AI Use in Prostate Cancer: Potential Improvements in Treatments and Patient Care.

Artificial intelligence use in prostate cancer encompasses 4 main areas including diagnostic imaging, prediction of outcomes, histopathology, and treatment planning.

Determinants of Symptomatic Intracranial Progression After an Initial Stereotactic Radiosurgery Course.

Purpose: Clinical and imaging surveillance of patients with brain metastases is important after stereotactic radiosurgery (SRS) because many will experience intracranial progression (ITCP) requiring multidisciplinary management. The prognostic significance of neurologic symptoms at the time of ITCP is poorly understood. Methods and Materials: This was a multi-institutional, retrospective cohort study from 2015 to 2020, including all patients with brain metastases completing an initial course of SRS. The primary outcome was overall survival (OS) by presence of neurologic symptoms at ITCP. OS, freedom from ITCP (FF-ITCP), and freedom from symptomatic ITCP (FF-SITCP) were assessed via Kaplan-Meier method. Cox proportional hazard models tested parameters impacting FF-ITCP and FF-SITCP. Results: Among 1383 patients, median age was 63.4 years, 55% were female, and common primaries were non-small cell lung (49%), breast (15%), and melanoma (9%). At a median follow-up of 8.72 months, asymptomatic and symptomatic ITCP were observed in 504 (36%) and 194 (14%) patients, respectively. The majority of ITCP were distant ITCP (79.5%). OS was worse with SITCP (median, 10.2 vs 17.9 months, P < .001). SITCP was associated with clinical factors including total treatment volume (P = .012), melanoma histology (P = .001), prior whole brain radiation therapy (P = .003), number of brain metastases (P < .001), interval of 1 to 2 years from primary and brain metastasis diagnosis (P = .012), controlled extracranial disease (P = .042), and receipt of pre-SRS chemotherapy (P = .015). Patients who were younger and received post-SRS chemotherapy (P = .001), immunotherapy (P < .001), and targeted or small-molecule inhibitor therapy (P < .026) had better FF-SITCP. Conclusions: In this cohort study of patients with brain metastases completing SRS, neurologic symptoms at ITCP is prognostic for OS. This data informs post-SRS surveillance in clinical practice as well as future prospective studies needed in the modern management of brain metastases.

Health Care Cost Reductions with Machine Learning-Directed Evaluations during Radiation Therapy - An Economic Analysis of a Randomized Controlled Study.

BACKGROUND: Machine learning (ML) may cost-effectively direct health care by identifying patients most likely to benefit from preventative interventions to avoid negative and expensive outcomes. System for High-Intensity Evaluation During Radiation Therapy (SHIELD-RT; NCT04277650) was a single-institution, randomized controlled study in which electronic health record-based ML accurately identified patients at high risk for acute care (emergency visit or hospitalization) during radiotherapy (RT) and targeted them for supplemental clinical evaluations. This ML-directed intervention resulted in decreased acute care utilization. Given the limited prospective data showing the ability of ML to direct interventions cost-efficiently, an economic analysis was performed. METHODS: A post hoc economic analysis was conducted of SHIELD-RT that included RT courses from January 7, 2019, to June 30, 2019. ML-identified high-risk courses (≥10% risk of acute care during RT) were randomized to receive standard of care weekly clinical evaluations with ad hoc supplemental evaluations per clinician discretion versus mandatory twice-weekly evaluations. The primary outcome was difference in mean total medical costs during and 15 days after RT. Acute care costs were obtained via institutional cost accounting. Physician and intervention costs were estimated via Medicare and Medicaid data. Negative binomial regression was used to estimate cost outcomes after adjustment for patient and disease factors. RESULTS: A total of 311 high-risk RT courses among 305 patients were randomized to the standard (n=157) or the intervention (n=154) group. Unadjusted mean intervention group supplemental visit costs were $155 per course (95% confidence interval, $142 to $168). The intervention group had fewer acute care visits per course (standard, 0.47; intervention, 0.31; P=0.04). Total mean adjusted costs were $3110 per course for the standard group and $1494 for the intervention group (difference in means, $1616 [95% confidence interval, $1450 to $1783]; P=0.03). CONCLUSIONS: In this economic analysis of a randomized controlled, health care ML study, mandatory supplemental evaluations for ML-identified high-risk patients were associated with both reduced total medical costs and improved clinical outcomes. Further study is needed to determine whether economic results are generalizable. (Funded in part by The Duke Endowment, The Conquer Cancer Foundation, the Duke Department of Radiation Oncology, and the National Cancer Institute of the National Institutes of Health [R01CA277782]; ClinicalTrials.gov number, NCT04277650.).

