David D. B. Bates

Background: Hospitals struggle to predict critical outcomes. Traditional early warning systems, like NEWS and MEWS, rely on static variables and fixed thresholds, limiting their adaptability, accuracy, and personalization. Methods: We previously developed the Enhanced Transformer for Health Outcome Simulation (ETHOS), an artificial intelligence (AI) model that tokenizes patient health timelines (PHTs) from electronic health records and uses transformer-based architectures to predict future PHTs. ETHOS is a versatile framework for developing a wide range of applications. In this work, we develop the Adaptive Risk Estimation System (ARES) that leverages ETHOS to compute dynamic, personalized risk probabilities for clinician-defined critical events. ARES also features a personalized explainability module that highlights key clinical factors influencing risk estimates. We evaluated ARES using the MIMIC-IV v2.2 dataset, together with its emergency department extension, and benchmarked performance against both classical early warning systems and contemporary machine learning models. Results: The entire dataset was tokenized, resulting in 285,622 PHTs (63% with at least 1 hospital admission), comprising over 357 million tokens. ETHOS outperformed benchmark models in predicting hospital admissions, intensive care unit admissions, and prolonged stays, achieving superior area under the curve scores. Its risk estimates were robust across demographic subgroups, with calibration curves confirming model reliability. The explainability module provided valuable insights into patient-specific risk factors Conclusions: ARES, powered by ETHOS, advances predictive health care AI by delivering dynamic, real-time, personalized risk estimation with patient-specific explainability. Although our results are promising, the clinical impact remains uncertain. Demonstrating ARES’s true utility in real-world settings will be the focus of our future work.

Radiologic imaging, especially MRI, has long been the mainstay for rectal cancer staging and patient selection for neoadjuvant therapy prior to surgical resection. In contrast, colonoscopy and CT have been the standard for colon cancer diagnosis and metastasis staging with T and N staging often performed at the time of surgical resection. With recent clinical trials exploring the expansion of the use of neoadjuvant therapy beyond the anorectum to the remainder of the colon, the current and future state of colon cancer treatment is evolving with a renewed interest in evaluating the role radiology may play in the primary T staging of colon cancer. The performance of CT, CT colonography, MRI, and FDG PET-CT for colon cancer staging will be reviewed. N staging will also be briefly discussed. It is expected that accurate radiologic T staging will significantly impact future clinical decisions regarding the neoadjuvant versus surgical management of colon cancer.

The role and method of image-based staging of anal cancer has evolved with the rapid development of newer imaging modalities and the need to address the rising incidence of this rare cancer. In 2014, the European Society of Medical Oncology mandated pelvic magnetic resonance imaging (MRI) for anal cancer and subsequently other societies such as the National Comprehensive Cancer Network followed suit with similar recommendations. Nevertheless, great variability exists from center to center and even within individual centers. Notably, this is in stark contrast to the imaging of the anatomically nearby rectal cancer. As participating team members for this malignancy, we embarked on a comprehensive literature review of anal cancer imaging to understand the relative merits of these new technologies which developed after computed tomography (CT), e.g., MRI and positron emission tomography/computed tomography (PET/CT). The results of this literature review helped to inform our next stage: questionnaire development regarding the imaging of anal cancer. Next, we distributed the questionnaire to members of the Society of Abdominal Radiology (SAR) Rectal and Anal Disease-Focused Panel, a group of abdominal radiologists with special interest, experience, and expertise in rectal and anal cancer, to provide expert radiologist opinion on the appropriate anal cancer imaging strategy. In our expert opinion survey, experts advocated the use of MRI in general (65% overall and 91–100% for primary staging clinical scenarios) and acknowledged the superiority of PET/CT for nodal assessment (52–56% agreement for using PET/CT in primary staging clinical scenarios compared to 30% for using MRI). We therefore support the use of MRI and PET and suggest further exploration of PET/MRI as an optimal combined evaluation. Our questionnaire responses emphasized the heterogeneity in imaging practice as performed at numerous academic cancer centers across the United States and underscore the need for further reconciliation and establishment of best imaging practice guidelines for optimized patient care in anal cancer.

PURPOSE: Natural language processing (NLP) applied to radiology reports can help identify clinically relevant M1 subcategories of patients with colorectal cancer (CRC). The primary purpose was to compare the overall survival (OS) of CRC according to American Joint Committee on Cancer TNM staging and explore an alternative classification. The secondary objective was to estimate the frequency of metastasis for each organ. METHODS: Retrospective study of CRC who underwent computed tomography (CT) chest, abdomen, and pelvis between July 1, 2009, and March 26, 2019, at a tertiary cancer center, previously labeled for the presence or absence of metastasis by an NLP prediction model. Patients were classified in M0, M1a, M1b, and M1c (American Joint Committee on Cancer), or an alternative classification on the basis of the metastasis organ number: M1, single; M2, two; M3, three or more organs. Cox regression models were used to estimate hazard ratios; Kaplan-Meier curves were used to visualize survival curves using the two M1 subclassifications. RESULTS: Nine thousand nine hundred twenty-eight patients with a total of 48,408 CT chest, abdomen, and pelvis reports were included. On the basis of NLP prediction, the median OS of M1a, M1b, and M1c was 4.47, 1.72, and 1.52 years, respectively. The median OS of M1, M2, and M3 was 4.24, 2.05, and 1.04 years, respectively. Metastases occurred most often in liver (35.8%), abdominopelvic lymph nodes (32.9%), lungs (29.3%), peritoneum (22.0%), thoracic nodes (19.9%), bones (9.2%), and pelvic organs (7.5%). Spleen and adrenal metastases occurred in < 5%. CONCLUSION: NLP applied to a large radiology report database can identify clinically relevant metastatic phenotypes and be used to investigate new M1 substaging for CRC. Patients with three or more metastatic disease organs have the worst prognosis, with an OS of 1 year.

