Disparities in Preoperative Goals of Care Documentation in Veterans.

Importance: Preoperative goals of care discussion and documentation are important for patients undergoing surgery, a major health care stressor that incurs risk. Objective: To assess the association of race, ethnicity, and other factors, including history of mental health disability, with disparities in preoperative goals of care documentation among veterans. Design, Setting, and Participants: This retrospective cross-sectional study assessed data from the Veterans Healthcare Administration (VHA) of 229 737 veterans who underwent surgical procedures between January 1, 2017, and October 18, 2022. Exposures: Patient-level (ie, race, ethnicity, medical comorbidities, history of mental health comorbidity) and system-level (ie, facility complexity level) factors. Main Outcomes and Measures: Preoperative life-sustaining treatment (LST) note documentation or no LST note documentation within 30 days prior to or on day of surgery. The standardized mean differences were calculated to assess the magnitude of differences between groups. Odds ratios (ORs) and 95% CIs were estimated with logistic regression. Results: In this study, 13 408 patients (5.8%) completed preoperative LST from 229 737 VHA patients (209 123 [91.0%] male; 20 614 [9.0%] female; mean [SD] age, 65.5 [11.9] years) who received surgery. Compared with patients who did complete preoperative LST, patients tended to complete preoperative documentation less often if they were female (19 914 [9.2%] vs 700 [5.2%]), Black individuals (42 571 [19.7%] vs 2416 [18.0%]), Hispanic individuals (11 793 [5.5%] vs 631 [4.7%]), or from rural areas (75 637 [35.0%] vs 4273 [31.9%]); had a history of mental health disability (65 974 [30.5%] vs 4053 [30.2%]); or were seen at lowest-complexity (ie, level 3) facilities (7849 [3.6%] vs 78 [0.6%]). Over time, despite the COVID-19 pandemic, patients undergoing surgical procedures completed preoperative LST increasingly more often. Covariate-adjusted estimates of preoperative LST completion demonstrated that patients of racial or ethnic minority background (Black patients: OR, 0.79; 95% CI, 0.77-0.80; P <.001; patients selecting other race: OR, 0.78; 95% CI, 0.74-0.81; P <.001; Hispanic patients: OR, 0.78; 95% CI, 0.76-0.81; P <.001) and patients from rural regions (OR, 0.91; 95% CI, 0.90-0.93; P <.001) had lower likelihoods of completing LST compared with patients who were White or non-Hispanic and patients from urban areas. Patients with any mental health disability history also had lower likelihood of completing preoperative LST than those without a history (OR, 0.93; 95% CI, 0.92-0.94; P = .001). Conclusions and Relevance: In this cross-sectional study, disparities in documentation rates within a VHA cohort persisted based on race, ethnicity, rurality of patient residence, history of mental health disability, and access to high-volume, high-complexity facilities.

Accomplished women leaders in informatics: insights about successful careers.

We sought to learn from the experiences of women leaders in informatics by interviewing women in Informatics leadership roles. Participants reported career challenges, how they built confidence, advice to their younger selves, and suggestions for attracting and retaining additional women. Respondents were 16 women in leadership roles in academia (n = 9) and industry (n = 7). We conducted a thematic analysis revealing: (1) careers in informatics are serendipitous and nurtured by supportive communities, (2) challenges in leadership were profoundly related to gender issues, (3) "Big wins" in informatics careers were about making a difference, and (4) women leaders highlighted resilience, excellence, and personal authenticity as important for future women leaders. Sexism is undeniably present, although not all participants reported overt gender barriers. Confidence and authenticity in leadership point to the value offered by individual leaders. The next step is to continue to foster an informatics culture that encourages authenticity across the gender spectrum.

Replication of Real-World Evidence in Oncology Using Electronic Health Record Data Extracted by Machine Learning.