Machine Learning-Based Prediction of Hospitalization During Chemoradiotherapy With Daily Step Counts.

Importance: Toxic effects of concurrent chemoradiotherapy (CRT) can cause treatment interruptions and hospitalizations, reducing treatment efficacy and increasing health care costs. Physical activity monitoring may enable early identification of patients at high risk for hospitalization who may benefit from proactive intervention. Objective: To develop and validate machine learning (ML) approaches based on daily step counts collected by wearable devices on prospective trials to predict hospitalizations during CRT. Design, Setting, and Participants: This study included patients with a variety of cancers enrolled from June 2015 to August 2018 on 3 prospective, single-institution trials of activity monitoring using wearable devices during CRT. Patients were followed up during and 1 month following CRT. Training and validation cohorts were generated temporally, stratifying for cancer diagnosis (70:30). Random forest, neural network, and elastic net-regularized logistic regression (EN) were trained to predict short-term hospitalization risk based on a combination of clinical characteristics and the preceding 2 weeks of activity data. To predict outcomes of activity data, models based only on activity-monitoring features and only on clinical features were trained and evaluated. Data analysis was completed from January 2022 to March 2023. Main Outcomes and Measures: Model performance was evaluated in terms of the receiver operating characteristic area under curve (ROC AUC) in the stratified temporal validation cohort. Results: Step counts from 214 patients (median [range] age, 61 [53-68] years; 113 [52.8%] male) were included. EN based on step counts and clinical features had high predictive ability (ROC AUC, 0.83; 95% CI, 0.66-0.92), outperforming random forest (ROC AUC, 0.76; 95% CI, 0.56-0.87; P = .02) and neural network (ROC AUC, 0.80; 95% CI, 0.71-0.88; P = .36). In an ablation study, the EN model based on only step counts demonstrated greater predictive ability than the EN model with step counts and clinical features (ROC AUC, 0.85; 95% CI, 0.70-0.93; P = .09). Both models outperformed the EN model trained on only clinical features (ROC AUC, 0.53; 95% CI, 0.31-0.66; P < .001). Conclusions and Relevance: This study developed and validated a ML model based on activity-monitoring data collected during prospective clinical trials. Patient-generated health data have the potential to advance predictive ability of ML approaches. The resulting model from this study will be evaluated in an upcoming multi-institutional, cooperative group randomized trial.

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways.

Natural language processing (NLP), a technology that translates human language into machine-readable data, is revolutionizing numerous sectors, including cancer care. This review outlines the evolution of NLP and its potential for crafting personalized treatment pathways for cancer patients. Leveraging NLP's ability to transform unstructured medical data into structured learnable formats, researchers can tap into the potential of big data for clinical and research applications. Significant advancements in NLP have spurred interest in developing tools that automate information extraction from clinical text, potentially transforming medical research and clinical practices in radiation oncology. Applications discussed include symptom and toxicity monitoring, identification of social determinants of health, improving patient-physician communication, patient education, and predictive modeling. However, several challenges impede the full realization of NLP's benefits, such as privacy and security concerns, biases in NLP models, and the interpretability and generalizability of these models. Overcoming these challenges necessitates a collaborative effort between computer scientists and the radiation oncology community. This paper serves as a comprehensive guide to understanding the intricacies of NLP algorithms, their performance assessment, past research contributions, and the future of NLP in radiation oncology research and clinics.

Multi-institutional Development and External Validation of a Machine Learning Model for the Prediction of Distant Metastasis in Patients Treated by Salvage Radiotherapy for Biochemical Failure After Radical Prostatectomy.

