Automated detection of causal relationships among diseases and imaging findings in textual radiology reports.

OBJECTIVE: Textual radiology reports contain a wealth of information that may help understand associations among diseases and imaging observations. This study evaluated the ability to detect causal associations among diseases and imaging findings from their co-occurrence in radiology reports. MATERIALS AND METHODS: This IRB-approved and HIPAA-compliant study analyzed 1 702 462 consecutive reports of 1 396 293 patients; patient consent was waived. Reports were analyzed for positive mention of 16 839 entities (disorders and imaging findings) of the Radiology Gamuts Ontology (RGO). Entities that occurred in fewer than 25 patients were excluded. A Bayesian network structure-learning algorithm was applied at P < 0.05 threshold: edges were evaluated as possible causal relationships. RGO and/or physician consensus served as ground truth. RESULTS: 2742 of 16 839 RGO entities were included, 53 849 patients (3.9%) had at least one included entity. The algorithm identified 725 pairs of entities as causally related; 634 were confirmed by reference to RGO or physician review (87% precision). As shown by its positive likelihood ratio, the algorithm increased detection of causally associated entities 6876-fold. DISCUSSION: Causal relationships among diseases and imaging findings can be detected with high precision from textual radiology reports. CONCLUSION: This approach finds causal relationships among diseases and imaging findings with high precision from textual radiology reports, despite the fact that causally related entities represent only 0.039% of all pairs of entities. Applying this approach to larger report text corpora may help detect unspecified or heretofore unrecognized associations.

Is Heterotopic Ossification Associated With Surgical Approach in Total Hip Arthroplasty?

BACKGROUND: Although risk factors for heterotopic ossification (HO) have been defined, the effect from surgical approach is not fully understood. The primary objective of our study was to evaluate the effect that surgical approach has on the risk for developing severe HO after total hip arthroplasty (THA) and compare this with other known risk factors. We hypothesized that there would be no difference in HO formation based on the surgical approach. METHODS: We retrospectively reviewed all patients who underwent primary THA at our hospital between March 2011 and March 2021. Patients with HO documented in the radiology reports were cross-referenced with our THA data set and manually reviewed to determine Brooker classification. Patient demographics, medical comorbidities, surgical details, and medication information were collected from the electronic medical record and compared. RESULTS: Of 3,427 patients who underwent THA, 677 (19.8%) developed HO postoperatively. A multivariable analysis confirmed that surgical approach was independently associated with increased odds for HO development. The anterolateral (odds ratio [OR], 3.43; P < 0.001) and posterior (OR, 2.24; P < 0.001) approaches had increased odds for developing HO compared with the direct anterior approach. However, only the anterolateral approach (OR, 1.85; P = 0.033) demonstrated an increased association with the development of severe HO (Brooker 3, 4) postoperatively. CONCLUSION: Although the use of the direct anterior approach had the lowest overall OR for developing HO after THA, this is likely only clinically notable when compared with the anterolateral approach. LEVEL OF EVIDENCE: III.

In vivo intra-articular contrast enhanced µCT imaging of mouse knee cartilage.

In vivo micro-Computed Tomography (µCT) is commonly used tool in the study of mouse bone architecture. However, in vivo imaging of mouse cartilage has been limited. Intra-articular contrast injection was evaluated for its utility in detecting mouse cartilage in µCT. Clinically used iodinated contrast agent was chosen for its widespread commercial availability. Imaging protocol was developed with wild type C57BL/6 mice for its ability to detect expected cartilage thinning that occurs with sexual maturity. The protocol was then validated with transgenic mouse model with known extracellular matrix loss. µCT findings showed good correspondence with histological assessment. In conclusion, in vivo intra-articular contrast-enhanced µCT arthrography is viable technique for evaluation of mouse cartilage. SUMMARY: In vivo intra-articular contrast enhanced µCT of the mouse knee joint can delineate cartilage thickness and extracellular matrix content. The imaging protocol may be useful for longitudinal evaluation of cartilage anomalies in transgenicmouse model.