Meaningful real-world evidence (RWE) generation requires unstructured data found in electronic health records (EHRs) which are often missing from administrative claims; however, obtaining relevant data from unstructured EHR sources is resource-intensive. In response, researchers are using natural language processing (NLP) with machine learning (ML) techniques (i.e., ML extraction) to extract real-world data (RWD) at scale. This study assessed the quality and fitness-for-use of EHR-derived oncology data curated using NLP with ML as compared to the reference standard of expert abstraction. Using a sample of 186,313 patients with lung cancer from a nationwide EHR-derived de-identified database, we performed a series of replication analyses demonstrating some common analyses conducted in retrospective observational research with complex EHR-derived data to generate evidence. Eligible patients were selected into biomarker- and treatment-defined cohorts, first with expert-abstracted then with ML-extracted data. We utilized the biomarker- and treatment-defined cohorts to perform analyses related to biomarker-associated survival and treatment comparative effectiveness, respectively. Across all analyses, the results differed by less than 8% between the data curation methods, and similar conclusions were reached. These results highlight that high-performance ML-extracted variables trained on expert-abstracted data can achieve similar results as when using abstracted data, unlocking the ability to perform oncology research at scale.

Evaluation of race/ethnicity-specific survival machine learning models for Hispanic and Black patients with breast cancer.

OBJECTIVES: Survival machine learning (ML) has been suggested as a useful approach for forecasting future events, but a growing concern exists that ML models have the potential to cause racial disparities through the data used to train them. This study aims to develop race/ethnicity-specific survival ML models for Hispanic and black women diagnosed with breast cancer to examine whether race/ethnicity-specific ML models outperform the general models trained with all races/ethnicity data. METHODS: We used the data from the US National Cancer Institute's Surveillance, Epidemiology and End Results programme registries. We developed the Hispanic-specific and black-specific models and compared them with the general model using the Cox proportional-hazards model, Gradient Boost Tree, survival tree and survival support vector machine. RESULTS: A total of 322 348 female patients who had breast cancer diagnoses between 1 January 2000 and 31 December 2017 were identified. The race/ethnicity-specific models for Hispanic and black women consistently outperformed the general model when predicting the outcomes of specific race/ethnicity. DISCUSSION: Accurately predicting the survival outcome of a patient is critical in determining treatment options and providing appropriate cancer care. The high-performing models developed in this study can contribute to providing individualised oncology care and improving the survival outcome of black and Hispanic women. CONCLUSION: Predicting the individualised survival outcome of breast cancer can provide the evidence necessary for determining treatment options and high-quality, patient-centred cancer care delivery for under-represented populations. Also, the race/ethnicity-specific ML models can mitigate representation bias and contribute to addressing health disparities.

Considerations for the Use of Machine Learning Extracted Real-World Data to Support Evidence Generation: A Research-Centric Evaluation Framework.

A vast amount of real-world data, such as pathology reports and clinical notes, are captured as unstructured text in electronic health records (EHRs). However, this information is both difficult and costly to extract through human abstraction, especially when scaling to large datasets is needed. Fortunately, Natural Language Processing (NLP) and Machine Learning (ML) techniques provide promising solutions for a variety of information extraction tasks such as identifying a group of patients who have a specific diagnosis, share common characteristics, or show progression of a disease. However, using these ML-extracted data for research still introduces unique challenges in assessing validity and generalizability to different cohorts of interest. In order to enable effective and accurate use of ML-extracted real-world data (RWD) to support research and real-world evidence generation, we propose a research-centric evaluation framework for model developers, ML-extracted data users and other RWD stakeholders. This framework covers the fundamentals of evaluating RWD produced using ML methods to maximize the use of EHR data for research purposes.

Expanding the Secondary Use of Prostate Cancer Real World Data: Automated Classifiers for Clinical and Pathological Stage.

