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.

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.

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.

Association of mental health diagnosis with race and all-cause mortality after a cancer diagnosis: Large-scale analysis of electronic health record data.

BACKGROUND: Disparity in mental health care among cancer patients remains understudied. METHODS: A large, retrospective, single tertiary-care institution cohort study was conducted based on deidentified electronic health record data of 54,852 adult cancer patients without prior mental health diagnosis (MHD) diagnosed at the University of California, San Francisco between January 2012 and September 2019. The exposure of interest was early-onset MHD with or without psychotropic medication (PM) within 12 months of cancer diagnosis and primary outcome was all-cause mortality. RESULTS: There were 8.2% of patients who received a new MHD at a median of 197 days (interquartile range, 61-553) after incident cancer diagnosis; 31.0% received a PM prescription; and 3.7% a mental health-related visit (MHRV). There were 62.6% of patients who were non-Hispanic White (NHW), 10.8% were Asian, 9.8% were Hispanic, and 3.8% were Black. Compared with NHWs, minority cancer patients had reduced adjusted odds of MHDs, PM prescriptions, and MHRVs, particularly for generalized anxiety (Asian odds ratio [OR], 0.66, 95% CI, 0.55-0.78; Black OR, 0.60, 95% CI, 0.45-0.79; Hispanic OR, 0.72, 95% CI, 0.61-0.85) and selective serotonin-reuptake inhibitors (Asian OR, 0.43, 95% CI, 0.37-0.50; Black OR, 0.51, 95% CI, 0.40-0.61; Hispanic OR, 0.79, 95% CI, 0.70-0.89). New early MHD with PM was associated with elevated all-cause mortality (12-24 months: hazard ratio [HR], 1.43, 95% CI, 1.25-1.64) that waned by 24 to 36 months (HR, 1.18, 95% CI, 0.95-1.45). CONCLUSIONS: New mental health diagnosis with PM was a marker of early mortality among cancer patients. Minority cancer patients were less likely to receive documentation of MHDs or treatment, which may represent missed opportunities to identify and treat cancer-related mental health conditions.

COVID-19 Outcomes Among Patients With Cancer: Observations From the University of California Cancer Consortium COVID-19 Project Outcomes Registry.

BACKGROUND: The risks associated with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its associated illness, coronavirus disease 2019 (COVID-19), among patients with a cancer diagnosis have not been fully characterized. This study leverages data from a multi-institutional cohort study, the University of California Cancer COVID Consortium, to evaluate outcomes associated with SARS-CoV-2 infection among patients with cancer. METHODS: Clinical data were collected from March to November 2020 and included patient demographics, cancer history and treatment, SARS-CoV-2 exposure and testing, and COVID-19 clinical management and outcomes. Multivariate ordinal logistic regression permitting unequal slopes was used to evaluate the impact of demographic, disease, and treatment factors on SARS-CoV-2 related hospitalization, intensive care unit (ICU) admission, and mortality. FINDINGS: Among all evaluated patients (n = 303), 147 (48%) were male, 118 (29%) were older adults (≥65 years old), and 104 (34%) were non-Hispanic white. A subset (n = 63, 21%) had hematologic malignancies and the remaining had solid tumors. Patients were hospitalized for acute care (n = 79, 26%), ICU-level care (n = 28, 9%), or died (n = 21, 7%) due to COVID-19. Patients with ≥2 comorbidities were more likely to require acute care (odds ratio [OR] 2.09 [95% confidence interval (CI), 1.23-3.55]). Cough was identified as a significant predictor of ICU hospitalization (OR 2.16 [95% CI, 1.03-4.57]). Importantly, mortality was associated with an active cancer diagnosis (OR 3.64 [95% CI, 1.40-9.5]) or advanced age (OR 3.86 [95% CI, 1.2-12.44]). INTERPRETATION: This study observed that patients with active cancer or advanced age are at an increased risk of death from COVID-19. These study observations can inform risk counseling related to COVID-19 for patients with a cancer diagnosis.

High-Risk Adenomas at Screening Colonoscopy Remain Predictive of Future High-Risk Adenomas Despite an Intervening Negative Colonoscopy.

