenges in moving from paper-based to electronic processes. Responses were summarized across responding institutions. RESULTS: Twenty-five institutions completed the survey (81% response rate). Respondents were from all census regions and included freestanding and matrix cancer centers. Twenty (80%) had e-consent capabilities, with variability in the extent of adoption: One (5%) had implemented e-consent for all clinical, research, and administrative needs while 19 (95%) had a mix of paper and electronic consenting. Among those with e-consent capabilities, the majority (14 of 20, 70%) were using features embedded in their electronic health record. Most had a combination of paper and e-consenting for clinical purposes (18, 72%). About two-thirds relied entirely on paper for research consents (16, 64%) but had at least some electronic processes for administrative consents (15, 60%). Obstacles to e-consenting included challenges with procuring or maintaining hardware, content management, workflow integration, and digital literacy of patients. Successes included positive user experiences, workflow improvements, and better record-keeping. Only two of 20 (10%) respondents with e-consent capabilities had evaluated the impact of automating consent processes. CONCLUSION: E-consent was prevalent in our sample, with 80% of institutions reporting at least some capabilities. Further progress is needed for the benefits of e-consenting to be realized broadly. Digital technologies can improve consenting processes. We surveyed National Comprehensive Cancer Network member institutions about electronic consenting capabilities and experiences. Twenty-five (81%) completed the survey. Twenty (80%) had e-consent capabilities, mostly embedded in their electronic health record (14, 70%). One (5%) had e-consent for all clinical, research, and administrative needs while 19 (95%) had a mix of paper and e-consenting. Obstacles included challenges procuring/maintaining hardware, content management, workflow integration, and patients' digital literacy. Successes included user satisfaction, workflow improvements, and better record-keeping. Only two had formally evaluated their e-consent processes. Further progress is needed to broadly realize e-consent's benefits. [ABSTRACT FROM AUTHOR]

Progress toward improvement in cancer therapy relies on clinical trials. Yet, only a minority of eligible patients with cancer enroll as a result of multiple barriers at the patient, investigator, center, and national level. However, the rise of the Internet and mobile technology has created a slew of tools with medical applications, from Web sites to apps to social media platforms, all of which may aide clinicians in our quest to improve the clinical research enterprise. SWOG is one of five members in the National Cancer Institute's National Clinical Trials Network--the nation's oldest and largest publicly funded cancer research network--and is taking a leadership role in exploring and testing the promise of digital engagement through the empaneling of the Digital Engagement Committee. This article outlines the mission, principles, and priorities of the Digital Engagement Committee and proposes how this work may inform the use of digital tools for the cancer research community and, hopefully, translate to improved outcomes for our patients. [ABSTRACT FROM AUTHOR]

PURPOSE: Inefficiencies in the clinical trial infrastructure result in protracted trial completion timelines, physician-investigator turnover, and a shrinking skilled labor force and present obstacles to research participation. Taken together, these barriers hinder scientific progress. Technological solutions to improve clinical trial efficiency have emerged, yet adoption remains slow because of concerns with cost, regulatory compliance, and implementation. METHODS: A prospective pilot study that compared regulatory-compliant digital and traditional wet ink paper signatures was conducted over a 6.5-month period in a hospital-based health system. Staff time and effort, error rate, costs, and time to completion were measured. Wilcoxon rank sum tests were used to compare staff time and time to completion. A value analysis was conducted. A survey was administered to measure user satisfaction. RESULTS: There where 96 participants (47 digital, 49 paper), 132 studies included (31 digital, 101 paper), and 265 documents processed (156 digital, 109 paper). A moderate reduction in staff time required to prepare documents for signature was observed (P <.0001). Error rates were reported in 5.1% of digital and 2.8% of paper documents, but this difference was not significant. Discrepancies requiring revisions included incomplete mandatory fields, inaccurate information submitted, and technical issues. A value analysis demonstrated a 19% labor savings with the use of digital signatures. Survey response rate was 57.4% (n = 27). Most participants (85.2%) preferred digital signatures. The time to complete documents was faster with digital signatures compared with paper (P =.0241). CONCLUSION: The use of digital signatures resulted in a decrease in document completion time and regulatory burden as represented by staff hours. Additional cost and time savings and information liquidity could be realized by integrating digital signatures and electronic document management systems. [ABSTRACT FROM AUTHOR]