Racial and Ethnic Diversity Among Students, Graduates, and Faculty in Biostatistics and Epidemiology, 2010-2020.

OBJECTIVE: This study is a follow-up to a study in 2020 that reviewed changes in the racial and ethnic composition of public health students, graduates, and faculty among Association of Schools and Programs of Public Health (ASPPH)-member institutions. In the current study, we evaluated how the racial and ethnic composition among biostatistics and epidemiology students, graduates, and faculty changed from 2010 to 2020. METHODS: We analyzed data on race and ethnicity of enrolled graduate students, graduates (master's and doctoral), and faculty at ASPPH-member institutions by using institutionally reported data from the ASPPH Data Center. We tabulated frequencies, percentages, and percentage-point changes by race and ethnicity. We measured differences between groups by using a test for difference in 2 proportions. RESULTS: The number of enrolled students, graduates, and faculty in all departments increased during the study period, while the number of tenure-track faculty in biostatistics decreased. The percentage of enrolled Hispanic/Latino biostatistics graduate students increased from 5.6% in 2010 to 10.2% in 2020 (P = .007), and the percentage of epidemiology graduates increased from 8.8% to 13.8% (P = .008). We found no differences among other underrepresented racial and ethnic groups. Most biostatistics and epidemiology professors at all ranks were non-Hispanic White, despite substantial decreases. The percentage of underrepresented racial and ethnic minority biostatistics and epidemiology professors was constant across all ranks. CONCLUSION: Although more Hispanic/Latino students are enrolled in and graduating from biostatistics and epidemiology departments at ASPPH-member institutions, we found no change among faculty. More work is needed to recruit and retain other (American Indian/Alaska Native, Black or African American, Native Hawaiian/Other Pacific Islander) underrepresented students and faculty.

Pre-deployment assessment of an AI model to assist radiologists in chest X-ray detection and identification of lead-less implanted electronic devices for pre-MRI safety screening: realized implementation needs and proposed operational solutions.

Purpose: Chest X-ray (CXR) use in pre-MRI safety screening, such as for lead-less implanted electronic device (LLIED) recognition, is common. To assist CXR interpretation, we "pre-deployed" an artificial intelligence (AI) model to assess (1) accuracies in LLIED-type (and consequently safety-level) identification, (2) safety implications of LLIED nondetections or misidentifications, (3) infrastructural or workflow requirements, and (4) demands related to model adaptation to real-world conditions. Approach: A two-tier cascading methodology for LLIED detection/localization and identification on a frontal CXR was applied to evaluate the performance of the original nine-class AI model. With the unexpected early appearance of LLIED types during simulated real-world trialing, retraining of a newer 12-class version preceded retrialing. A zero footprint (ZF) graphical user interface (GUI)/viewer with DICOM-based output was developed for inference-result display and adjudication, supporting end-user engagement and model continuous learning and/or modernization. Results: During model testing or trialing using both the nine-class and 12-class models, robust detection/localization was consistently 100%, with mAP 0.99 from fivefold cross-validation. Safety-level categorization was high during both testing ( AUC ≥ 0.98 and ≥ 0.99 , respectively) and trialing (accuracy 98% and 97%, respectively). LLIED-type identifications by the two models during testing (1) were 98.9% and 99.5% overall correct and (2) consistently showed AUC ≥ 0.92 (1.00 for 8/9 and 9/12 LLIED-types, respectively). Pre-deployment trialing of both models demonstrated overall type-identification accuracies of 94.5% and 95%, respectively. Of the small number of misidentifications, none involved MRI-stringently conditional or MRI-unsafe types of LLIEDs. Optimized ZF GUI/viewer operations led to greater user-friendliness for radiologist engagement. Conclusions: Our LLIED-related AI methodology supports (1) 100% detection sensitivity, (2) high identification (including MRI-safety) accuracy, and (3) future model deployment with facilitated inference-result display and adjudication for ongoing model adaptation to future real-world experiences.

Including diverse and admixed populations in genetic epidemiology research.