INTRODUCTION: Limited data inform the current postpolypectomy surveillance guidelines, which suggest a shortened interval to third colonoscopy after a negative second examination if high-risk adenomas (HRA) were present on the initial screening colonoscopy. Therefore, we examined the risk of HRA at third colonoscopy stratified by findings on 2 previous examinations in a prospective screening colonoscopy cohort of US veterans. METHODS: We identified participants who had 3 or more colonoscopies from CSP#380. We examined the risk of HRA on the third examination based on findings from the previous 2 examinations. Multivariate logistic regression was used to adjust for multiple covariates. RESULTS: HRA were found at the third examination in 114 (12.8%) of 891 participants. Those with HRA on both previous examinations had the greatest incidence of HRA at third examination (14/56, 25.0%). Compared with those with no adenomas on both previous examinations, participants with HRA on the first examination remained at significantly increased risk for HRA at the third examination at 3 years after a negative second examination (odds ratio [OR] 3.41, 95% confidence interval [CI] 1.28-9.08), 5 years (OR 3.14, 95% CI 1.49-6.61), and 7 years (OR 2.89, 95% CI 1.08-7.74). DISCUSSION: In a screening population, HRA on the first examination identified individuals who remained at increased risk for HRA at the third examination, even after a negative second examination. This finding supports current colorectal cancer surveillance guidelines, which suggest a shortened, 5-year time interval to third colonoscopy after a negative second examination if high-risk findings were present on the baseline examination.

Survival Advantage With Adjuvant Chemotherapy for Locoregionally Advanced Rectal Cancer: A Veterans Health Administration Analysis.

BACKGROUND: Adjuvant chemotherapy (AC) after chemoradiation (CRT) and surgery for locoregionally advanced rectal cancer (LARC) is a standard of care in the United States. This study examined the role, optimal regimen, and duration of AC using data from the largest integrated health system in the United States. PATIENTS AND METHODS: Using the Veterans Affairs Central Cancer Registry, patients with stage II-III rectal cancer diagnosed in 2001 through 2011 who received neoadjuvant CRT and surgery with or without AC were identified. Kaplan-Meier analysis, log-rank tests, and propensity score (PS) adjustment analysis were used to assess survival. RESULTS: A total of 866 patients were identified; 417 received AC and 449 did not (observation [OBS] group). Median follow-up was 109 months. Median disease-specific survival (DSS) was not reached. Six-year DSS was 73.7%; 79.5% for the AC group versus 68.0% for the OBS group. PS-matched analysis for DSS favored AC (P=.0002). Median overall survival (OS) was 90.8 months. Six-year OS was 56.7%; 64.3% for AC versus 49.6% for OBS. In PS-matched analysis, median OS was 117.4 months for AC and 74.3 months for OBS (P<.0001). A DSS advantage was seen when comparing ≥4 months with <4 months of AC (P=.023). No difference in DSS or OS was seen with single-agent versus multiagent AC. CONCLUSIONS: In this population of patients with LARC treated with neoadjuvant CRT and surgery, OS and DSS were improved among those treated with AC versus OBS. DSS benefits were seen with ≥4 months of AC. No additional benefit was observed with multiagent therapy. In the absence of phase III data, these findings support the use of AC for LARC.

Increasing PET Use in Small Cell Lung Cancer: Survival Improvement and Stage Migration in the VA Central Cancer Registry.

Background: Accurate staging for small cell lung cancer (SCLC) is critical for determining appropriate therapy. The clinical impact of increasing PET adoption and stage migration is well described in non-small cell lung cancer but not in SCLC. The objective of this study was to evaluate temporal trends in PET staging and survival in the Veterans Affairs Central Cancer Registry and the impact of PET on outcomes. Patients and Methods: Patients diagnosed with SCLC from 2001 to 2010 were identified. PET staging, overall survival (OS), and lung cancer-specific survival (LCSS) were assessed over time. The impact of PET staging on OS and LCSS was assessed for limited-stage (LS) and extensive-stage (ES) SCLC. Results: From 2001 to 2010, PET use in a total of 10,135 patients with SCLC increased from 1.1% to 39.2%. Median OS improved for all patients (from 6.2 to 7.9 months), those with LS-SCLC (from 10.9 to 13.2 months), and those with ES-SCLC (from 5.0 to 7.0 months). Among staged patients, the proportion of ES-SCLC increased from 63.9% to 65.7%. Among 1,536 patients with LS-SCLC treated with concurrent chemoradiotherapy, 397 were staged by PET. In these patients, PET was associated with longer OS (median, 19.8 vs 14.3 months; hazard ratio [HR], 0.78; 95% CI, 0.68-0.90; P<.0001) and LCSS (median, 22.9 vs 16.7 months; HR, 0.74; 95% CI, 0.63-0.87; P<.0001) with multivariate adjustment and propensity-matching. In the 6,143 patients with ES-SCLC, PET was also associated with improved OS and LCSS. Conclusions: From 2001 to 2010, PET staging increased in this large cohort, with a corresponding relative increase in ES-SCLC. PET was associated with greater OS and LCSS for LS-SCLC and ES-SCLC, likely reflecting stage migration and stage-appropriate therapy. These findings emphasize the importance of PET in SCLC and support its routine use.