Purpose: Immediate transfer of patient-reported outcome measures (PROMs) for use in medical consultations is facilitated by electronic assessments. We aimed to describe the rationale and development of Eir version 3 (EirV3), a computer-based symptom assessment tool for cancer, with emphasis on content and user-friendliness. Methods: EirV3's specifications and content were developed through multiprofessional, stepwise, and iterative processes (from 2013 to 2016), with literature reviews on traditional and electronic assessment and classification methods, formative iterative usability tests with end-users, and assessment of patient preferences for paper versus electronic assessments. Results: EirV3 has the following two modules: Eir-Patient for PROMs registration on tablets and Eir-Doctor for presentation of PROMs in a user-friendly interface on computers. Eir-Patient starts with 19 common cancer symptoms followed by specific, in-depth questions for endorsed symptoms. The pain section includes a body map for pain location and intensity, whereas physical functioning, nutritional intake, and well-being are standard questions for all. Data are wirelessly transferred to Eir-Doctor. Symptoms with intensity scores ≥ 3 (on a 0 to 10 scale) are marked in red, with brighter colors corresponding to higher intensity, and supplemented with graphs displaying symptom development over time. Usability results showed that patients and health care providers found EirV3 to be intuitive, easy to use, and relevant. When comparing PROM assessments on paper versus tablets (n = 114), 19% of patients preferred paper, 41% preferred tablets, and 40% had no preference. Median intraclass correlation coefficient between paper and tablets (0.815) was excellent. Conclusion: Iterative test rounds followed by continuous improvements led to a user-friendly, applicable symptom assessment tool, EirV3, developed for and by end-users. EirV3 is undergoing international testing of clinical and cross-cultural adaptability. [ABSTRACT FROM AUTHOR]

Purpose: With the shift in the majority of oncology clinical care in the United States from paper records to electronic health records, researchers need efficient and validated processes to obtain accurate data about the entire treatment history of patients diagnosed with cancer. The objective of this study was to develop and validate an algorithm that is agnostic to the source of data but that can identify specific regimens in the entire course of systemic therapy treatment for patients diagnosed with breast, colorectal, or lung cancer. Methods: A cohort of patients with incident breast, colorectal, and lung cancer were randomly distributed into six groups. The algorithm was iteratively modified, and the performance was assessed until no additional modifications could be identified in the first three groups. The performance of the algorithm was confirmed in the three groups that remained. Results: The final model produced ranges of sensitivity between 97.2% and 100% for first-course systemic therapy across all cancers, with a false-positive rate of 0%. The algorithm matched the exact number of courses and the exact regimens of systemic therapy agents as captured by infusion, pharmacy, and procedure electronic medical record data for all courses of therapy 88% to 100% of the time. Conclusion: Use of our validated algorithm that characterizes entire courses of systemic therapy treatment in patients diagnosed with breast, colorectal, and lung cancer will allow researchers in a variety of settings to conduct comparative effectiveness studies related to the uptake, safety, outcomes, and costs associated with the use of both novel and standard regimens. [ABSTRACT FROM AUTHOR]

PURPOSE: The specific aims of this paper are to (1) develop and operationalize an electronic health record (EHR) data quality framework, (2) apply the dimensions of the framework to the phenotype and treatment pathways of ductal carcinoma in situ (DCIS) using All of Us Research Program data, and (3) propose and apply a checklist to evaluate the application of the framework. METHODS: We developed a framework of five data quality dimensions (DQD; completeness, concordance, conformance, plausibility, and temporality). Participants signed a consent and Health Insurance Portability and Accountability Act authorization to share EHR data and responded to demographic questions in the Basics questionnaire. We evaluated the internal characteristics of the data and compared data with external benchmarks with descriptive and inferential statistics. We developed a DQD checklist to evaluate concept selection, internal verification, and external validity for each DQD. The Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) concept ID codes for DCIS were used to select a cohort of 2,209 females 18 years and older. RESULTS: Using the proposed DQD checklist criteria, (1) concepts were selected and internally verified for conformance; (2) concepts were selected and internally verified for completeness; (3) concepts were selected, internally verified, and externally validated for concordance; (4) concepts were selected, internally verified, and externally validated for plausibility; and (5) concepts were selected, internally verified, and externally validated for temporality. CONCLUSION: This assessment and evaluation provided insights into data quality for the DCIS phenotype using EHR data from the All of Us Research Program. The review demonstrates that salient clinical measures can be selected, applied, and operationalized within a conceptual framework and evaluated for fitness for use by applying a proposed checklist. A Data Quality Framework Applied to ductal carcinoma in situ EHR data. [ABSTRACT FROM AUTHOR]