BACKGROUND: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy (SRT) being the only curative option. In 2016, Tendulkar et al. (Contemporary update of a multi-institutional predictive nomogram for salvage radiotherapy after radical prostatectomy. J Clin Oncol 2016;34:3648-54) published a nomogram to predict distant metastasis in a cohort of patients treated with SRT with pre-SRT prostate-specific antigen (PSA) of 0.5 ng/ml after radical prostatectomy. In modern practice, SRT is delivered at lower PSA values. OBJECTIVE: To train and externally validate a machine learning model to predict the risk of distant metastasis at 5 yr in a contemporary cohort of patients receiving SRT. DESIGN, SETTING, AND PARTICIPANTS: We trained a machine learning model on data from 2418 patients treated with SRT at one institution, with a median PSA value of 0.27 ng/ml. External validation was done in 475 patients treated at two different institutions. Patients with cM1, pN1, or pT4 disease were excluded, as were patients with PSA >2 ng/ml or PSA 0, and patients with radiation dose <60 or ≥80 Gy. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Model performance was assessed using calibration and time-dependent area under the receiver operating curve (tAUC). RESULTS AND LIMITATIONS: Our model had better calibration and showed improved discrimination (tAUC = 0.72) compared with the Tendulkar model (tAUC = 0.60, p < 0.001). The main limitations of this study are its retrospective design and lack of validation on patients who received hormone therapy. CONCLUSIONS: The updated model can be used to provide more individualized risk assessments to patients treated with SRT at low PSA values, improving decision-making. PATIENT SUMMARY: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy as the only potentially curative option. We trained and validated a machine learning model using clinical and surgical data to predict a patient's risk of distant metastasis at 5 yr after treatment. Our model outperformed the reference tool and can improve clinical decision-making by providing more personalized risk assessment.

Ctrl-C: a cross-sectional study of the electronic health record usage patterns of US oncology clinicians.

Despite some positive impact, the use of electronic health records (EHRs) has been associated with negative effects, such as emotional exhaustion. We sought to compare EHR use patterns for oncology vs nononcology medical specialists. In this cross-sectional study, we employed EHR usage data for 349 ambulatory health-care systems nationwide collected from the vendor Epic from January to August 2019. We compared note composition, message volume, and time in the EHR system for oncology vs nononcology clinicians. Compared with nononcology medical specialists, oncologists had a statistically significantly greater percentage of notes derived from Copy and Paste functions but less SmartPhrase use. They received more total EHR messages per day than other medical specialists, with a higher proportion of results and system-generated messages. Our results point to priorities for enhancing EHR systems to meet the needs of oncology clinicians, particularly as related to facilitating the complex documentation, results, and therapy involved in oncology care.

Unlocking the Power of ChatGPT, Artificial Intelligence, and Large Language Models: Practical Suggestions for Radiation Oncologists.

Recent advances in artificial intelligence (AI), such as generative AI and large language models (LLMs), have generated significant excitement about the potential of AI to revolutionize our lives, work, and interaction with technology. This article explores the practical applications of LLMs, particularly ChatGPT, in the field of radiation oncology. We offer a guide on how radiation oncologists can interact with LLMs like ChatGPT in their routine clinical and administrative tasks, highlighting potential use cases of the present and future. We also highlight limitations and ethical considerations, including the current state of LLMs in decision making, protection of sensitive data, and the important role of human review of AI-generated content.

Operational Ontology for Oncology (O3): A Professional Society-Based, Multistakeholder, Consensus-Driven Informatics Standard Supporting Clinical and Research Use of Real-World Data From Patients Treated for Cancer.

PURPOSE: The ongoing lack of data standardization severely undermines the potential for automated learning from the vast amount of information routinely archived in electronic health records (EHRs), radiation oncology information systems, treatment planning systems, and other cancer care and outcomes databases. We sought to create a standardized ontology for clinical data, social determinants of health, and other radiation oncology concepts and interrelationships. METHODS AND MATERIALS: The American Association of Physicists in Medicine's Big Data Science Committee was initiated in July 2019 to explore common ground from the stakeholders' collective experience of issues that typically compromise the formation of large inter- and intra-institutional databases from EHRs. The Big Data Science Committee adopted an iterative, cyclical approach to engaging stakeholders beyond its membership to optimize the integration of diverse perspectives from the community. RESULTS: We developed the Operational Ontology for Oncology (O3), which identified 42 key elements, 359 attributes, 144 value sets, and 155 relationships ranked in relative importance of clinical significance, likelihood of availability in EHRs, and the ability to modify routine clinical processes to permit aggregation. Recommendations are provided for best use and development of the O3 to 4 constituencies: device manufacturers, centers of clinical care, researchers, and professional societies. CONCLUSIONS: O3 is designed to extend and interoperate with existing global infrastructure and data science standards. The implementation of these recommendations will lower the barriers for aggregation of information that could be used to create large, representative, findable, accessible, interoperable, and reusable data sets to support the scientific objectives of grant programs. The construction of comprehensive "real-world" data sets and application of advanced analytical techniques, including artificial intelligence, holds the potential to revolutionize patient management and improve outcomes by leveraging increased access to information derived from larger, more representative data sets.

