An overview of real-world data sources for oncology and considerations for research.

Generating evidence on the use, effectiveness, and safety of new cancer therapies is a priority for researchers, health care providers, payers, and regulators given the rapid pace of change in cancer diagnosis and treatments. The use of real-world data (RWD) is integral to understanding the utilization patterns and outcomes of these new treatments among patients with cancer who are treated in clinical practice and community settings. An initial step in the use of RWD is careful study design to assess the suitability of an RWD source. This pivotal process can be guided by using a conceptual model that encourages predesign conceptualization. The primary types of RWD included are electronic health records, administrative claims data, cancer registries, and specialty data providers and networks. Careful consideration of each data type is necessary because they are collected for a specific purpose, capturing a set of data elements within a certain population for that purpose, and they vary by population coverage and longitudinality. In this review, the authors provide a high-level assessment of the strengths and limitations of each data category to inform data source selection appropriate to the study question. Overall, the development and accessibility of RWD sources for cancer research are rapidly increasing, and the use of these data requires careful consideration of composition and utility to assess important questions in understanding the use and effectiveness of new therapies.

Deep learning uncertainty quantification for clinical text classification.

INTRODUCTION: Machine learning algorithms are expected to work side-by-side with humans in decision-making pipelines. Thus, the ability of classifiers to make reliable decisions is of paramount importance. Deep neural networks (DNNs) represent the state-of-the-art models to address real-world classification. Although the strength of activation in DNNs is often correlated with the network's confidence, in-depth analyses are needed to establish whether they are well calibrated. METHOD: In this paper, we demonstrate the use of DNN-based classification tools to benefit cancer registries by automating information extraction of disease at diagnosis and at surgery from electronic text pathology reports from the US National Cancer Institute (NCI) Surveillance, Epidemiology, and End Results (SEER) population-based cancer registries. In particular, we introduce multiple methods for selective classification to achieve a target level of accuracy on multiple classification tasks while minimizing the rejection amount-that is, the number of electronic pathology reports for which the model's predictions are unreliable. We evaluate the proposed methods by comparing our approach with the current in-house deep learning-based abstaining classifier. RESULTS: Overall, all the proposed selective classification methods effectively allow for achieving the targeted level of accuracy or higher in a trade-off analysis aimed to minimize the rejection rate. On in-distribution validation and holdout test data, with all the proposed methods, we achieve on all tasks the required target level of accuracy with a lower rejection rate than the deep abstaining classifier (DAC). Interpreting the results for the out-of-distribution test data is more complex; nevertheless, in this case as well, the rejection rate from the best among the proposed methods achieving 97% accuracy or higher is lower than the rejection rate based on the DAC. CONCLUSIONS: We show that although both approaches can flag those samples that should be manually reviewed and labeled by human annotators, the newly proposed methods retain a larger fraction and do so without retraining-thus offering a reduced computational cost compared with the in-house deep learning-based abstaining classifier.

Ascertainment of Incident Cancer by US Population-Based Cancer Registries Versus Self-Reports and Death Certificates in a Nationwide Cohort Study, the US Radiologic Technologists Study.

Follow-up of US cohort members for incident cancer is time-consuming, is costly, and often results in underascertainment when the traditional methods of self-reporting and/or medical record validation are used. We conducted one of the first large-scale investigations to assess the feasibility, methods, and benefits of linking participants in the US Radiologic Technologists (USRT) Study (n = 146,022) with the majority of US state or regional cancer registries. Follow-up of this cohort has relied primarily on questionnaires (mailed approximately every 10 years) and linkage with the National Death Index. We compared the level of agreement and completeness of questionnaire/death-certificate-based information with that of registry-based (43 registries) incident cancer follow-up in the USRT cohort. Using registry-identified first primary cancers from 1999-2012 as the gold standard, the overall sensitivity was 46.5% for self-reports only and 63.0% for both self-reports and death certificates. Among the 37.0% false-negative reports, 27.8% were due to dropout, while 9.2% were due to misreporting. The USRT cancer reporting patterns differed by cancer type. Our study indicates that linkage to state cancer registries would greatly improve completeness and accuracy of cancer follow-up in comparison with questionnaire self-reporting. These findings support ongoing development of a national US virtual pooled registry with which to streamline cohort linkages.