PURPOSE: Selection of appropriate adjuvant therapy to ultimately reduce the risk of breast cancer (BC) recurrence is a challenge for medical oncologists. Several automated risk prediction models have been developed using retrospective clinical data and have evolved significantly over the years in terms of predictors of recurrence, data usage, and predictive techniques (statistical/machine learning [ML]). METHODS: Following PRISMA guidelines, we performed a systematic literature review of the aforementioned statistical and ML models published between January 2008 and December 2022 through searching five digital databases—PubMed, ScienceDirect, Scopus, Cochrane, and Web of Science. The comprehensive search yielded a total of 163 papers and after a screening process focusing on papers that dealt exclusively with statistical/ML methods, only 23 papers were deemed appropriate for further analysis. We benchmarked the studies on the basis of development, evaluation metrics, and validation strategy with an added emphasis on racial diversity of patients included in the studies. RESULTS: In total, 30.4% of the included studies use statistical techniques, while 69.6% are ML-based. Among these, traditional ML models (support vector machines, decision tree, logistic regression, and naïve Bayes) are the most frequently used (26.1%) along with deep learning (26.1%). Deep learning and ensemble learning provide the most accurate predictions (AUC = 0.94 each). CONCLUSION: ML-based prediction models exhibit outstanding performance, yet their practical applicability might be hindered by limited interpretability and reduced generalization. Moreover, predictive models for BC recurrence often focus on limited variables related to tumor, treatment, molecular, and clinical features. Imbalanced classes and the lack of open-source data sets impede model development and validation. Furthermore, existing models predominantly overlook African and Middle Eastern populations, as they are trained and validated mainly on Caucasian and Asian patients. We traced the advancement of breast cancer recurrence risk prediction models published between 2008 and 2022 in a systematic way that includes both statistical and artificial intelligence models. This review article serves as a guide for practitioners, offering valuable insights on how to effectively incorporate predictive tools into clinical practice. Moreover, it provides researchers with valuable feedback and recommendations to further improve and refine the predictive models. [ABSTRACT FROM AUTHOR]

PURPOSE: Increasing use of immune checkpoint inhibitors (ICIs) in routine cancer care will increase the incidence of immune-related adverse events (irAEs). Systems are needed to support remote monitoring for irAEs. Electronic patient-reported outcome (ePRO) symptom monitoring systems can help monitor and manage symptoms and side effects. We assessed the content and features of ePRO symptom monitoring systems for irAEs, and their feasibility, acceptability, and impact on patient outcomes and health care utilization. METHODS: A systematic literature search was conducted in May 2022 on MEDLINE, Embase, PsycINFO, and Cochrane Central Register of Controlled Trials. Quantitative and qualitative data relevant to the review questions were extracted and synthesized in tables. RESULTS: Seven papers describing five ePRO systems were included. All systems collected PROs between clinic visits. Two of five used validated symptom questionnaires, 3/5 provided prompts to complete questionnaires, 4/5 provided reminders to self-report, and 3/5 provided clinician alerts for severe/worsening side effects. Four of five provided coverage of ≥26/30 irAEs in the ASCO irAE guideline. Feasibility and acceptability were demonstrated with consent rates of 54%-100%, 17%-27% of questionnaires generating alerts, and adherence rates of 74%-75%. One paper showed a reduction in grade 3-4 irAEs, treatment discontinuation, clinic visit duration, and emergency department presentations, while another showed no difference in these outcomes or the rate of steroid use. CONCLUSION: There is preliminary evidence of the feasibility and acceptability of ePRO symptom monitoring for irAEs. However, further studies are needed to confirm the impact on ICI-specific outcomes, such as the frequency of grade 3-4 irAEs and duration of immunosuppression. Suggestions for the content and features of future ePRO systems for irAEs are provided. [ABSTRACT FROM AUTHOR]

PURPOSE: Real-world data (RWD) derived from electronic health records (EHRs) are often used to understand population-level relationships between patient characteristics and cancer outcomes. Machine learning (ML) methods enable researchers to extract characteristics from unstructured clinical notes, and represent a more cost-effective and scalable approach than manual expert abstraction. These extracted data are then used in epidemiologic or statistical models as if they were abstracted observations. Analytical results derived from extracted data in this way may differ from those given by abstracted data, and the magnitude of this difference is not directly informed by standard ML performance metrics. METHODS: In this paper, we define the task of postprediction inference, which is to recover similar estimation and inference from an ML-extracted variable that would be obtained from abstracting the variable. We consider fitting a Cox proportional hazards model that uses a binary ML-extracted variable as a covariate and evaluate four approaches for postprediction inference in this setting. The first two approaches only require the ML-predicted probability, while the latter two additionally require a labeled (human abstracted) validation data set. RESULTS: Our results for both simulated data and EHR-derived RWD from a national cohort demonstrate that we can improve inference from ML-extracted variables by leveraging a limited amount of labeled data. CONCLUSION: We describe and evaluate methods for fitting statistical models using ML-extracted variables subject to model error. We show that estimation and inference is generally valid when using extracted data from high-performing ML models. More complex methods that incorporate auxiliary labeled data provide further improvements. This paper develops novel methodology for using ML-extracted variables in statistical analyses. [ABSTRACT FROM AUTHOR]