Primary Versus Preoperative Radiation for Locally Advanced Vulvar Cancer.

OBJECTIVES: The objective of this study was to evaluate patterns of care and the survival impact of primary radiation and preoperative radiation therapy with surgery in women with locally advanced vulvar cancer using a large national cohort. METHODS AND MATERIALS: Women with vulvar cancer, diagnosed from 2004 to 2012, who received primary or preoperative radiation therapy were identified in the National Cancer Database. Patient characteristics, such as age, race, American Joint Committee on Cancer stage, and comorbidity score, were compared between those that received primary radiation only and those that received preoperative radiation with surgery using the χ, Fisher exact, and Mann-Whitney tests as appropriate. Overall survival (OS) by treatment approaches was estimated via the Kaplan-Meier method and compared using the log-rank test. Factors associated with OS were determined using univariate and multivariate Cox proportional hazards regression models. RESULTS: A total of 2046 women were identified; 1407 of these women (69%) received primary radiation therapy (RT; n = 421) or chemoradiation therapy (CRT; n = 986) (RT/CRT), and 639 women (31%) received preoperative RT (n = 92) or CRT (n = 547) followed by surgery (RT/CRT + S). The American Joint Committee on Cancer staging distributions were as follows: T1 (n = 152), T2 (n = 1436), T3 (n = 405), N0 (n = 899), N1 (n = 480), N2 (n = 445), and N3 (n = 40). Median follow-up was 21.9 months. Primary RT/CRT was associated with compromised OS, compared with preoperative RT/CRT + S (41.7% vs 57.1% at 3 years, respectively; P < 0.001). On multivariate analysis, OS associated with primary RT/CRT with doses more than 55 Gy was not significantly different from RT/CRT + S (hazards ratio, 1.139; 95% confidence interval, 0.969-1.338; P = 0.116). Use of concurrent chemotherapy improved OS of primary RT with doses more than 55 Gy compared with CRT + S (hazards ratio, 1.107; 95% confidence interval, 0.919-1.334; P = 0.234). CONCLUSIONS: In a large nationwide analysis, primary nonsurgical management of vulvar cancer with RT was associated with compromised survival compared with preoperative RT with surgery. However, with doses more than 55 Gy and concurrent chemotherapy, nonoperative approaches had comparable survival compared with preoperative CRT + S.

Impact of Chemotherapy and Radiotherapy on Management of Early Stage Clear Cell and Papillary Serous Carcinoma of the Uterus.

OBJECTIVE: The aim of the study was to assess interaction of lymph node dissection (LND), adjuvant chemotherapy (CT), and radiotherapy (RT) in stage I uterine papillary serous carcinoma (UPSC) and uterine clear cell carcinoma (UCC). METHODS/MATERIALS: The National Cancer Data Base was queried for women diagnosed with International Federation of Gynecology and Obstetrics stage I UPSC and UCC from 1998 to 2012. Overall survival (OS) was estimated for combinations of RT and CT by the Kaplan-Meier method stratified by histology and LND. Multivariate Cox proportional hazard models were generated. RESULTS: Uterine papillary serous carcinoma: 5432 women with UPSC were identified. Uterine papillary serous carcinoma had the highest 5-year OS with CT + RT with (83%) or without LND (76%). On multivariate analyses, CT [hazard ratio (HR), 0.77; P = 0.01] and vaginal cuff brachytherapy (HR, 0.68; P = 0.003) with LND were independently associated with OS. Without LND, vaginal cuff brachytherapy (HR, 0.53; P = 0.03), but not CT (HR, 1.21; P = 0.92), was associated with OS. Uterine clear cell carcinoma: 2516 women with UCC were identified. Uterine clear cell carcinoma with and without LND had comparable 5-year OS for all combinations of CT and RT on univariate and multivariate analyses. CONCLUSIONS: In stage I papillary serous uterine cancer, brachytherapy and CT were associated with increased survival; however, the benefit of chemotherapy was limited to those with surgical staging. In contrast, no adjuvant therapy was associated with survival in stage I uterine clear cell carcinoma, and further investigation to identify more effective therapies is warranted.