Class imbalance in out-of-distribution datasets: Improving the robustness of the TextCNN for the classification of rare cancer types.

In the last decade, the widespread adoption of electronic health record documentation has created huge opportunities for information mining. Natural language processing (NLP) techniques using machine and deep learning are becoming increasingly widespread for information extraction tasks from unstructured clinical notes. Disparities in performance when deploying machine learning models in the real world have recently received considerable attention. In the clinical NLP domain, the robustness of convolutional neural networks (CNNs) for classifying cancer pathology reports under natural distribution shifts remains understudied. In this research, we aim to quantify and improve the performance of the CNN for text classification on out-of-distribution (OOD) datasets resulting from the natural evolution of clinical text in pathology reports. We identified class imbalance due to different prevalence of cancer types as one of the sources of performance drop and analyzed the impact of previous methods for addressing class imbalance when deploying models in real-world domains. Our results show that our novel class-specialized ensemble technique outperforms other methods for the classification of rare cancer types in terms of macro F1 scores. We also found that traditional ensemble methods perform better in top classes, leading to higher micro F1 scores. Based on our findings, we formulate a series of recommendations for other ML practitioners on how to build robust models with extremely imbalanced datasets in biomedical NLP applications.

Deep active learning for classifying cancer pathology reports.

BACKGROUND: Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. RESULTS: We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. CONCLUSIONS: Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.

Development of paediatric non-stage prognosticator guidelines for population-based cancer registries and updates to the 2014 Toronto Paediatric Cancer Stage Guidelines.

Population-based cancer registries (PBCRs) generate measures of cancer incidence and survival that are essential for cancer surveillance, research, and cancer control strategies. In 2014, the Toronto Paediatric Cancer Stage Guidelines were developed to standardise how PBCRs collect data on the stage at diagnosis for childhood cancer cases. These guidelines have been implemented in multiple jurisdictions worldwide to facilitate international comparative studies of incidence and outcome. Robust stratification by risk also requires data on key non-stage prognosticators (NSPs). Key experts and stakeholders used a modified Delphi approach to establish principles guiding paediatric cancer NSP data collection. With the use of these principles, recommendations were made on which NSPs should be collected for the major malignancies in children. The 2014 Toronto Stage Guidelines were also reviewed and updated where necessary. Wide adoption of the resultant Paediatric NSP Guidelines and updated Toronto Stage Guidelines will enhance the harmonisation and use of childhood cancer data provided by PBCRs.

Accelerated training of bootstrap aggregation-based deep information extraction systems from cancer pathology reports.

OBJECTIVE: In machine learning, it is evident that the classification of the task performance increases if bootstrap aggregation (bagging) is applied. However, the bagging of deep neural networks takes tremendous amounts of computational resources and training time. The research question that we aimed to answer in this research is whether we could achieve higher task performance scores and accelerate the training by dividing a problem into sub-problems. MATERIALS AND METHODS: The data used in this study consist of free text from electronic cancer pathology reports. We applied bagging and partitioned data training using Multi-Task Convolutional Neural Network (MT-CNN) and Multi-Task Hierarchical Convolutional Attention Network (MT-HCAN) classifiers. We split a big problem into 20 sub-problems, resampled the training cases 2,000 times, and trained the deep learning model for each bootstrap sample and each sub-problem-thus, generating up to 40,000 models. We performed the training of many models concurrently in a high-performance computing environment at Oak Ridge National Laboratory (ORNL). RESULTS: We demonstrated that aggregation of the models improves task performance compared with the single-model approach, which is consistent with other research studies; and we demonstrated that the two proposed partitioned bagging methods achieved higher classification accuracy scores on four tasks. Notably, the improvements were significant for the extraction of cancer histology data, which had more than 500 class labels in the task; these results show that data partition may alleviate the complexity of the task. On the contrary, the methods did not achieve superior scores for the tasks of site and subsite classification. Intrinsically, since data partitioning was based on the primary cancer site, the accuracy depended on the determination of the partitions, which needs further investigation and improvement. CONCLUSION: Results in this research demonstrate that 1. The data partitioning and bagging strategy achieved higher performance scores. 2. We achieved faster training leveraged by the high-performance Summit supercomputer at ORNL.