PURPOSE: To evaluate natural language processing (NLP) methods to infer metastatic sites from radiology reports. METHODS: A set of 4,522 computed tomography (CT) reports of 550 patients with 14 types of cancer was used to fine-tune four clinical large language models (LLMs) for multilabel classification of metastatic sites. We also developed an NLP information extraction (IE) system (on the basis of named entity recognition, assertion status detection, and relation extraction) for comparison. Model performances were measured by F1 scores on test and three external validation sets. The best model was used to facilitate analysis of metastatic frequencies in a cohort study of 6,555 patients with 53,838 CT reports. RESULTS: The RadBERT, BioBERT, GatorTron-base, and GatorTron-medium LLMs achieved F1 scores of 0.84, 0.87, 0.89, and 0.91, respectively, on the test set. The IE system performed best, achieving an F1 score of 0.93. F1 scores of the IE system by individual cancer type ranged from 0.89 to 0.96. The IE system attained F1 scores of 0.89, 0.83, and 0.81, respectively, on external validation sets including additional cancer types, positron emission tomography-CT ,and magnetic resonance imaging scans, respectively. In our cohort study, we found that for colorectal cancer, liver-only metastases were higher in de novo stage IV versus recurrent patients (29.7% v 12.2%; P <.001). Conversely, lung-only metastases were more frequent in recurrent versus de novo stage IV patients (17.2% v 7.3%; P <.001). CONCLUSION: We developed an IE system that accurately infers metastatic sites in multiple primary cancers from radiology reports. It has explainable methods and performs better than some clinical LLMs. The inferred metastatic phenotypes could enhance cancer research databases and clinical trial matching, and identify potential patients for oligometastatic interventions. Ever thought of using NLP to extract sites of metastases from radiology reports? Read this paper. [ABSTRACT FROM AUTHOR]

PURPOSE: Real-world evidence (RWE)—derived from analysis of real-world data (RWD)—has the potential to guide personalized treatment decisions. However, because of potential confounding, generating valid RWE is challenging. This study demonstrates how to responsibly generate RWE for treatment decisions. We validate our approach by demonstrating that we can uncover an existing adjuvant chemotherapy (ACT) guideline for stage II and III colon cancer (CC)—which came about using both data from randomized controlled trials and expert consensus—solely using RWD. METHODS: Data from the population-based Netherlands Cancer Registry from a total of 27,056 patients with stage II and III CC who underwent curative surgery were analyzed to estimate the overall survival (OS) benefit of ACT. Focusing on 5-year OS, the benefit of ACT was estimated for each patient using G-computation methods by adjusting for patient and tumor characteristics and estimated propensity score. Subsequently, on the basis of these estimates, an ACT decision tree was constructed. RESULTS: The constructed decision tree corresponds to the current Dutch guideline: patients with stage III or stage II with T stage 4 should receive surgery and ACT, whereas patients with stage II with T stage 3 should only receive surgery. Interestingly, we do not find sufficient RWE to conclude against ACT for stage II with T stage 4 and microsatellite instability-high (MSI-H), a recent addition to the current guideline. CONCLUSION: RWE, if used carefully, can provide a valuable addition to our construction of evidence on clinical decision making and therefore ultimately affect treatment guidelines. Next to validating the ACT decisions advised in the current Dutch guideline, this paper suggests additional attention should be paid to MSI-H in future iterations of the guideline. This article demonstrates the value of real-world evidence in constructing a treatment guideline. [ABSTRACT FROM AUTHOR]

Paper describes our development of a web-based tool to make Medicare patient prices for cancer drugs known to their care teams. [ABSTRACT FROM AUTHOR]

PURPOSE: Although there are commonly accepted criteria of what defines quality of health care including cancer care, less is known about what defines quality of mHealth interventions in health care. The aim of this review was to identify how quality of mHealth interventions for cancer survivors is described and measured. METHODS: CINAHL, EmCare, JBI, Medline, SCOPUS, and ProQuest databases from January 2008 to January 2020 were searched. Review papers with search terms related to mobile devices, quality, and cancer relevant to adults with cancer were included. Interventions needed to consist of mHealth technologies, such as mobile applications or short message service, or wearable devices. Title and abstract screening, full-text screening, and data extraction were performed independently by two reviewers. Conflicts were resolved by a third reviewer. Reviews were evaluated for coverage of quality according to six metrics defined by the Institute of Medicine: patient-centeredness, equitability, safety, effectiveness, timeliness, and efficiency. Any additional quality items were recorded. A Measurement Tool to Assess systematic Reviews (AMSTAR) was used to rate the quality of the reviews included. RESULTS: The initial search yielded 766 papers with seven systematic reviews meeting the eligibility criteria. Four papers were of AMSTAR moderate quality, with three of low quality. The median number of quality metrics reported in a review was two (the range was 1-4). Efficacy and safety and timeliness and efficiency were most reported (n = 4), followed by usability (n = 3), equitability and access (n = 2), privacy and security (n = 2), and patient-centeredness (n = 2). CONCLUSION: There is great variability in how quality of mHealth interventions is defined with no reviews addressing all quality metrics. A comprehensive approach to measure quality of mHealth interventions is needed. Quality metrics of mHealth interventions for cancer survivors: variable and limited—standards needed [ABSTRACT FROM AUTHOR]