The inclusion of ancestrally diverse participants in genetic studies can lead to new discoveries and is important to ensure equitable health care benefit from research advances. Here, members of the Ethical, Legal, Social, Implications (ELSI) committee of the International Genetic Epidemiology Society (IGES) offer perspectives on methods and analysis tools for the conduct of inclusive genetic epidemiology research, with a focus on admixed and ancestrally diverse populations in support of reproducible research practices. We emphasize the importance of distinguishing socially defined population categorizations from genetic ancestry in the design, analysis, reporting, and interpretation of genetic epidemiology research findings. Finally, we discuss the current state of genomic resources used in genetic association studies, functional interpretation, and clinical and public health translation of genomic findings with respect to diverse populations.

PSMA-targeting TGFß-insensitive armored CAR T cells in metastatic castration-resistant prostate cancer: a phase 1 trial.

Chimeric antigen receptor (CAR) T cells have demonstrated promising efficacy, particularly in hematologic malignancies. One challenge regarding CAR T cells in solid tumors is the immunosuppressive tumor microenvironment (TME), characterized by high levels of multiple inhibitory factors, including transforming growth factor (TGF)-ß. We report results from an in-human phase 1 trial of castration-resistant, prostate cancer-directed CAR T cells armored with a dominant-negative TGF-ß receptor (NCT03089203). Primary endpoints were safety and feasibility, while secondary objectives included assessment of CAR T cell distribution, bioactivity and disease response. All prespecified endpoints were met. Eighteen patients enrolled, and 13 subjects received therapy across four dose levels. Five of the 13 patients developed grade ≥2 cytokine release syndrome (CRS), including one patient who experienced a marked clonal CAR T cell expansion, >98% reduction in prostate-specific antigen (PSA) and death following grade 4 CRS with concurrent sepsis. Acute increases in inflammatory cytokines correlated with manageable high-grade CRS events. Three additional patients achieved a PSA reduction of ≥30%, with CAR T cell failure accompanied by upregulation of multiple TME-localized inhibitory molecules following adoptive cell transfer. CAR T cell kinetics revealed expansion in blood and tumor trafficking. Thus, clinical application of TGF-ß-resistant CAR T cells is feasible and generally safe. Future studies should use superior multipronged approaches against the TME to improve outcomes.

Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data.

OBJECTIVES: Early recognition of coronavirus disease 2019 (COVID-19) severity can guide patient management. However, it is challenging to predict when COVID-19 patients will progress to critical illness. This study aimed to develop an artificial intelligence system to predict future deterioration to critical illness in COVID-19 patients. METHODS: An artificial intelligence (AI) system in a time-to-event analysis framework was developed to integrate chest CT and clinical data for risk prediction of future deterioration to critical illness in patients with COVID-19. RESULTS: A multi-institutional international cohort of 1,051 patients with RT-PCR confirmed COVID-19 and chest CT was included in this study. Of them, 282 patients developed critical illness, which was defined as requiring ICU admission and/or mechanical ventilation and/or reaching death during their hospital stay. The AI system achieved a C-index of 0.80 for predicting individual COVID-19 patients' to critical illness. The AI system successfully stratified the patients into high-risk and low-risk groups with distinct progression risks (p < 0.0001). CONCLUSIONS: Using CT imaging and clinical data, the AI system successfully predicted time to critical illness for individual patients and identified patients with high risk. AI has the potential to accurately triage patients and facilitate personalized treatment. KEY POINT: • AI system can predict time to critical illness for patients with COVID-19 by using CT imaging and clinical data.

Adult Pleomorphic Rhabdomyosarcomas: Assessing Outcomes Associated with Radiotherapy and Chemotherapy Use in the National Cancer Database.