Annual Report to the Nation on the Status of Cancer, part II: Recent changes in prostate cancer trends and disease characteristics.

BACKGROUND: Temporal trends in prostate cancer incidence and death rates have been attributed to changing patterns of screening and improved treatment (mortality only), among other factors. This study evaluated contemporary national-level trends and their relations with prostate-specific antigen (PSA) testing prevalence and explored trends in incidence according to disease characteristics with stage-specific, delay-adjusted rates. METHODS: Joinpoint regression was used to examine changes in delay-adjusted prostate cancer incidence rates from population-based US cancer registries from 2000 to 2014 by age categories, race, and disease characteristics, including stage, PSA, Gleason score, and clinical extension. In addition, the analysis included trends for prostate cancer mortality between 1975 and 2015 by race and the estimation of PSA testing prevalence between 1987 and 2005. The annual percent change was calculated for periods defined by significant trend change points. RESULTS: For all age groups, overall prostate cancer incidence rates declined approximately 6.5% per year from 2007. However, the incidence of distant-stage disease increased from 2010 to 2014. The incidence of disease according to higher PSA levels or Gleason scores at diagnosis did not increase. After years of significant decline (from 1993 to 2013), the overall prostate cancer mortality trend stabilized from 2013 to 2015. CONCLUSIONS: After a decline in PSA test usage, there has been an increased burden of late-stage disease, and the decline in prostate cancer mortality has leveled off. Cancer 2018;124:2801-2814. © 2018 American Cancer Society.

Hysterectomy-corrected rates of endometrial cancer among women younger than age 50 in the United States.

PURPOSE: This analysis describes the impact of hysterectomy on incidence rates and trends in endometrioid endometrial cancer in the United States among women of reproductive age. METHODS: Hysterectomy prevalence for states containing Surveillance, Epidemiology, and End Results (SEER) registry was estimated using data from the Behavioral Risk Factor Surveillance System (BRFSS) between 1992 and 2010. The population was adjusted for age, race, and calendar year strata. Age-adjusted incidence rates and trends of endometrial cancer among women age 20-49 corrected for hysterectomy were estimated. RESULTS: Hysterectomy prevalence varied by age, race, and ethnicity. Increasing incidence trends were observed, and were attenuated after correcting for hysterectomy. Among all women, the incidence was increasing 1.6% annually (95% CI 0.9, 2.3) and this increase was no longer significant after correction for hysterectomy (+ 0.7; 95% CI - 0.1, 1.5). Stage at diagnosis was similar with and without correction for hysterectomy. The largest increase in incidence over time was among Hispanic women; even after correction for hysterectomy, incidence was increasing (1.8%; 95% CI 0.2, 3.4) annually. CONCLUSION: Overall, endometrioid endometrial cancer incidence rates in the US remain stable among women of reproductive age. Routine reporting of endometrial cancer incidence does not accurately measure incidence among racial and ethnic minorities.

Validation of prostate-specific antigen laboratory values recorded in Surveillance, Epidemiology, and End Results registries.