Background: Explicit documentation of stage is an endorsed quality metric by the National Quality Forum. Clinical and pathological cancer staging is inconsistently recorded within clinical narratives but can be derived from text in the Electronic Health Record (EHR). To address this need, we developed a Natural Language Processing (NLP) solution for extraction of clinical and pathological TNM stages from the clinical notes in prostate cancer patients. Methods: Data for patients diagnosed with prostate cancer between 2010 and 2018 were collected from a tertiary care academic healthcare system's EHR records in the United States. This system is linked to the California Cancer Registry, and contains data on diagnosis, histology, cancer stage, treatment and outcomes. A randomly selected sample of patients were manually annotated for stage to establish the ground truth for training and validating the NLP methods. For each patient, a vector representation of clinical text (written in English) was used to train a machine learning model alongside a rule-based model and compared with the ground truth. Results: A total of 5,461 prostate cancer patients were identified in the clinical data warehouse and over 30% were missing stage information. Thirty-three to thirty-six percent of patients were missing a clinical stage and the models accurately imputed the stage in 21-32% of cases. Twenty-one percent had a missing pathological stage and using NLP 71% of missing T stages and 56% of missing N stages were imputed. For both clinical and pathological T and N stages, the rule-based NLP approach out-performed the ML approach with a minimum F1 score of 0.71 and 0.40, respectively. For clinical M stage the ML approach out-performed the rule-based model with a minimum F1 score of 0.79 and 0.88, respectively. Conclusions: We developed an NLP pipeline to successfully extract clinical and pathological staging information from clinical narratives. Our results can serve as a proof of concept for using NLP to augment clinical and pathological stage reporting in cancer registries and EHRs to enhance the secondary use of these data.

Analyzing real world data of blood transfusion adverse events: Opportunities and challenges.

BACKGROUND: Blood transfusions are a vital component of modern healthcare, yet adverse reactions to blood product transfusions can cause morbidity, and rarely result in mortality. Therefore, accurate reporting of transfusion related adverse events (TRAEs) is paramount to improved transfusion practice. This study aims to investigate real-world data (RWD) on TRAEs by evaluating differences between ICD 9/10-based electronic health records (EHR) and blood bank-specific reporting. STUDY DESIGN AND METHODS: TRAE data were retrospectively collected from a blood bank-specific database between Jan 2015 and June 2019 as the reference data source and compared it to ICD 9/10 diagnostic codes corresponding to various TRAEs. Seven reactions that have corresponding ICD 9/10 diagnostic codes were evaluated: Transfusion related circulatory overload (TACO), transfusion related acute lung injury (TRALI), febrile non-hemolytic reaction (FNHTR), transfusion-related anaphylactic reaction (TRA), acute hemolytic transfusion reaction (AHTR), delayed hemolytic transfusion reaction (DHTR), and delayed serologic reaction (DSTR). These accounted for 33% of the TRAEs at an academic institution during the study period. RESULTS: Among 18637 adult blood transfusion recipients, there were 229 unique patients with 263 TRAE related ICD codes in the EHR, while there were 191 unique patients with 287 TRAEs identified in the blood bank database. None of the categories of reaction we investigated had perfect alignment between ICD 9/10 codes and blood bank specific diagnoses. DISCUSSION: Multiple systemic challenges were identified that hinder effective reporting of TRAEs. Identifying factors causing inconsistent reporting between blood banks and EHRs is paramount to developing effective workability between these electronic systems, as well as across clinical and laboratory teams.

Peeking into a black box, the fairness and generalizability of a MIMIC-III benchmarking model.

As artificial intelligence (AI) makes continuous progress to improve quality of care for some patients by leveraging ever increasing amounts of digital health data, others are left behind. Empirical evaluation studies are required to keep biased AI models from reinforcing systemic health disparities faced by minority populations through dangerous feedback loops. The aim of this study is to raise broad awareness of the pervasive challenges around bias and fairness in risk prediction models. We performed a case study on a MIMIC-trained benchmarking model using a broadly applicable fairness and generalizability assessment framework. While open-science benchmarks are crucial to overcome many study limitations today, this case study revealed a strong class imbalance problem as well as fairness concerns for Black and publicly insured ICU patients. Therefore, we advocate for the widespread use of comprehensive fairness and performance assessment frameworks to effectively monitor and validate benchmark pipelines built on open data resources.