PURPOSE: Practice patterns for treatment of localized adult pleomorphic rhabdomyosarcoma (PRMS) remain quite variable given its rarity. Current national guidelines recommend management similar to that of other high-grade soft tissue sarcomas (STS), which include surgery with perioperative radiation (RT) with or without chemotherapy. Using the National Cancer Database (NCDB), we assessed practice patterns and overall outcomes of patients with localized PRMS. Patients and Methods. Patients with stage II/III PRMS treated with surgical resection from 2004 to 2015 were identified from the NCDB. Predictors of RT and chemotherapy use were assessed using multivariable logistic regression analysis. The association of radiation and chemotherapy status on overall survival was assessed using Kaplan-Meier and Cox proportional hazards analyses. RESULTS: Of 243 total patients, RT and chemotherapy were not uniformly utilized, with 44% receiving chemotherapy and in those who did not undergo amputation 62% receiving RT. In those who did not undergo amputation, RT was associated with improved survival on both univariate (HR: 0.49, 95% CI 0.32-0.73, P < 0.001) and multivariate analysis (HR: 0.40, 95% CI 0.26-0.62, P < 0.001), corresponding to greater 5-year overall survival (59% vs. 38%, P < 0.001). Chemotherapy was associated with a higher rate of 5-year overall survival (63% vs. 39%, P < 0.001). However, the survival benefit of chemotherapy did not reach statistical significance on multivariate analysis (HR: 0.65, 95% CI 0.41-1.03, P=0.064). Notable predictors of omission of RT included female gender (OR: 0.40, 95% CI 0.22-0.74, P < 0.01) and age ≥ 70 (OR: 0.55, 95% CI 0.30-1.00, P=0.05). Correspondingly, factors associated with omission of chemotherapy included age ≥70 (OR: 0.17, 95% CI 0.08-0.39, P < 0.001). CONCLUSIONS: A significant proportion of patients with localized adult PRMS are not receiving RT. Likewise, use of chemotherapy was heterogeneous. Our findings note potential benefits and underutilization of RT, for which further investigation is warranted.

Definitive Local Therapy Is Associated with Improved Survival in Metastatic Soft Tissue Sarcomas.

Background: Definitive local therapy is often utilized in patients with metastatic soft tissue sarcomas (STS) to reduce morbidity associated with local tumor progression. We hypothesize that it is associated with improved overall survival (OS). Methods: Patients with newly diagnosed metastatic STS treated with chemotherapy were identified from the National Cancer Database and dichotomized into cohorts: 1. definitive local therapy (defined as either definitive dose radiotherapy, definitive surgery, or surgery with perioperative radiotherapy) or 2. conservative therapy (defined as systemic therapy with or without palliative therapy). The association between definitive local therapy and OS, and factors associated with the receipt of definitive local therapy were assessed. Results: Total of 4180 patients were identified. Compared with the conservative therapy, receipt of any definitive local therapy was associated with improved OS (median 17.9 vs. 10.1 months). The survival benefit remained on multivariate analyses and propensity-score matched analyses, with a stepwise improvement with surgery and combined modality local therapy, specifically radiotherapy (HR: 0.77; p < 0.001), surgery (HR: 0.67; p < 0.001), and combined surgery and radiotherapy (HR: 0.42; p < 0.001). Conclusions: Analysis of a large national cancer registry of patients with metastatic STS suggests that chemotherapy plus definitive local therapy is associated with a significant survival benefit compared to the standard chemotherapy alone.

Radiotherapy Remains Underused in the Treatment of Soft-Tissue Sarcomas: Disparities in Practice Patterns in the United States.