Intracranial and Extracranial Progression and Their Correlation With Overall Survival After Stereotactic Radiosurgery in a Multi-institutional Cohort With Brain Metastases.

Importance: Clinical trials for metastatic malignant neoplasms are increasingly being extended to patients with brain metastases. Despite the preeminence of progression-free survival (PFS) as a primary oncologic end point, the correlation of intracranial progression (ICP) and extracranial progression (ECP) events with overall survival (OS) is poorly understood for patients with brain metastases following stereotactic radiosurgery (SRS). Objective: To determine the correlation of ICP and ECP with OS among patients with brain metastases completing an initial SRS course. Design, Setting, and Participants: This multi-institutional retrospective cohort study was conducted from January 1, 2015, to December 31, 2020. We included patients who completed an initial course of SRS for brain metastases during the study period, including receipt of single and/or multifraction SRS, prior whole-brain radiotherapy, and brain metastasis resection. Data analysis was performed on November 15, 2022. Exposures: Non-OS end points included intracranial PFS, extracranial PFS, PFS, time to ICP, time to ECP, and any time to progression. Progression events were radiologically defined, incorporating multidisciplinary clinical consensus. Main Outcomes and Measures: The primary outcome was correlation of surrogate end points to OS. Clinical end points were estimated from time of SRS completion via the Kaplan-Meier method, while end-point correlation to OS was measured using normal scores rank correlation with the iterative multiple imputation approach. Results: This study included 1383 patients, with a mean age of 63.1 years (range, 20.9-92.8 years) and a median follow-up of 8.72 months (IQR, 3.25-19.68 months). The majority of participants were White (1032 [75%]), and more than half (758 [55%]) were women. Common primary tumor sites included the lung (757 [55%]), breast (203 [15%]), and skin (melanoma; 100 [7%]). Intracranial progression was observed in 698 patients (50%), preceding 492 of 1000 observed deaths (49%). Extracranial progression was observed in 800 patients (58%), preceding 627 of 1000 observed deaths (63%). Irrespective of deaths, 482 patients (35%) experienced both ICP and ECP, 534 (39%) experienced ICP (216 [16%]) or ECP (318 [23%]), and 367 (27%) experienced neither. The median OS was 9.93 months (95% CI, 9.08-11.05 months). Intracranial PFS had the highest correlation with OS (ρ = 0.84 [95% CI, 0.82-0.85]; median, 4.39 months [95% CI, 4.02-4.92 months]). Time to ICP had the lowest correlation with OS (ρ = 0.42 [95% CI, 0.34-0.50]) and the longest median time to event (median, 8.76 months [95% CI, 7.70-9.48 months]). Across specific primary tumor types, correlations of intracranial PFS and extracranial PFS with OS were consistently high despite corresponding differences in median outcome durations. Conclusions and Relevance: The results of this cohort study of patients with brain metastases completing SRS suggest that intracranial PFS, extracranial PFS, and PFS had the highest correlations with OS and time to ICP had the lowest correlation with OS. These data may inform future patient inclusion and end-point selection for clinical trials.

Development and External Validation of a Machine Learning Model for Prediction of Lymph Node Metastasis in Patients with Prostate Cancer.

BACKGROUND: Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND. OBJECTIVE: To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables. DESIGN, SETTING, AND PARTICIPANTS: Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA). RESULTS AND LIMITATIONS: LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design. CONCLUSIONS: Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI. PATIENT SUMMARY: Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.

Healthcare provider evaluation of machine learning-directed care: reactions to deployment on a randomised controlled study.