BACKGROUND: Researchers have used prostate-specific antigen (PSA) values collected by central cancer registries to evaluate tumors for potential aggressive clinical disease. An independent study collecting PSA values suggested a high error rate (18%) related to implied decimal points. To evaluate the error rate in the Surveillance, Epidemiology, and End Results (SEER) program, a comprehensive review of PSA values recorded across all SEER registries was performed. METHODS: Consolidated PSA values for eligible prostate cancer cases in SEER registries were reviewed and compared with text documentation from abstracted records. Four types of classification errors were identified: implied decimal point errors, abstraction or coding implementation errors, nonsignificant errors, and changes related to "unknown" values. RESULTS: A total of 50,277 prostate cancer cases diagnosed in 2012 were reviewed. Approximately 94.15% of cases did not have meaningful changes (85.85% correct, 5.58% with a nonsignificant change of <1 ng/mL, and 2.80% with no clinical change). Approximately 5.70% of cases had meaningful changes (1.93% due to implied decimal point errors, 1.54% due to abstract or coding errors, and 2.23% due to errors related to unknown categories). Only 419 of the original 50,277 cases (0.83%) resulted in a change in disease stage due to a corrected PSA value. CONCLUSIONS: The implied decimal error rate was only 1.93% of all cases in the current validation study, with a meaningful error rate of 5.81%. The reasons for the lower error rate in SEER are likely due to ongoing and rigorous quality control and visual editing processes by the central registries. The SEER program currently is reviewing and correcting PSA values back to 2004 and will re-release these data in the public use research file. Cancer 2017;123:697-703. © 2016 American Cancer Society.

Preliminary estimates of SEER cancer incidence for 2013.

BACKGROUND: This article presents a first look at rates and trends for cases in the Surveillance, Epidemiology, and End Results (SEER) program diagnosed through 2013 using the February 2015 submission, and a validation of rates and trends from the February 2014 submission using the subsequent November 2014 submission. To the authors' knowledge, this is the second time SEER has published trends based on the early February submission. Three new cancer sites were added: cervix, thyroid, and liver/ intrahepatic bile duct. METHODS: A reporting delay model adjusted for the undercount of cases, which is substantially larger for the February than the subsequent November submission, was used. Joinpoint regression methodology was used to assess trends. Delay-adjusted rates and trends were checked to assess validity between the February and November 2014 submissions. RESULTS: The validation of rates and trends from the February and November 2014 submissions demonstrated even better agreement than the previously reported comparison between the February and November 2013 submissions, thereby affording additional confidence that the delay-adjusted February submission data can be used to produce valid estimates of incidence trends. Trends for cases diagnosed through 2013 revealed more rapid declines in female colon and rectal cancer and prostate cancer. A plateau in female melanoma trends and a slowing of the increases in thyroid cancer and male liver/intrahepatic bile duct cancer trends were observed. CONCLUSIONS: Analysis of early cancer data submissions can provide a preliminary indication of differences in incidence trends with an additional year of data. Although the delay adjustment correction adjusts for underreporting of cases, caution should be exercised when interpreting the results in this early submission. Cancer 2016;122:1579-87. © 2016 American Cancer Society.

Annual Report to the Nation on the Status of Cancer, 1975-2012, featuring the increasing incidence of liver cancer.

BACKGROUND: Annual updates on cancer occurrence and trends in the United States are provided through an ongoing collaboration among the American Cancer Society (ACS), the Centers for Disease Control and Prevention (CDC), the National Cancer Institute (NCI), and the North American Association of Central Cancer Registries (NAACCR). This annual report highlights the increasing burden of liver and intrahepatic bile duct (liver) cancers. METHODS: Cancer incidence data were obtained from the CDC, NCI, and NAACCR; data about cancer deaths were obtained from the CDC's National Center for Health Statistics (NCHS). Annual percent changes in incidence and death rates (age-adjusted to the 2000 US Standard Population) for all cancers combined and for the leading cancers among men and women were estimated by joinpoint analysis of long-term trends (incidence for 1992-2012 and mortality for 1975-2012) and short-term trends (2008-2012). In-depth analysis of liver cancer incidence included an age-period-cohort analysis and an incidence-based estimation of person-years of life lost because of the disease. By using NCHS multiple causes of death data, hepatitis C virus (HCV) and liver cancer-associated death rates were examined from 1999 through 2013. RESULTS: Among men and women of all major racial and ethnic groups, death rates continued to decline for all cancers combined and for most cancer sites; the overall cancer death rate (for both sexes combined) decreased by 1.5% per year from 2003 to 2012. Overall, incidence rates decreased among men and remained stable among women from 2003 to 2012. Among both men and women, deaths from liver cancer increased at the highest rate of all cancer sites, and liver cancer incidence rates increased sharply, second only to thyroid cancer. Men had more than twice the incidence rate of liver cancer than women, and rates increased with age for both sexes. Among non-Hispanic (NH) white, NH black, and Hispanic men and women, liver cancer incidence rates were higher for persons born after the 1938 to 1947 birth cohort. In contrast, there was a minimal birth cohort effect for NH Asian and Pacific Islanders (APIs). NH black men and Hispanic men had the lowest median age at death (60 and 62 years, respectively) and the highest average person-years of life lost per death (21 and 20 years, respectively) from liver cancer. HCV and liver cancer-associated death rates were highest among decedents who were born during 1945 through 1965. CONCLUSIONS: Overall, cancer incidence and mortality declined among men; and, although cancer incidence was stable among women, mortality declined. The burden of liver cancer is growing and is not equally distributed throughout the population. Efforts to vaccinate populations that are vulnerable to hepatitis B virus (HBV) infection and to identify and treat those living with HCV or HBV infection, metabolic conditions, alcoholic liver disease, or other causes of cirrhosis can be effective in reducing the incidence and mortality of liver cancer. Cancer 2016;122:1312-1337. © 2016 American Cancer Society.