BACKGROUND: Practice patterns of radiation therapy (RT) use for soft-tissue sarcoma (STS) remain quite variable, despite clinical practice guidelines recommending the addition of RT to surgery for patients with high-grade STS, particularly for larger tumors. Using the National Cancer Database (NCDB), we assessed patterns of overall RT use, neoadjuvant versus adjuvant treatment, and specific RT modalities in this population. PATIENTS AND METHODS: Patients aged ≥18 years with stage II/III STS in 2004 through 2015 were identified from the NCDB. Patterns of care were assessed using multivariable logistic regression analysis. RESULTS: Of 27,426 total patients, 11,654 (42%) were treated with surgery alone versus 15,772 (58%) with RT in addition to surgery, with no overall increase in RT use over the study period. Notable clinical predictors of receipt of RT included tumor size (>5 cm), grade III, and tumors arising in the extremities. Conversely, female sex, older age (≥70 years), Black race, noncommercial insurance coverage, farther distance to treatment, and poor performance status were negative predictors of RT use. Of those receiving RT, 27% were treated with neoadjuvant RT and 73% with adjuvant RT. The proportion of those receiving neoadjuvant RT increased over time. Relevant factors associated with neoadjuvant RT included treatment at academic centers, larger tumor size, and extremity tumors. Of those who received RT with a modality specified as either intensity-modulated RT (IMRT) or 3D conformal RT (3DCRT), 61% were treated with IMRT and 39% with 3DCRT. The proportion of patients treated with IMRT increased over time. Relevant factors associated with IMRT use included treatment at academic centers, commercial insurance coverage, and larger and nonextremity tumors. CONCLUSIONS: Although use of neoadjuvant RT and IMRT has increased over time, a significant number of patients with STS are not receiving adjuvant or neoadjuvant RT. Our findings also note potential sociodemographic disparities and highlight the concern that not all patients with STS are being equally considered for RT.

Impact of Tumor-Infiltrating Lymphocytes on Overall Survival in Merkel Cell Carcinoma.

BACKGROUND: Merkel cell carcinoma (MCC) is a rare and aggressive neuroendocrine carcinoma of the skin. As the clinical course can be variable, prognostic markers are needed to better stratify patients. Prior literature, composed of small series with limited sample size, has demonstrated that tumor-infiltrating lymphocytes (TILs) are an important prognostic marker in MCC. To validate these findings on a population level, we sought to analyze and report the prognostic value of TILs in a large national data set. MATERIALS AND METHODS: A retrospective observational cohort study was conducted of patients with nonmetastatic MCC from 2010 to 2015 using the National Cancer Database. Individual variables trending toward significance using a univariable analysis were included in a multivariable Cox proportional hazards model to assess their independent effect on overall survival (OS). TILs were subclassified into none, nonbrisk, and brisk and the survival analysis was performed. Propensity score-weighted multivariable analysis (PS MVA) was performed to adjust for additional confounding. RESULTS: A total of 2,182 patients met inclusion criteria: 611 (28.0%) were identified as having TILs present, and 1,571 (72.0%) had TILs absent in the tumor. On MVA, subdivision of TIL status into nonbrisk (hazard ratio [HR], 0.750; 95% confidence interval [CI], 0.602-0.933) and brisk (HR, 0.499; 95% CI, 0.338-0.735) was associated with incrementally improved OS compared with no TILs. The association of nonbrisk and brisk TILs with improved OS was retained on PS MVA (Nonbrisk: HR, 0.720; 95% CI, 0.550-0.944; Brisk: HR, 0.483; 95% CI, 0.286-0.814). CONCLUSION: The presence of nonbrisk and brisk TILs is associated with incrementally improved OS in patients with nonmetastatic MCC in a large national data set. This pathologic feature can aid with risk stratification, estimation of prognosis, and, importantly, decision-making with respect to treatment intensification in high-risk patients. IMPLICATIONS FOR PRACTICE: Merkel cell carcinoma (MCC) is an aggressive neuroendocrine cutaneous malignancy with variable clinical course. Prognostic markers are needed to better risk stratify patients. We present the largest retrospective observational cohort study of patients with nonmetastatic MCC using the National Cancer Database. Our analysis demonstrates an association between increasing degrees of tumor-infiltrating lymphocytes and incrementally improved survival. These conclusions improve pathologic risk stratification, and decision-making with respect to treatment intensification. Intensification may include adjuvant radiation therapy to the primary site after wide excision despite small tumor size, to the nodal basin in sentinel lymph node-negative patients, or offering closer follow-up.

Deep learning-based classification of primary bone tumors on radiographs: A preliminary study.