OBJECTIVES: Clinical artificial intelligence and machine learning (ML) face barriers related to implementation and trust. There have been few prospective opportunities to evaluate these concerns. System for High Intensity EvaLuation During Radiotherapy (NCT03775265) was a randomised controlled study demonstrating that ML accurately directed clinical evaluations to reduce acute care during cancer radiotherapy. We characterised subsequent perceptions and barriers to implementation. METHODS: An anonymous 7-question Likert-type scale survey with optional free text was administered to multidisciplinary staff focused on workflow, agreement with ML and patient experience. RESULTS: 59/71 (83%) responded. 81% disagreed/strongly disagreed their workflow was disrupted. 67% agreed/strongly agreed patients undergoing intervention were high risk. 75% agreed/strongly agreed they would implement the ML approach routinely if the study was positive. Free-text feedback focused on patient education and ML predictions. CONCLUSIONS: Randomised data and firsthand experience support positive reception of clinical ML. Providers highlighted future priorities, including patient counselling and workflow optimisation.

Serial stereotactic body radiation therapy for oligometastatic prostate cancer detected by novel PET-based radiotracers.

BACKGROUND: Radiopharmaceuticals, including Ga-68-prostate specific membrane antigen (PSMA)-11 and F-18-Fluciclovine, are increasingly used to inform therapies for prostate cancer (CaP). Stereotactic body radiation therapy (SBRT) to PET-detected oligometastatic CaP has been shown to improve progression free survival (PFS) and delay androgen deprivation therapy (ADT) compared to observation. For men who subsequently develop oligorecurrent CaP, outcomes following second SBRT are unknown. METHODS: A retrospective cohort study was conducted. Eligibility criteria included patients with oligometastatic (1-5 lesions) CaP detected on PSMA or Fluciclovine PET who underwent 2 consecutive SBRT courses to tracer-avid sites. Data on stage, tracer type, concurrent systemic therapy, and prostate-specific antigen (PSA) responses for first SBRT (SBRT1) and second SBRT (SBRT2) were collected. Outcomes included PSA decline ≥50% (PSA50), PFS after SBRT2, and ADT initiation or intensification-free survival after SBRT2. Factors potentially associated with PSA50 after SBRT2 was evaluated with multivariable logistic regression. Factors potentially associated with PFS and ADT initiation/intensification-free survival after SBRT2 were evaluated with separate multivariable Cox proportional-hazards models. RESULTS: Twenty-five patients were identified. At SBRT2, oligorecurrence was detected on PSMA and Fluciclovine PET in 17 (68%) and 8 (32%) patients, respectively. Fifteen (60%) patients had castration-sensitive disease and 10 (40%) had castration-resistant disease. After SBRT2, 16 (64%) achieved a PSA50 response, median PFS was 11.0mo, and median ADT initiation/intensification-free survival was 23.2mo. On multivariable analysis, maximum percent change in PSA after SBRT1 (OR 0.94, 95%CI 0.88-0.99, P = 0.046) and concurrent change in systemic therapy (OR 21.61, 95%CI 1.12-417.9, P = 0.042) were associated with PSA50 responses after SBRT2. PSA50 response after SBRT1 was associated with improved PFS (HR 0.36, 95%CI 0.00-0.42, P = 0.008) and ADT initiation/intensification-free survival (HR 0.07, 95%CI 0.01-0.68, P = 0.021) after SBRT2. From SBRT1 to last follow-up (median 48 months), 7 (28%) patients remained ADT-free. CONCLUSIONS: Serial SBRT for oligometastatic CaP detected on PSMA or Fluciclovine PET is feasible and can achieve PSA declines, with or without systemic therapy. Degree of biochemical response to first SBRT warrants further study as a potential predictor of PSA response, PFS, and ADT initiation/intensification-free survival following a subsequent SBRT course. This preliminary evidence provides rationale for larger, prospective studies of this strategy.

Assessing Unique Risk Factors for COVID-19 Complications Among Cancer Patients: A Multi-ethnic Cohort Study.