Association of Major Adverse Financial Events and Later-Stage Cancer Diagnosis in the United States.

PURPOSE: This study assessed the prevalence of specific major adverse financial events (AFEs)-bankruptcies, liens, and evictions-before a cancer diagnosis and their association with later-stage cancer at diagnosis. METHODS: Patients age 20-69 years diagnosed with cancer during 2014-2015 were identified from the Seattle, Louisiana, and Georgia SEER population-based cancer registries. Registry data were linked with LexisNexis consumer data to identify patients with a history of court-documented AFEs before cancer diagnosis. The association of AFEs and later-stage cancer diagnoses (stages III/IV) was assessed using separate sex-specific multivariable logistic regression. RESULTS: Among 101,649 patients with cancer linked to LexisNexis data, 36,791 (36.2%) had a major AFE reported before diagnosis. The mean and median timing of the AFE closest to diagnosis were 93 and 77 months, respectively. AFEs were most common among non-Hispanic Black, unmarried, and low-income patients. Individuals with previous AFEs were more likely to be diagnosed with later-stage cancer than individuals with no AFE (males-odds ratio [OR], 1.09 [95% CI, 1.03 to 1.14]; P < .001; females-OR, 1.18 [95% CI, 1.13 to 1.24]; P < .0001) after adjusting for age, race, marital status, income, registry, and cancer type. Associations between AFEs prediagnosis and later-stage disease did not vary by AFE timing. CONCLUSION: One third of newly diagnosed patients with cancer had a major AFE before their diagnosis. Patients with AFEs were more likely to have later-stage diagnosis, even accounting for traditional measures of socioeconomic status that influence the stage at diagnosis. The prevalence of prediagnosis AFEs underscores financial vulnerability of patients with cancer before their diagnosis, before any subsequent financial burden associated with cancer treatment.

Impact on the Volume of Pathology Reports Before and During the COVID-19 Pandemic in SEER Cancer Registries.

INTRODUCTION: Health care procedures including cancer screening and diagnosis were interrupted due to the COVID-19 pandemic. The extent of this impact on cancer care in the United States is not fully understood. We investigated pathology report volume as a reflection of trends in oncology services pre-pandemic and during the pandemic. METHODS: Electronic pathology reports were obtained from 11 U.S. central cancer registries from NCI's SEER Program. The reports were sorted by cancer site and document type using a validated algorithm. Joinpoint regression was used to model temporal trends from January 2018 to February 2020, project expected counts from March 2020 to February 2021 and calculate observed-to-expected ratios. Results were stratified by sex, age, cancer site, and report type. RESULTS: During the first 3 months of the pandemic, pathology report volume decreased by 25.5% and 17.4% for biopsy and surgery reports, respectively. The 12-month O/E ratio (March 2020-February 2021) was lowest for women (O/E 0.90) and patients 65 years and older (O/E 0.91) and lower for cancers with screening (melanoma skin, O/E 0.86; breast, O/E 0.88; lung O/E 0.89, prostate, O/E 0.90; colorectal, O/E 0.91) when compared with all other cancers combined. CONCLUSIONS: These findings indicate a decrease in cancer diagnosis, likely due to the COVID-19 pandemic. This decrease in the number of pathology reports may result in a stage shift causing a subsequent longer-term impact on survival patterns. IMPACT: Investigation on the longer-term impact of the pandemic on pathology services is vital to understand if cancer care delivery levels continue to be affected.