BACKGROUND: To develop a deep learning model to classify primary bone tumors from preoperative radiographs and compare performance with radiologists. METHODS: A total of 1356 patients (2899 images) with histologically confirmed primary bone tumors and pre-operative radiographs were identified from five institutions' pathology databases. Manual cropping was performed by radiologists to label the lesions. Binary discriminatory capacity (benign versus not-benign and malignant versus not-malignant) and three-way classification (benign versus intermediate versus malignant) performance of our model were evaluated. The generalizability of our model was investigated on data from external test set. Final model performance was compared with interpretation from five radiologists of varying level of experience using the Permutations tests. FINDINGS: For benign vs. not benign, model achieved area under curve (AUC) of 0•894 and 0•877 on cross-validation and external testing, respectively. For malignant vs. not malignant, model achieved AUC of 0•907 and 0•916 on cross-validation and external testing, respectively. For three-way classification, model achieved 72•1% accuracy vs. 74•6% and 72•1% for the two subspecialists on cross-validation (p = 0•03 and p = 0•52, respectively). On external testing, model achieved 73•4% accuracy vs. 69•3%, 73•4%, 73•1%, 67•9%, and 63•4% for the two subspecialists and three junior radiologists (p = 0•14, p = 0•89, p = 0•93, p = 0•02, p < 0•01 for radiologists 1-5, respectively). INTERPRETATION: Deep learning can classify primary bone tumors using conventional radiographs in a multi-institutional dataset with similar accuracy compared to subspecialists, and better performance than junior radiologists. FUNDING: The project described was supported by RSNA Research & Education Foundation, through grant number RSCH2004 to Harrison X. Bai.

Association of health insurance status with presentation, treatment and outcomes in soft tissue sarcoma.

BACKGROUND: Numerous studies across a variety of malignancies have demonstrated that health insurance status is associated with differences in clinical presentation, type of treatments received, and survival. The effect of insurance status on the management of soft tissue sarcoma is unknown. We assessed the association of insurance on (a) stage at diagnosis, (b) receipt of neoadjuvant/adjuvant radiation therapy, and (c) overall survival (OS) in patients with soft tissue sarcoma. METHODS: The study cohort was identified from the National Cancer Database (NCDB) and consisted of patients with stage I-IV soft tissue sarcoma of various histologies diagnosed from 2004 to 2015. The patients were stratified by age (<65 and ≥65 years) and by insurance status (commercial, Medicare, Medicaid and uninsured). Using multivariable logistic regression analysis, we evaluated the association between insurance status and (a) stage at diagnosis (Stage I-III vs IV), and (b) receipt of neoadjuvant/adjuvant radiation therapy in patients with locally advanced disease. The association of insurance status on OS was assessed using Kaplan-Meier and multivariable Cox proportional hazards analyses. A propensity score matched survival analysis was performed to account for measured confounders. RESULTS: 49 754 patients were identified of whom 23 677 (48%) had commercial insurance, 20 867 (42%) had Medicare, 3229 (6%) had Medicaid, and 1981 (4%) were uninsured. In patients <65 years, those with Medicaid (OR = 1.74, 95% CI: 1.57-1.93, P < .001) and the uninsured (OR = 1.71, 95% CI: 1.51-1.94, P < .001) were more likely to present with stage IV vs Stage I-III disease. Furthermore, among patients with locally advanced disease treated with limb sparing surgery, those with Medicaid (OR = 0.87, 95% CI: 0.77- 0.98, P = .021) and the uninsured (OR = 0.73, 95% CI: 0.63-0.85, P < .001) were less likely to receive neoadjuvant or adjuvant radiotherapy as compared to those with commercial insurance. Lastly, having Medicaid (HR = 1.26, 95% CI: 1.17-1.34, P < .001) and no insurance (HR = 1.30, 95% CI: 1.20-1.41, P < .001) was associated with worse OS compared to having commercial insurance, a finding which remained significant after propensity score matching. In contrast, in patients ≥65 years, there were no statistically significant differences between those with Medicare and commercial insurance with regards to disease presentation, receipt of radiotherapy, or survival. CONCLUSIONS: In a large modern cohort identified from the NCDB, commercial insurance status in patients <65 years was associated early diagnosis, receipt of neoadjuvant/adjuvant radiation therapy, and overall survival for patients with soft tissue sarcoma. Further efforts are warranted to understand disparities in care based on health insurance in the United States.