A myriad of organ-specific complications have been observed with COVID-19. While racial/ethnic minorities have been disproportionately burdened by this disease, our understanding of the unique risk factors for complications among a diverse population of cancer patients remains limited. This is a multi-institutional, multi-ethnic cohort study evaluating COVID-19 complications among cancer patients. Patients with an invasive cancer diagnosis and confirmed SARS-CoV-2 infection were identified from March to November 2020. Demographic and clinical data were obtained and a multivariate logistic regression was employed to evaluate the impact of demographic and clinical factors on COVID-19 complications. The study endpoints were evaluated independently and included any complication, sepsis, pulmonary complications and cardiac complications. A total of 303 patients were evaluated, of whom 48% were male, 79% had solid tumors, and 42% were Hispanic/Latinx (Hispanic). Malignant hematologic cancers were associated with a higher risk of sepsis (OR 3.93 (95% CI 1.58-9.81)). Male patients had a higher risk of sepsis (OR 4.42 (95% CI 1.63-11.96)) and cardiac complications (OR 2.02 (95% CI 1.05-3.89)). Hispanic patients had a higher odds of any complication (OR 2.31 (95% CI 1.18-4.51)) and other race was associated with a higher odds of cardiac complications (OR 2.41 (95% CI 1.01-5.73)). Clinically, fever, cough, and ≥2 co-morbidities were independently significantly associated with any complication. This analysis evaluated covariates that can significantly predict a myriad of complications among a multi-ethnic cohort of cancer patients. The conclusions drawn from this analysis elucidate a mechanistic understanding of differential illness severity from COVID-19.

A Clinical Reasoning-Encoded Case Library Developed through Natural Language Processing.

IMPORTANCE: Case reports that externalize expert diagnostic reasoning are utilized for clinical reasoning instruction but are difficult to search based on symptoms, final diagnosis, or differential diagnosis construction. Computational approaches that uncover how experienced diagnosticians analyze the medical information in a case as they formulate a differential diagnosis can guide educational uses of case reports. OBJECTIVE: To develop a "reasoning-encoded" case database for advanced clinical reasoning instruction by applying natural language processing (NLP), a sub-field of artificial intelligence, to a large case report library. DESIGN: We collected 2525 cases from the New England Journal of Medicine (NEJM) Clinical Pathological Conference (CPC) from 1965 to 2020 and used NLP to analyze the medical terminology in each case to derive unbiased (not prespecified) categories of analysis used by the clinical discussant. We then analyzed and mapped the degree of category overlap between cases. RESULTS: Our NLP algorithms identified clinically relevant categories that reflected the relationships between medical terms (which included symptoms, signs, test results, pathophysiology, and diagnoses). NLP extracted 43,291 symptoms across 2525 cases and physician-annotated 6532 diagnoses (both primary and related diagnoses). Our unsupervised learning computational approach identified 12 categories of medical terms that characterized the differential diagnosis discussions within individual cases. We used these categories to derive a measure of differential diagnosis similarity between cases and developed a website ( universeofcpc.com ) to allow visualization and exploration of 55 years of NEJM CPC case series. CONCLUSIONS: Applying NLP to curated instances of diagnostic reasoning can provide insight into how expert clinicians correlate and coordinate disease categories and processes when creating a differential diagnosis. Our reasoning-encoded CPC case database can be used by clinician-educators to design a case-based curriculum and by physicians to direct their lifelong learning efforts.

Prognostic Model for Intracranial Progression after Stereotactic Radiosurgery: A Multicenter Validation Study.

Stereotactic radiosurgery (SRS) is a standard of care for many patients with brain metastases. To optimize post-SRS surveillance, this study aimed to validate a previously published nomogram predicting post-SRS intracranial progression (IP). We identified consecutive patients completing an initial course of SRS across two institutions between July 2017 and December 2020. Patients were classified as low- or high-risk for post-SRS IP per a previously published nomogram. Overall survival (OS) and freedom from IP (FFIP) were assessed via the Kaplan−Meier method. Assessment of parameters impacting FFIP was performed with univariable and multivariable Cox proportional hazard models. Among 890 patients, median follow-up was 9.8 months (95% CI 9.1−11.2 months). In total, 47% had NSCLC primary tumors, and 47% had oligometastatic disease (defined as ≤5 metastastic foci) at the time of SRS. Per the IP nomogram, 53% of patients were deemed high-risk. For low- and high-risk patients, median FFIP was 13.9 months (95% CI 11.1−17.1 months) and 7.6 months (95% CI 6.4−9.3 months), respectively, and FFIP was superior in low-risk patients (p < 0.0001). This large multisite BM cohort supports the use of an IP nomogram as a quick and simple means of stratifying patients into low- and high-risk groups for post-SRS IP.