Risk of and duration of protection from SARS-CoV-2 reinfection assessed with real-world data.

This retrospective observational study aimed to gain a better understanding of the protective duration of prior SARS-CoV-2 infection against reinfection. The objectives were two-fold: to assess the durability of immunity to SARS-CoV-2 reinfection among initially unvaccinated individuals with previous SARS-CoV-2 infection, and to evaluate the crude SARS-CoV-2 reinfection rate and associated risk factors. During the pandemic era time period from February 29, 2020, through April 30, 2021, 144,678,382 individuals with SARS-CoV-2 molecular diagnostic or antibody test results were studied. Rates of reinfection among index-positive individuals were compared to rates of infection among index-negative individuals. Factors associated with reinfection were evaluated using multivariable logistic regression. For both objectives, the outcome was a subsequent positive molecular diagnostic test result. Consistent with prior findings, the risk of reinfection among index-positive individuals was 87% lower than the risk of infection among index-negative individuals. The duration of protection against reinfection was stable over the median 5 months and up to 1-year follow-up interval. Factors associated with an increased reinfection risk included older age, comorbid immunologic conditions, and living in congregate care settings; healthcare workers had a decreased reinfection risk. This large US population-based study suggests that infection induced immunity is durable for variants circulating pre-Delta predominance.

The Childhood Cancer Data Initiative: Using the Power of Data to Learn From and Improve Outcomes for Every Child and Young Adult With Pediatric Cancer.

Data-driven basic, translational, and clinical research has resulted in improved outcomes for children, adolescents, and young adults (AYAs) with pediatric cancers. However, challenges in sharing data between institutions, particularly in research, prevent addressing substantial unmet needs in children and AYA patients diagnosed with certain pediatric cancers. Systematically collecting and sharing data from every child and AYA can enable greater understanding of pediatric cancers, improve survivorship, and accelerate development of new and more effective therapies. To accomplish this goal, the Childhood Cancer Data Initiative (CCDI) was launched in 2019 at the National Cancer Institute. CCDI is a collaborative community endeavor supported by a 10-year, $50-million (in US dollars) annual federal investment. CCDI aims to learn from every patient diagnosed with a pediatric cancer by designing and building a data ecosystem that facilitates data collection, sharing, and analysis for researchers, clinicians, and patients across the cancer community. For example, CCDI's Molecular Characterization Initiative provides comprehensive clinical molecular characterization for children and AYAs with newly diagnosed cancers. Through these efforts, the CCDI strives to provide clinical benefit to patients and improvements in diagnosis and care through data-focused research support and to build expandable, sustainable data resources and workflows to advance research well past the planned 10 years of the initiative. Importantly, if CCDI demonstrates the success of this model for pediatric cancers, similar approaches can be applied to adults, transforming both clinical research and treatment to improve outcomes for all patients with cancer.

Hematologic malignancies: an opportunity to fill a gap in cancer surveillance.