Can peripheral blood monocyte percentage and lymphocyte monocyte ratio at diagnosis predict survival in pediatric neuroblastoma patients?

BACKGROUND: Previous studies have shown that the immune system plays a critical role in cancer pathogenesis. The lymphocyte monocyte ratio (LMR) and monocyte percentage (MP) have been found to be prognostic factors in various types of adult cancers. But studies about pediatric tumors are scarce and to our knowledge, there are no studies evaluating the immune system effect in pediatric neuroblastoma patients. The aim of this study was to assess whether LMR and MP at diagnosis may have an effect on prognosis in neuroblastoma patients. METHODS: We retrospectively analyzed MP and LMR at diagnosis in 71 pediatric neuroblastoma patients treated between 2002 and 2016. RESULTS: The optimal cut-off values of LMR and MP were determined using the receiver operating characteristics curves (ROC) and area under the curve (AUC). We found that a low LMR (≤3.5) and a high MP (≥7.5%) were correlated with worse overall survival and shorter event-free survival in univariate analysis. Multivariate analysis revealed that elevated LMR was an independent factor for better OS and EFS. CONCLUSIONS: In conclusion, LMR and MP might be valuable prognostic factors for predicting OS in neuroblastoma patients. Multicenter and prospective studies are warranted to confirm this hypothesis.

Characterizing patient flow after an academic hospital merger and acquisition.

OBJECTIVES: Hospital mergers and acquisitions are increasingly used as a strategy to facilitate value-based care. However, no studies have assessed health care utilization (HCU) and patient flow across merged institutions. We aim to evaluate patient population distribution, HCU, and patient flow across a recent hospital merger of an academic medical center (AMC), a primary and specialty care alliance (PSC), and a community-based medical center (CMC). STUDY DESIGN: This was a retrospective observational study. METHODS: The study used 2018 adult demographic and encounter data from electronic health records. Patients' parent health care institution was determined by the most frequently visited site of face-to-face visits. Differences in patient demographics and HCU (ie, emergency department [ED] visits, hospitalizations, primary care visits) were compared. Independent factors associated with utilization were identified using adjusted logistic regression models. RESULTS: A total of 406,303 adult patients were identified in the cohort. The PSC setting, compared with the AMC and the CMC, had significantly more female (62.7% vs 54.4% and 58.5%, respectively), older (mean [SD] age, 52.0 [18.1] vs 51.1 [17.8] and 49.2 [17.8] years), and privately insured (63.6% vs 51.3% and 56.0%) patients. A higher proportion of patients at the CMC (27.5%) visited the ED compared with patients at the AMC (10.8%). Approximately 1645 primary care patients (7%) at the CMC setting went to the AMC for specialized care such as oncology, surgery, and neurology. CONCLUSIONS: Hospital mergers are increasing across the United States, allowing AMCs to expand their reach. These findings suggest that patients mainly sought care at their parent health care institution, yet appropriately received specialized care at the AMC. These results provide insights for future mergers and guide resource allocation and opportunities for improving care delivery.

Diverse patient trajectories during cytotoxic chemotherapy: Capturing longitudinal patient-reported outcomes.