PURPOSE: Despite advances in molecular therapeutics, few anticancer agents achieve durable responses. Rational combinations using two or more anticancer drugs have the potential to achieve a synergistic effect and overcome drug resistance, enhancing antitumor efficacy. A publicly accessible biomedical literature search engine dedicated to this domain will facilitate knowledge discovery and reduce manual search and review. METHODS: We developed RetriLite, an information retrieval and extraction framework that leverages natural language processing and domain-specific knowledgebase to computationally identify highly relevant papers and extract key information. The modular architecture enables RetriLite to benefit from synergizing information retrieval and natural language processing techniques while remaining flexible to customization. We customized the application and created an informatics pipeline that strategically identifies papers that describe efficacy of using combination therapies in clinical or preclinical studies. RESULTS: In a small pilot study, RetriLite achieved an F 1 score of 0.93. A more extensive validation experiment was conducted to determine agents that have enhanced antitumor efficacy in vitro or in vivo with poly (ADP-ribose) polymerase inhibitors: 95.9% of the papers determined to be relevant by our application were true positive and the application's feature of distinguishing a clinical paper from a preclinical paper achieved an accuracy of 97.6%. Interobserver assessment was conducted, which resulted in a 100% concordance. The data derived from the informatics pipeline have also been made accessible to the public via a dedicated online search engine with an intuitive user interface. CONCLUSION: RetriLite is a framework that can be applied to establish domain-specific information retrieval and extraction systems. The extensive and high-quality metadata tags along with keyword highlighting facilitate information seekers to more effectively and efficiently discover knowledge in the combination therapy domain. [ABSTRACT FROM AUTHOR]

PURPOSE: This discussion paper outlines challenges and proposes solutions for successfully implementing prediction models that incorporate patient-reported outcomes (PROs) in cancer practice. METHODS: We organized a full-day multidisciplinary meeting of people with expertise in cancer care delivery, PRO collection, PRO use in prediction modeling, computing, implementation, and decision science. The discussions presented here focused on identifying challenges to the development, implementation and use of prediction models incorporating PROs, and suggesting possible solutions. RESULTS: Specific challenges and solutions were identified across three broad areas. (1) Understanding decision making and implementation: necessitating multidisciplinary collaboration in the early stages and throughout; early stakeholder engagement to define the decision problem and ensure acceptability of PROs in prediction; understanding patient/clinician interpretation of PRO predictions and uncertainty to optimize prediction impact; striving for model integration into existing electronic health records; and early regulatory alignment. (2) Recognizing the limitations to PRO collection and their impact on prediction: incorporating validated, clinically important PROs to maximize model generalizability and clinical engagement; and minimizing missing PRO data (resulting from both structural digital exclusion and time-varying factors) to avoid exacerbating existing inequalities. (3) Statistical and modeling challenges: incorporating statistical methods to address missing data; ensuring predictive modeling recognizes complex causal relationships; and considering temporal and geographic recalibration so that model predictions reflect the relevant population. CONCLUSION: Developing and implementing PRO-based prediction models in cancer care requires extensive multidisciplinary working from the earliest stages, recognition of implementation challenges because of PRO collection and model presentation, and robust statistical methods to manage missing data, causality, and calibration. Prediction models incorporating PROs should be viewed as complex interventions, with their development and impact assessment carried out to reflect this. Challenges and solutions to implementing patient-reported outcome–based predictive models in cancer. [ABSTRACT FROM AUTHOR]

PURPOSE: Patient portal technology offers important new opportunities to support person-centered clinician-patient communication. METHODS: Questionnaires relating to understanding of illness and treatment intent were sent quarterly via portal to all patients scheduled for follow-up in GI medical oncology clinics. For patients in selected clinics, items eliciting health-related values were added. Patient responses were available to all oncology team members in the electronic health record. Workflow and content of clinician-patient discussions about illness, treatment, and care goals stayed within clinicians' discretion. Feasibility (patient response rate), patient understanding, acceptability (three-item patient questionnaire), and efficacy (quality of clinician communication) were evaluated. RESULTS: From May 2021 through December 2022, a total of 12,233 questionnaires about illness/treatment understanding were sent to 6,325 patients (one to six per patient), with 97% response, including 9,358 with both open- and closed-ended responses. Fewer than 0.1% of patients indicated distress related to the questionnaire/process. Open-ended responses complemented closed-ended answers by revealing prognostic awareness and illness concerns. Of 48 patients approached to complete the full questionnaire including values items via portal, 15 first received and completed them in clinic (5 on iPad, 10 on paper), while 33 received and 27 (82%) completed the portal questionnaire. Patients found the portal process acceptable, and ratings of clinician communication were higher after clinic visits informed by patients' questionnaire responses (average prescore 6.8 v 5.9 post; P =.03). CONCLUSION: Almost all patients in this large GI cancer cohort responded via the portal about their understanding of illness and treatment goals. Eliciting their personal values by portal was also feasible, accepted by patients, and improved patient ratings of clinicians' communication. Portals represent a promising tool for scaling assessment of essential patient-reported elements of person-centered communication. Patient portals can help scale assessment of patient-reported elements of person-centered communication. [ABSTRACT FROM AUTHOR]