Severe extra-glandular involvement and pleural effusions complicating primary Sjogren's syndrome: a case report.

BACKGROUND: Sjogren's syndrome, an autoimmune disease of the exocrine glands, results in keratoconjunctivitis sicca, xerostomia, and dental caries. It is often overlooked, considered by clinicians to be a benign disease. However, it can cause life-threatening extra-glandular complications that affect multiple organ systems. CASE PRESENTATION: Here we present a 78-year-old Caucasian woman with a history of primary Sjogren's syndrome (pSS) whose symptoms of keratoconjunctivitis sicca were managed managed conservatively. She was evaluated for sub-acute shortness of breath. Imaging showed severe bronchiectasis with features of lymphocytic interstitial pneumonia. She also had exudative bilateral pleural effusions and skin ulcers, likely vasculitic in origin. The workup was significant for anti-Ro antibody, pancytopenia, hypocomplementia, cryoglobulinemia and monoclonal gammopathy, all of which reflect disease severity. Although there was no evidence of malignancy, she developed B-cell non-Hodgkin lymphoma during follow-up. CONCLUSIONS: Primary Sjogren's syndrome can result in severe multi-organ disease. Pleural effusions are a rare complication of pSS, with only ten cases reported in the literature over the last 30 years, and tend to respond well to steroids. Prognostic biomarkers for disease severity include hypocomplementia, cryoglobulinemia, monoclonal gammopathy, and hypergammaglobulinemia. In this report we review the literature and the management of the disease.

Analysis of Serious Adverse Event Reporting for Patients Enrolled in Cancer Clinical Trials During the COVID-19 Pandemic.

This cross-sectional study assesses whether a change occurred in reporting of serious adverse events for patients in oncology clinical trials in the US during the COVID-19 pandemic.

Implementation of machine learning in the clinic: challenges and lessons in prospective deployment from the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) randomized controlled study.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) have resulted in significant enthusiasm for their promise in healthcare. Despite this, prospective randomized controlled trials and successful clinical implementation remain limited. One clinical application of ML is mitigation of the increased risk for acute care during outpatient cancer therapy. We previously reported the results of the System for High Intensity EvaLuation During Radiation Therapy (SHIELD-RT) study (NCT04277650), which was a prospective, randomized quality improvement study demonstrating that ML based on electronic health record (EHR) data can direct supplemental clinical evaluations and reduce the rate of acute care during cancer radiotherapy with and without chemotherapy. The objective of this study is to report the workflow and operational challenges encountered during ML implementation on the SHIELD-RT study. RESULTS: Data extraction and manual review steps in the workflow represented significant time commitments for implementation of clinical ML on a prospective, randomized study. Barriers include limited data availability through the standard clinical workflow and commercial products, the need to aggregate data from multiple sources, and logistical challenges from altering the standard clinical workflow to deliver adaptive care. CONCLUSIONS: The SHIELD-RT study was an early randomized controlled study which enabled assessment of barriers to clinical ML implementation, specifically those which leverage the EHR. These challenges build on a growing body of literature and may provide lessons for future healthcare ML adoption. TRIAL REGISTRATION: NCT04277650. Registered 20 February 2020. Retrospectively registered quality improvement study.

Opportunities to use electronic health record audit logs to improve cancer care.

The rapid adoption of electronic health records (EHRs) has created extensive repositories of digitized data that can be used to inform improvements in care delivery, processes, and patient outcomes. While the clinical data captured in EHRs are widely used for such efforts, EHRs also capture audit log data that reflect how users interact with the EHR to deliver care. Automatically collected audit log data provide a unique opportunity for new insights into EHR user behavior and decision-making processes. Here, we provide an overview of audit log data and examples that could be used to improve oncology care and outcomes in four domains: diagnostic reasoning and consumption, care team collaboration and communication, patient outcomes and experience, and provider burnout/fatigue. This data source could identify gaps in performance and care, physician uptake of EHR features that enhance decision-making, and integration of data trends for oncology. Ensuring researchers and oncologists are familiar with the data's potential and developing the data engineering capacity to utilize this rich data source, will expand the breadth of research to improve cancer care.