BACKGROUND: High-value cancer care balances effective treatment with preservation of quality of life. Chemotherapy is known to affect patients' physical and psychological well-being negatively. Patient-reported outcomes (PROs) provide a means to monitor declines in a patients' well-being during treatment. METHODS: We identified 741 oncology patients undergoing chemotherapy in our electronic health record (EHR) system who completed Patient-Reported Outcomes Measurement Information System (PROMIS) surveys during treatment at a comprehensive cancer center, 2013-2018. PROMIS surveys were collected before, during, and after chemotherapy treatment. Linear mixed-effects models were performed to identify predictors of physical and mental health scores over time. A k-mean cluster analysis was used to group patient PROMIS score trajectories. RESULTS: Mean global physical health (GPH) scores were 48.7 (SD 9.3), 47.7 (8.8), and 48.6 (8.9) and global mental health (GMH) scores were 50.4 (8.6), 49.5 (8.8), and 50.6 (9.1) before, during, and after chemotherapy, respectively. Asian race, Hispanic ethnicity, public insurance, anxiety/depression, stage III cancer, and palliative care were predictors of GPH and GMH decline. The treatment time period was also a predictor of both GPH and GMH decline relative to pre-treatment. Trajectory clustering identified four distinct PRO clusters associated with chemotherapy treatment. CONCLUSIONS: Patient-reported outcomes are increasingly used to help monitor cancer treatment and are now a part of care reimbursement. This study leveraged routinely collected PROMIS surveys linked to EHRs to identify novel patient trajectories of physical and mental well-being in oncology patients undergoing chemotherapy and potential predictors. Supportive care interventions in high-risk populations identified by our study may optimize resource deployment. NOVELTY AND IMPACT: This study leveraged routinely collected patient-reported outcome (PROMIS) surveys linked to electronic health records to characterize oncology patients' quality of life during chemotherapy. Important clinical and demographic predictors of declines in quality of life were identified and four novel trajectories to guide personalized interventions and support. This work highlights the utility of monitoring patient-reported outcomes not only before and after, but during chemotherapy to help advert adverse patient outcomes and improve treatment adherence.

Assessment of a Clinical Trial-Derived Survival Model in Patients With Metastatic Castration-Resistant Prostate Cancer.

Importance: Randomized clinical trials (RCTs) are considered the criterion standard for clinical evidence. Despite their many benefits, RCTs have limitations, such as costliness, that may reduce the generalizability of their findings among diverse populations and routine care settings. Objective: To assess the performance of an RCT-derived prognostic model that predicts survival among patients with metastatic castration-resistant prostate cancer (CRPC) when the model is applied to real-world data from electronic health records (EHRs). Design, Setting, and Participants: The RCT-trained model and patient data from the RCTs were obtained from the Dialogue for Reverse Engineering Assessments and Methods (DREAM) challenge for prostate cancer, which occurred from March 16 to July 27, 2015. This challenge included 4 phase 3 clinical trials of patients with metastatic CRPC. Real-world data were obtained from the EHRs of a tertiary care academic medical center that includes a comprehensive cancer center. In this study, the DREAM challenge RCT-trained model was applied to real-world data from January 1, 2008, to December 31, 2019; the model was then retrained using EHR data with optimized feature selection. Patients with metastatic CRPC were divided into RCT and EHR cohorts based on data source. Data were analyzed from March 23, 2018, to October 22, 2020. Exposures: Patients who received treatment for metastatic CRPC. Main Outcomes and Measures: The primary outcome was the performance of an RCT-derived prognostic model that predicts survival among patients with metastatic CRPC when the model is applied to real-world data. Model performance was compared using 10-fold cross-validation according to time-dependent integrated area under the curve (iAUC) statistics. Results: Among 2113 participants with metastatic CRPC, 1600 participants were included in the RCT cohort, and 513 participants were included in the EHR cohort. The RCT cohort comprised a larger proportion of White participants (1390 patients [86.9%] vs 337 patients [65.7%]) and a smaller proportion of Hispanic participants (14 patients [0.9%] vs 42 patients [8.2%]), Asian participants (41 patients [2.6%] vs 88 patients [17.2%]), and participants older than 75 years (388 patients [24.3%] vs 191 patients [37.2%]) compared with the EHR cohort. Participants in the RCT cohort also had fewer comorbidities (mean [SD], 1.6 [1.8] comorbidities vs 2.5 [2.6] comorbidities, respectively) compared with those in the EHR cohort. Of the 101 variables used in the RCT-derived model, 10 were not available in the EHR data set, 3 of which were among the top 10 features in the DREAM challenge RCT model. The best-performing EHR-trained model included only 25 of the 101 variables included in the RCT-trained model. The performance of the RCT-trained and EHR-trained models was adequate in the EHR cohort (mean [SD] iAUC, 0.722 [0.118] and 0.762 [0.106], respectively); model optimization was associated with improved performance of the best-performing EHR model (mean [SD] iAUC, 0.792 [0.097]). The EHR-trained model classified 256 patients as having a high risk of mortality and 256 patients as having a low risk of mortality (hazard ratio, 2.7; 95% CI, 2.0-3.7; log-rank P < .001). Conclusions and Relevance: In this study, although the RCT-trained models did not perform well when applied to real-world EHR data, retraining the models using real-world EHR data and optimizing variable selection was beneficial for model performance. As clinical evidence evolves to include more real-world data, both industry and academia will likely search for ways to balance model optimization with generalizability. This study provides a pragmatic approach to applying RCT-trained models to real-world data.