PURPOSE: In 2014, the ASCO developed CancerLinQ (CLQ), a health technology platform for oncology. The CLQ Discovery (CLQD) database was created to make data available for research and this paper provides a summary of this database. METHODS: This study described the clinical and demographic characteristics of the 12 most common cancers in the CLQD database. We included patients with a new malignant tumor diagnosis between January 1, 2013, and December 31, 2018, of the following cancers: breast, lung and bronchus, prostate, colon and rectum, melanoma of the skin, bladder, non-Hodgkin lymphoma, kidney and renal pelvis, uterus, leukemia, pancreas, and thyroid. Patients with an in-situ diagnosis were excluded. Summary statistics and Kaplan-Meier survival estimates were calculated for each tumor. RESULTS: From 2013 to 2018, 491,360 patients were diagnosed with the study tumors. Breast cancer (139,506) was the most common, followed by lung and bronchus (70,959), prostate (63,303), and colon and rectum (53,504). The median age at diagnosis (years) was 61, 68, 68, and 64 in breast, lung and bronchus, prostate, and colon and rectum cohorts, respectively. Compared to the SEER 5-year overall survival estimates for several tumor types were higher in the CLQD database, possibly because of incomplete mortality capture in electronic health records. CONCLUSION: This paper presents the first description of the CLQD database since its inception. CLQ will continue to evolve over time, and the breadth and depth of this data asset will continue to grow. ASCO and CLQ's long-term goal is to improve the quality of patient care and create a sustainable database for oncology researchers. These results demonstrate that CLQ built a scalable database that can be used for oncology research. [ABSTRACT FROM AUTHOR]

PURPOSE: Synoptic reporting provides a mechanism for uniform and structured pathology diagnostics. This paper demonstrates the functionality of Perl alternation and grouping expressions to classify electronic pathology reports generated from military treatment facilities. Eight Perl-based algorithms are validated to classify malignant melanoma, Hodgkin lymphoma, non-Hodgkin lymphoma, leukemia, and malignant neoplasms of the breast, ovary, testis, and thyroid. METHODS: Case finding cohorts were developed using diagnostic codes for neoplasm groups and matched by unique identifiers to obtain pathology records. Preprocessing techniques and Perl-based algorithms were applied to classify records as malignant, in situ, suspect, or nonapplicable, followed by a hand-review process to determine the accuracy of the algorithm classifications. Interrater reliability, sensitivity, specificity, positive predictive values, and negative predictive values were computed following abstractor adjudication. RESULTS: The specificity of the Perl-based algorithms was consistently high, over 98%. Very few benign results were classified as malignant or in situ by the Perl-based algorithms; the leukemia algorithm classification was the only group to demonstrate a positive predictive value below 95%, at 91.9%. Three algorithm classification groups demonstrated a sensitivity of < 80%, including malignant neoplasm of the ovary (33.3%), leukemia (52.8%), and non-Hodgkin lymphoma (62.9%). The pathology records for these results included substantial linguistic variation. CONCLUSION: This paper contextualizes the utility and value of an algorithm logic built around synoptic reporting to identify neoplasms from electronic pathology results. The major strength includes the application of Perl-based coding in SAS, an accessible software application, to develop highly specific algorithms across institutional variation in diagnostic documentation. [ABSTRACT FROM AUTHOR]

PURPOSE: We developed a system to automate analysis of the clinical oncology scientific literature from bibliographic databases and match articles to specific patient cohorts to answer specific questions regarding the efficacy of a treatment. The approach attempts to replicate a clinician's mental processes when reviewing published literature in the context of a patient case. We describe the system and evaluate its performance. METHODS: We developed separate ground truth data sets for each of the tasks described in the paper. The first ground truth was used to measure the natural language processing (NLP) accuracy from approximately 1,300 papers covering approximately 3,100 statements and approximately 25 concepts; performance was evaluated using a standard F1 score. The ground truth for the expert classifier model was generated by dividing papers cited in clinical guidelines into a training set and a test set in an 80:20 ratio, and performance was evaluated for accuracy, sensitivity, and specificity. RESULTS: The NLP models were able to identify individual attributes with a 0.7-0.9 F1 score, depending on the attribute of interest. The expert classifier machine learning model was able to classify the individual records with a 0.93 accuracy (95% CI, 0.9 to 0.96, P <.0001), and sensitivity and specificity of 0.95 and 0.91, respectively. Using a decision boundary of 0.5 for the positive (expert) label, the classifier demonstrated an F1 score of 0.92. CONCLUSION: The system identified and extracted evidence from the oncology literature with a high degree of accuracy, sensitivity, and specificity. This tool enables timely access to the most relevant biomedical literature, providing critical support to evidence-based practice in areas of rapidly evolving science. [ABSTRACT FROM AUTHOR]