Objective To review existing structured MRI reports for primary staging of rectal cancer and create a new, freely available structured report based on multidisciplinary expert opinion and literature review. Methods Twenty abdominal imaging experts from the Society of Abdominal Radiology (SAR)’s Disease Focused Panel (DFP) on Rectal and Anal Cancer completed a questionnaire and participated in a subsequent consensus meeting based on the RAND-UCLA Appropriateness Method. Twenty-two items were classified via a group survey as “appropriate” or “inappropriate” (defined by ≥ 70% consensus), or “needs group discussion” (defined by < 70% consensus). Certain items were also discussed with multidisciplinary team members from colorectal surgery, oncology and pathology. Results After completion of the questionnaire, 16 (72%) items required further discussion (< 70% consensus). Following group discussion, consensus was achieved for 21 (95%) of the items. Based on the consensus meeting, a revised structured report was developed. The most significant modifications included (1) Exclusion of the T2/early T3 category; (2) Replacement of the term “circumferential resection margin (CRM)” with “mesorectal fascia (MRF)”; (3) A revised definition of “mucinous content”; (4) Creation of two distinct categories for suspicious lymph nodes (LNs) and tumor deposits; and (5) Classification of suspicious extra-mesorectal LNs by anatomic location. Conclusion The SAR DFP on Rectal and Anal Cancer recommends using this newly updated reporting template for primary MRI staging of rectal cancer. Graphical abstract

Purpose To evaluate computed tomography (CT) findings in patients with ovarian cancer presenting to a comprehensive cancer center’s urgent care unit with acute abdominal symptoms. Methods This retrospective study included consecutive patients with ovarian cancer who underwent abdominal CT at a comprehensive cancer center’s urgent care unit between January 1, 2018, and January 14, 2020, due to acute abdominal symptoms. Two abdominal radiologists reviewed the abdominal CT reports, categorizing imaging findings as follows: (a) no new or acute finding, (b) new or increased bowel or gastric obstruction, (c) new or increased ascites, (d) new or increased peritoneal carcinomatosis, (e) new or increased nonperitoneal metastases, (f) new inflammatory or infectious changes, (g) new or increased hydronephrosis, (h) new or increased biliary dilatation, (i) new vascular complications, or (j) new bowel perforation. Results A total of 200 patients (mean age, 59 years; range, 22–87) underwent a total of 259 abdominal CT scans, of which 217/259 (83.8%) scans were found to have new or increased findings. A total of 115/259 (44.4%) scans had only one finding while 102/259 (39.4%) scans had 2 or more findings. Altogether, 382 new or increased findings were detected: findings were most commonly related to bowel or gastric obstruction (92/382, 24.1%) with small bowel obstruction being the most common finding (80/382, 20.9%); ascites (78/382, 20.4%); peritoneal carcinomatosis (62/382, 16.2%); and nonperitoneal metastases (62/382, 16.2%). Inflammatory or infectious findings accounted for 30/382 (7.9%) findings. Conclusion Most patients with ovarian cancer presenting with acute abdominal had relevant positive findings on abdominal CT, with small bowel obstruction being the most common finding.

Accurate evaluation of tumor response to treatment is critical to allow personalized treatment regimens according to the predicted response and to support clinical trials investigating new therapeutic agents by providing them with an accurate response indicator. Recent advances in medical imaging, computer hardware, and machine-learning algorithms have resulted in the increased use of these tools in the field of medicine as a whole and specifically in cancer imaging for detection and characterization of malignant lesions, prognosis, and assessment of treatment response. Among the currently available imaging techniques, magnetic resonance imaging (MRI) plays an important role in the evaluation of treatment assessment of many cancers, given its superior soft-tissue contrast and its ability to allow multiplanar imaging and functional evaluation. In recent years, deep learning (DL) has become an active area of research, paving the way for computer-assisted clinical and radiological decision support. DL can uncover associations between imaging features that cannot be visually identified by the naked eye and pertinent clinical outcomes. The aim of this review is to highlight the use of DL in the evaluation of tumor response assessed on MRI. In this review, we will first provide an overview of common DL architectures used in medical imaging research in general. Then, we will review the studies to date that have applied DL to magnetic resonance imaging for the task of treatment response assessment. Finally, we will discuss the challenges and opportunities of using DL within the clinical workflow.