Phenotyping severity of patient-centered outcomes using clinical notes: A prostate cancer use case.

INTRODUCTION: A learning health system (LHS) must improve care in ways that are meaningful to patients, integrating patient-centered outcomes (PCOs) into core infrastructure. PCOs are common following cancer treatment, such as urinary incontinence (UI) following prostatectomy. However, PCOs are not systematically recorded because they can only be described by the patient, are subjective and captured as unstructured text in the electronic health record (EHR). Therefore, PCOs pose significant challenges for phenotyping patients. Here, we present a natural language processing (NLP) approach for phenotyping patients with UI to classify their disease into severity subtypes, which can increase opportunities to provide precision-based therapy and promote a value-based delivery system. METHODS: Patients undergoing prostate cancer treatment from 2008 to 2018 were identified at an academic medical center. Using a hybrid NLP pipeline that combines rule-based and deep learning methodologies, we classified positive UI cases as mild, moderate, and severe by mining clinical notes. RESULTS: The rule-based model accurately classified UI into disease severity categories (accuracy: 0.86), which outperformed the deep learning model (accuracy: 0.73). In the deep learning model, the recall rates for mild and moderate group were higher than the precision rate (0.78 and 0.79, respectively). A hybrid model that combined both methods did not improve the accuracy of the rule-based model but did outperform the deep learning model (accuracy: 0.75). CONCLUSION: Phenotyping patients based on indication and severity of PCOs is essential to advance a patient centered LHS. EHRs contain valuable information on PCOs and by using NLP methods, it is feasible to accurately and efficiently phenotype PCO severity. Phenotyping must extend beyond the identification of disease to provide classification of disease severity that can be used to guide treatment and inform shared decision-making. Our methods demonstrate a path to a patient centered LHS that could advance precision medicine.

Reporting of demographic data and representativeness in machine learning models using electronic health records.

OBJECTIVE: The development of machine learning (ML) algorithms to address a variety of issues faced in clinical practice has increased rapidly. However, questions have arisen regarding biases in their development that can affect their applicability in specific populations. We sought to evaluate whether studies developing ML models from electronic health record (EHR) data report sufficient demographic data on the study populations to demonstrate representativeness and reproducibility. MATERIALS AND METHODS: We searched PubMed for articles applying ML models to improve clinical decision-making using EHR data. We limited our search to papers published between 2015 and 2019. RESULTS: Across the 164 studies reviewed, demographic variables were inconsistently reported and/or included as model inputs. Race/ethnicity was not reported in 64%; gender and age were not reported in 24% and 21% of studies, respectively. Socioeconomic status of the population was not reported in 92% of studies. Studies that mentioned these variables often did not report if they were included as model inputs. Few models (12%) were validated using external populations. Few studies (17%) open-sourced their code. Populations in the ML studies include higher proportions of White and Black yet fewer Hispanic subjects compared to the general US population. DISCUSSION: The demographic characteristics of study populations are poorly reported in the ML literature based on EHR data. Demographic representativeness in training data and model transparency is necessary to ensure that ML models are deployed in an equitable and reproducible manner. Wider adoption of reporting guidelines is warranted to improve representativeness and reproducibility.

MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care.

The rise of digital data and computing power have contributed to significant advancements in artificial intelligence (AI), leading to the use of classification and prediction models in health care to enhance clinical decision-making for diagnosis, treatment and prognosis. However, such advances are limited by the lack of reporting standards for the data used to develop those models, the model architecture, and the model evaluation and validation processes. Here, we present MINIMAR (MINimum Information for Medical AI Reporting), a proposal describing the minimum information necessary to understand intended predictions, target populations, and hidden biases, and the ability to generalize these emerging technologies. We call for a standard to accurately and responsibly report on AI in health care. This will facilitate the design and implementation of these models and promote the development and use of associated clinical decision support tools, as well as manage concerns regarding accuracy and bias.

Acute pain after breast surgery and reconstruction: A two-institution study of surgical factors influencing short-term pain outcomes.

BACKGROUND AND OBJECTIVES: Acute postoperative pain following surgery is known to be associated with chronic pain development and lower quality of life. We sought to analyze the relationship between differing breast cancer excisional procedures, reconstruction, and short-term pain outcomes. METHODS: Women undergoing breast cancer excisional procedures with or without reconstruction at two systems: an academic hospital (AH) and Veterans Health Administration (VHA) were included. Average pain scores at the time of discharge and at 30-day follow-up were analyzed across demographic and clinical characteristics. Linear mixed effects modeling was used to assess the relationship between patient/clinical characteristics and interval pain scores with a random slope to account for differences in baseline pain. RESULTS: Our study included 1402 patients at AH and 1435 at VHA, of which 426 AH and 165 patients with VHA underwent reconstruction. Pain scores improved over time and were found to be highest at discharge. Time at discharge, 30-day follow-up, and preoperative opioid use were the strongest predictors of high pain scores. Younger age and longer length of stay were independently associated with worse pain scores. CONCLUSIONS: Younger age, preoperative opioid use, and longer length of stay were associated with higher levels of postoperative pain across both sites.

Knowledge, attitudes and medical practice regarding hepatitis B prevention and management among healthcare workers in Northern Vietnam.

BACKGROUND AND AIM: Vietnam's burden of liver cancer is largely due to its high prevalence of chronic hepatitis B virus (HBV) infection. This study aimed to examine healthcare workers' (HCWs) knowledge, attitude and practices regarding HBV prevention and management. METHODS: A cross-sectional survey among health care workers working at primary and tertiary facilities in two Northern provinces in Vietnam in 2017. A standardized questionnaire was administered to randomly selected HCWs. Multivariate regression was used to identify predictors of the HBV knowledge score. RESULTS: Among the 314 participants, 75.5% did not know HBV infection at birth carries the highest risk of developing chronic infection. The median knowledge score was 25 out of 42 (59.5%). About one third (30.2%) wrongly believed that HBV can be transmitted through eating or sharing food with chronic hepatitis B patients. About 38.8% did not feel confident that the hepatitis B vaccine is safe. Only 30.1% provided correct answers to all the questions on injection safety. Up to 48.2% reported they consistently recap needles with two hands after injection, a practice that would put them at greater risk of needle stick injury. About 24.2% reported having been pricked by a needle at work within the past 12 months. More than 40% were concerned about having casual contact or sharing food with a person with chronic hepatitis B infection (CHB). In multivariate analysis, physicians scored significantly higher compared to other healthcare professionals. Having received training regarding hepatitis B within the last two years was also significantly associated with a better HBV knowledge score. CONCLUSIONS: Findings from the survey indicated an immediate need to implement an effective hepatitis B education and training program to build capacity among Vietnam's healthcare workers in hepatitis B prevention and control and to dispel hepatitis B stigma.