BACKGROUND: Reporting of hematologic malignancies is an increasingly important focus for cancer surveillance. As trends in cancer care are shifting to the outpatient setting, hospital-based data collection methods used for cancer surveillance will result in under-reporting of these cancers. This study describes the testing and validation of an automated system for capturing and reporting cancers from community oncology providers. METHODS: The system was evaluated in 5 oncology practices in two states processing claims data for a 4- or 8-month interval. Resulting cancers were matched with the state registries. A random sample of nonmatched cases was reabstracted to measure the accuracy of the claims data for reporting of hematologic malignancies. RESULTS: The overall match rate for the 1,935 hematologic malignancies reported during the study period was 58.2 % (range, 37.4 % for CLL to 71.2 % for Hodgkin's Lymphoma). The overall accuracy rate for billing-reported hematologic malignancies was 95 %. Accuracy among cases that did not match with the cancer registry was 88 %. The estimated number of missed cases for the five participating practices ranged from 0.8 leukemia cases/oncologist/year to 3.4 CLL cases/oncologist/year. The estimated total number of missed cases in the five participating practices was 292 with an interquartile range of 263-323. CONCLUSION: As cancer diagnosis and treatment continue migration into ambulatory physician practice settings unreported hematopoietic cases will become increasingly problematic. Leveraging the standardized electronic billing data for automated reporting of cancer cases from physician practices may be an efficient method to reduce this gap in cancer surveillance reporting.

Barriers to therapeutic clinical trials enrollment: differences between African-American and white cancer patients identified at the time of eligibility assessment.

BACKGROUND: Clinical trials (CTs) are the mechanism by which research is translated into standards of care. Low recruitment among underserved and minority populations may result in inequity in access to the latest technology and treatments, compromise the generalizability, and lead to failure in identification of important positive or negative treatment effects among under-represented populations. METHODS: Data were collected over a 39-month period on patient eligibility for available therapeutic cancer CTs. Reasons for ineligibility and refusal were collected. The data were captured using an automated software tool for tracking eligibility pre-enrollment. We examined characteristics associated with being evaluated for a trial, and reasons for ineligibility and refusal, overall and by patient race. RESULTS: African-Americans (AAs) were more likely than Whites to be ineligible (odds ratio, (OR) = 1.26, 95% confidence interval (CI) = 1.0-1.58) and if eligible, to refuse participation (OR = 1.79, 95% CI = 1.27-2.52), even after adjusting for insurance, age, gender, study phase, and cancer type. White patients were more likely to be ineligible due to study-specific or cancer characteristics. AAs were more likely to be ineligible due to mental status or perceived noncompliance. Whites were more likely to refuse due to extra burden, due to concerns with randomization and toxicity, or because they express a positive treatment preference. AAs were more likely to refuse because they were not interested in CTs, because of family pressures, or they felt overwhelmed (NS)). DISCUSSION: This study is the first to directly compare ineligibility and refusal rates and reasons captured prospectively in AA and White cancer patients. The data are consistent with earlier studies that indicated that AA patients more often are deemed ineligible and, when eligible, more often refuse participation. However, differences in reasons for ineligibility and refusal by race have implications for a cancer center to participate in CTs appropriate for the population of patients served. On a broader scale, consideration should be given to modifying eligibility criteria and other design aspects to permit broader participation of minority and other underserved groups.

Automatic information extraction from childhood cancer pathology reports.

Objectives: The International Classification of Childhood Cancer (ICCC) facilitates the effective classification of a heterogeneous group of cancers in the important pediatric population. However, there has been no development of machine learning models for the ICCC classification. We developed deep learning-based information extraction models from cancer pathology reports based on the ICD-O-3 coding standard. In this article, we describe extending the models to perform ICCC classification. Materials and Methods: We developed 2 models, ICD-O-3 classification and ICCC recoding (Model 1) and direct ICCC classification (Model 2), and 4 scenarios subject to the training sample size. We evaluated these models with a corpus consisting of 29 206 reports with age at diagnosis between 0 and 19 from 6 state cancer registries. Results: Our findings suggest that the direct ICCC classification (Model 2) is substantially better than reusing the ICD-O-3 classification model (Model 1). Applying the uncertainty quantification mechanism to assess the confidence of the algorithm in assigning a code demonstrated that the model achieved a micro-F1 score of 0.987 while abstaining (not sufficiently confident to assign a code) on only 14.8% of ambiguous pathology reports. Conclusions: Our experimental results suggest that the machine learning-based automatic information extraction from childhood cancer pathology reports in the ICCC is a reliable means of supplementing human annotators at state cancer registries by reading and abstracting the majority of the childhood cancer pathology reports accurately and reliably.