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.

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.

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.).

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.

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.

Chemoradiotherapy before and after surgery for locally advanced esophageal cancer: a SEER-Medicare analysis.

PURPOSE: The optimal combination and timing of therapy for esophageal cancer remains controversial. The Surveillance, Epidemiology, and End Results (SEER)-Medicare registry was used to assess neoadjuvant and adjuvant therapy. METHODS: Patients diagnosed with nonmetastatic T3+ or N1+ esophageal adenocarcinoma (ACA) or squamous cell carcinoma (SCC) from 1995 to 2002 who underwent surgical resection within 6 months of diagnosis were studied. Medicare data defined preoperative chemoradiotherapy (preCRT), preoperative radiotherapy (preRT), postoperative CRT (postCRT), chemotherapy and surgery (CT + S), and surgery alone. RESULTS: Of 419 eligible patients, 126 received preCRT, 55 preRT, 40 postCRT, 29 CT + S, and 169 surgery alone. PreCRT yielded median overall survival (OS) of 37 months, greater than surgery alone (17 months, p = 0.002) and postCRT (17 months, p = 0.06). PreRT (20 months, p = 0.20), postCRT (p = 0.88), and CT + S (20 months, p = 0.42) were not associated with OS benefit versus surgery alone. For SCC, preCRT improved survival versus surgery alone (p = 0.01), with a trend for ACA (p = 0.07). ACA (22 months) had greater OS than SCC (17 months) (p = 0.03). ACA, younger age, and married status were associated with increased OS. Adjusting for these, preCRT had longer OS versus surgery alone (p = 0.02) and postCRT (p = 0.03). Chemotherapy agents and surgical approach did not affect OS. CONCLUSIONS: In the SEER-Medicare cohort, preCRT significantly improved survival versus surgery alone and postCRT for locally advanced esophageal cancer, particularly for SCC. PreRT, postCRT, and CT + S were not associated with longer survival.

Migration of implanted markers for image-guided lung tumor stereotactic ablative radiotherapy.

The purpose of this study was to quantify postimplantation migration of percutaneously implanted cylindrical gold seeds ("seeds") and platinum endovascular embolization coils ("coils") for tumor tracking in pulmonary stereotactic ablative radiotherapy (SABR). We retrospectively analyzed the migration of markers in 32 consecutive patients with computed tomography scans postimplantation and at simulation. We implanted 147 markers (59 seeds, 88 coils) in or around 34 pulmonary tumors over 32 procedures, with one lesion implanted twice. Marker coordinates were rigidly aligned by minimizing fiducial registration error (FRE), the root mean square of the differences in marker locations for each tumor between scans. To also evaluate whether single markers were responsible for most migration, we aligned with and without the outlier causing the largest FRE increase per tumor. We applied the resultant transformation to all markers. We evaluated migration of individual markers and FRE of each group. Median scan interval was 8 days. Median individual marker migration was 1.28 mm (interquartile range [IQR] 0.78-2.63 mm). Median lesion FRE was 1.56 mm (IQR 0.92-2.95 mm). Outlier identification yielded 1.03 mm median migration (IQR 0.52-2.21 mm) and 1.97 mm median FRE (IQR 1.44-4.32 mm). Outliers caused a mean and median shift in the centroid of 1.22 and 0.80 mm (95th percentile 2.52 mm). Seeds and coils had no statistically significant difference. Univariate analysis suggested no correlation of migration with the number of markers, contact with the chest wall, or time elapsed. Marker migration between implantation and simulation is limited and unlikely to cause geometric miss during tracking.

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.

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.