PURPOSE: Precision oncology mandates developing standardized common data models (CDMs) to facilitate analyses and enable clinical decision making. Expert-opinion–based precision oncology initiatives are epitomized in Molecular Tumor Boards (MTBs), which process large volumes of clinical-genomic data to match genotypes with molecularly guided therapies. METHODS: We used the Johns Hopkins University MTB as a use case and developed a precision oncology core data model (Precision-DM) to capture key clinical-genomic data elements. We leveraged existing CDMs, building upon the Minimal Common Oncology Data Elements model (mCODE). Our model was defined as a set of profiles with multiple data elements, focusing on next-generation sequencing and variant annotations. Most elements were mapped to terminologies or code sets and the Fast Healthcare Interoperability Resources (FHIR). We subsequently compared our Precision-DM with existing CDMs, including the National Cancer Institute's Genomic Data Commons (NCI GDC), mCODE, OSIRIS, the clinical Genome Data Model (cGDM), and the genomic CDM (gCDM). RESULTS: Precision-DM contained 16 profiles and 355 data elements. 39% of the elements derived values from selected terminologies or code sets, and 61% were mapped to FHIR. Although we used most elements contained in mCODE, we significantly expanded the profiles to include genomic annotations, resulting in a partial overlap of 50.7% between our core model and mCODE. Limited overlap was noted between Precision-DM and OSIRIS (33.2%), NCI GDC (21.4%), cGDM (9.3%), and gCDM (7.9%). Precision-DM covered most of the mCODE elements (87.7%), with less coverage for OSIRIS (35.8%), NCI GDC (11%), cGDM (26%) and gCDM (33.3%). CONCLUSION: Precision-DM supports clinical-genomic data standardization to support the MTB use case and may allow for harmonized data pulls across health care systems, academic institutions, and community medical centers. New paper led by @TaxiarchisB, @ValsamoA at @hopkinskimmel reports the development of Precision-DM, a #precision #oncology core data model that supports #clinical-#genomics data standardization and integration. [ABSTRACT FROM AUTHOR]

The article is a response to a letter sent by Kempf et al. regarding a publication on the automatic detection of distant metastasis mentions in radiology reports in Spanish. The authors acknowledge the interest in their paper and discuss the importance of context in determining the metastatic status of a tumor. They compare their machine learning-based model to a rule-based algorithm and highlight the limitations of rule-based methods in imaging reports in Spanish. The authors also provide performance metrics for their model and discuss the annotation process of the corpus used in their study. They express their commitment to improving their model and methodology and invite further collaboration and discussion with the research community. [Extracted from the article]

PURPOSE: Accurate and efficient data collection is a challenge for quality improvement initiatives and clinical research. We describe the development of a custom electronic health record (EHR)–based registry to automatically extract structured Commission on Cancer axillary surgery-specific metrics from a custom synoptic note template included in the operative reports for patients with breast cancer undergoing surgery. METHODS: The smart functionality of our enterprise-based EHR system was leveraged to create a custom smart phrase to capture axillary surgery-specific variables. A multidisciplinary team developed structured data elements correlating to each axillary surgery-specific variable. These data elements were then included in a note template for the operative report. Each variable could be aggregated and converted into a single flat database through the EHR's reporting workbench and serve as a live, prospective registry for all users within the EHR. RESULTS: The final axillary surgery-specific note template in a synoptic format allowed for efficient and easy entry and automatic collection of breast cancer–specific metrics. From initial adoption in February 2021-December 2021, there were 1,254 patients who underwent breast surgery with axillary surgery. The operative notes allowed for automatic capture of metrics from 60.5% (n = 759) of patients. Data capture improved from 37.6% in the initial adoption period of 6 months to 86.2% in the last 5 months. CONCLUSION: We were able to demonstrate successful implementation of provider-driven structured data entry into EHR systems that permits automatic data capture. The end result is a custom synoptic note template and a real-time, prospective registry of breast cancer–specific Commission on Cancer metrics that are robust enough to use for quality improvement initiatives and clinical research. New @JCOCCI_ASCO paper on the implementation of a structured data entry system to collect axillary surgery specific metrics for #breast cancer patient demonstrates how existing #EHR systems can be used to improve documentation standards and surgical care. [ABSTRACT FROM AUTHOR]

PURPOSE: The medical literature relevant to germline genetics is growing exponentially. Clinicians need tools that help to monitor and prioritize the literature to understand the clinical implications of pathogenic genetic variants. We developed and evaluated two machine learning models to classify abstracts as relevant to the penetrance—risk of cancer for germline mutation carriers—or prevalence of germline genetic mutations. MATERIALS AND METHODS: We conducted literature searches in PubMed and retrieved paper titles and abstracts to create an annotated data set for training and evaluating the two machine learning classification models. Our first model is a support vector machine (SVM) which learns a linear decision rule on the basis of the bag-of-ngrams representation of each title and abstract. Our second model is a convolutional neural network (CNN) which learns a complex nonlinear decision rule on the basis of the raw title and abstract. We evaluated the performance of the two models on the classification of papers as relevant to penetrance or prevalence. RESULTS: For penetrance classification, we annotated 3,740 paper titles and abstracts and evaluated the two models using 10-fold cross-validation. The SVM model achieved 88.93% accuracy—percentage of papers that were correctly classified—whereas the CNN model achieved 88.53% accuracy. For prevalence classification, we annotated 3,753 paper titles and abstracts. The SVM model achieved 88.92% accuracy and the CNN model achieved 88.52% accuracy. CONCLUSION: Our models achieve high accuracy in classifying abstracts as relevant to penetrance or prevalence. By facilitating literature review, this tool could help clinicians and researchers keep abreast of the burgeoning knowledge of gene–cancer associations and keep the knowledge bases for clinical decision support tools up to date. [ABSTRACT FROM AUTHOR]