Natural Language Processing Approaches to Detect the Timeline of Metastatic Recurrence of Breast Cancer.

PURPOSE: Electronic medical records (EMRs) and population-based cancer registries contain information on cancer outcomes and treatment, yet rarely capture information on the timing of metastatic cancer recurrence, which is essential to understand cancer survival outcomes. We developed a natural language processing (NLP) system to identify patient-specific timelines of metastatic breast cancer recurrence. PATIENTS AND METHODS: We used the OncoSHARE database, which includes merged data from the California Cancer Registry and EMRs of 8,956 women diagnosed with breast cancer in 2000 to 2018. We curated a comprehensive vocabulary by interviewing expert clinicians and processing radiology and pathology reports and progress notes. We developed and evaluated the following two distinct NLP approaches to analyze free-text notes: a traditional rule-based model, using rules for metastatic detection from the literature and curated by domain experts; and a contemporary neural network model. For each 3-month period (quarter) from 2000 to 2018, we applied both models to infer recurrence status for that quarter. We trained the NLP models using 894 randomly selected patient records that were manually reviewed by clinical experts and evaluated model performance using 179 hold-out patients (20%) as a test set. RESULTS: The median follow-up time was 19 quarters (5 years) for the training set and 15 quarters (4 years) for the test set. The neural network model predicted the timing of distant metastatic recurrence with a sensitivity of 0.83 and specificity of 0.73, outperforming the rule-based model, which had a specificity of 0.35 and sensitivity of 0.88 (P < .001). CONCLUSION: We developed an NLP method that enables identification of the occurrence and timing of metastatic breast cancer recurrence from EMRs. This approach may be adaptable to other cancer sites and could help to unlock the potential of EMRs for research on real-world cancer outcomes.

Machine Learning Approaches for Extracting Stage from Pathology Reports in Prostate Cancer.

Clinical and pathological stage are defining parameters in oncology, which direct a patient's treatment options and prognosis. Pathology reports contain a wealth of staging information that is not stored in structured form in most electronic health records (EHRs). Therefore, we evaluated three supervised machine learning methods (Support Vector Machine, Decision Trees, Gradient Boosting) to classify free-text pathology reports for prostate cancer into T, N and M stage groups.

Is it possible to automatically assess pretreatment digital rectal examination documentation using natural language processing? A single-centre retrospective study.

OBJECTIVES: To develop and test a method for automatic assessment of a quality metric, provider-documented pretreatment digital rectal examination (DRE), using the outputs of a natural language processing (NLP) framework. SETTING: An electronic health records (EHR)-based prostate cancer data warehouse was used to identify patients and associated clinical notes from 1 January 2005 to 31 December 2017. Using a previously developed natural language processing pipeline, we classified DRE assessment as documented (currently or historically performed), deferred (or suggested as a future examination) and refused. PRIMARY AND SECONDARY OUTCOME MEASURES: We investigated the quality metric performance, documentation 6 months before treatment and identified patient and clinical factors associated with metric performance. RESULTS: The cohort included 7215 patients with prostate cancer and 426 227 unique clinical notes associated with pretreatment encounters. DREs of 5958 (82.6%) patients were documented and 1257 (17.4%) of patients did not have a DRE documented in the EHR. A total of 3742 (51.9%) patient DREs were documented within 6 months prior to treatment, meeting the quality metric. Patients with private insurance had a higher rate of DRE 6 months prior to starting treatment as compared with Medicaid-based or Medicare-based payors (77.3%vs69.5%, p=0.001). Patients undergoing chemotherapy, radiation therapy or surgery as the first line of treatment were more likely to have a documented DRE 6 months prior to treatment. CONCLUSION: EHRs contain valuable unstructured information and with NLP, it is feasible to accurately and efficiently identify quality metrics with current documentation clinician workflow.