Purpose: This study reports on the implementation of an electronic consent-to-treatment system (e-Consent) in a busy radiation medicine program and compares it with the previous paper-based method of documenting patient consent. Methods: A password-protected, electronic, e-Consent application was designed in-house and installed on iPad devices to document patient consent for radiation therapy treatments. A feasibility study, followed by a program-wide deployment of e-Consent, was executed. The effectiveness and impact of e-Consent on workflow were determined by comparing the number of problems arising from the paper-based consenting method with those from the e-Consent process. Staff satisfaction and perceived impact of e-Consent on workflow were determined by a program-wide survey of e-Consent users. Results: The e-Consent completion rate was 94.2% (5,600 of 5,943 forms) 1 year after implementation, indicating successful uptake at the program level. Although the paper-based method of documenting patient consent was associated with an error rate of 7% (24 of 343 forms), e-Consent was associated with an error rate of 0.32% (18 of 5,600 forms) 1 year after deployment. Results of a 10-item e-Consent user survey indicated improvement in staff workflow and high overall satisfaction with e-Consent. Conclusion: e-Consent is more efficient than paper-based methods for documenting patient consent. Moreover, replacing paper-based consent methods with an electronic version facilitated an improved workflow and staff satisfaction. Efforts aimed at implementing e-Consent throughout the entire cancer program are currently underway. [ABSTRACT FROM AUTHOR]

PURPOSE: The field of oncology is expanding rapidly. New trials are opening as an increasing number of therapeutic agents are being investigated before they can become approved therapies. Aggregate views of these data, particularly data associated with diseases, biomarkers, and drugs, can be helpful in understanding the trends in current research as well as existing gaps in cancer care. METHODS: In this paper, we performed a landscape analysis for breast cancer and acute myeloid leukemia related trials with structured, curated data from clinical trials using the My Cancer Genome clinical trial knowledgebase. RESULTS: We have performed detailed analytics on breast cancer (N = 1,128) and acute myeloid leukemia trial sets (N = 483) to highlight the top biomarkers, drug classes, and drugs—thereby supporting a full view of biomarkers, biomarker groups, and drugs that are currently being explored in these respective diseases. CONCLUSION: Analysis and data visualization of the cancer clinical trial landscape can inform strategic planning for new trial designs and trial activation at a particular site. Deep analysis of breast cancer & AML trials using the my cancer genome model [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

PURPOSE: Building well-performing machine learning (ML) models in health care has always been exigent because of the data-sharing concerns, yet ML approaches often require larger training samples than is afforded by one institution. This paper explores several federated learning implementations by applying them in both a simulated environment and an actual implementation using electronic health record data from two academic medical centers on a Microsoft Azure Cloud Databricks platform. MATERIALS AND METHODS: Using two separate cloud tenants, ML models were created, trained, and exchanged from one institution to another via a GitHub repository. Federated learning processes were applied to both artificial neural networks (ANNs) and logistic regression (LR) models on the horizontal data sets that are varying in count and availability. Incremental and cyclic federated learning models have been tested in simulation and real environments. RESULTS: The cyclically trained ANN showed a 3% increase in performance, a significant improvement across most attempts (P <.05). Single weight neural network models showed improvement in some cases. However, LR models did not show much improvement after federated learning processes. The specific process that improved the performance differed based on the ML model and how federated learning was implemented. Moreover, we have confirmed that the order of the institutions during the training did influence the overall performance increase. CONCLUSION: Unlike previous studies, our work has shown the implementation and effectiveness of federated learning processes beyond simulation. Additionally, we have identified different federated learning models that have achieved statistically significant performances. More work is needed to achieve effective federated learning processes in biomedicine, while preserving the security and privacy of the data. [ABSTRACT FROM AUTHOR]

We thank Ritzwoller et al[1] for their interest in reading our paper on natural language processing (NLP) algorithm for detecting breast and hepatocellular cancer recurrence using unstructured electronic health record (EHR) data. We found that the NLP model identified 11.1% of patients who had recurrence, compared with 2.3% identified by ICD codes only. Ritzwoller et al[1] have demonstrated that including chemotherapy codes increases sensitivity for recurrence detection only minimally compared to ICD codes,[2] particularly given that breast cancer is often treated with noncytotoxic regimens at the time of recurrence. [Extracted from the article]