PURPOSE: This study assesses the accuracy of radiographic clinical staging by computed tomography (CT) of mismatch repair-deficient (dMMR) colon cancer, given emerging data for neoadjuvant immune checkpoint inhibitors (ICIs). METHODS: Patients with stage I-III colon cancer treated with upfront surgical resection were retrospectively reviewed using the electronic medical record from a single institution from 2012 to 2023. We performed a cohort study of dMMR tumors with a stage-matched control cohort of mismatch repair-proficient (pMMR) tumors. The primary end point was the accuracy of clinical stage using preoperative CT compared with pathologic stage for dMMR colon cancer. Statistical analysis was performed using R. RESULTS: We identified 78 patients with dMMR colon cancer. For dMMR tumors, T-stage clinical radiologic staging matched pathologic stage in 51% of cases and the nodal stage was accurately matched in 55% of cases. For stage I and IIA (low-risk) tumors, the overstaging rate on CT was 41% and for T4 or N+ (high-risk), the understaging rate was 25%. When comparing the dMMR and pMMR cohorts, pMMR nodal status was more likely to be understaged ( P < .001). There was moderate to substantial interrater reliability for overall stage, T stage, and N staging between radiologists (kappa = 0.64, 0.60, and 0.63, respectively). CONCLUSION: Radiographic tumor and nodal staging for dMMR colon tumors is unreliable with high rates of overstaging low-risk tumors where neoadjuvant treatment may not be indicated. The low accuracy of clinical staging demonstrates clear limitations to make systemic therapy decisions. Additional diagnostic modalities for lymph node status may be necessary to accurately clinically stage patients before neoadjuvant ICIs in patients with locally advanced disease.
Introduction: Low anterior resection syndrome (LARS) can be a debilitating condition that develops after undergoing sphincter-preserving surgery for rectal cancer. Chemotherapy-induced peripheral neuropathy is a common side effect of platinum-based chemotherapy agents used as systemic therapy for rectal cancer treatment. The purpose of this study was to determine the potential relationship between CIPN and LARS. Methods: This was a retrospective review of patients who underwent a low anterior resection for rectal cancer and received systemic therapy contacted at least six months from the most recent surgery. Eligible patients were called and completed the relevant surveys over the phone or email. Results: There was a total of 42 patients who completed the surveys with 33 (79%) having major LARS. Presence of a diverting ileostomy was the only significantly differentcharacteristic in those with major LARS versus those without. CIPN was independently associated with LARS (p = 0.046) on linear regression when controlling for neoadjuvant chemoradiation, diverting ileostomy and tumor distance from the anal verge. Conclusions: Developing severe CIPN is associated with developing LARS. Further studies evaluating the etiology behind this relationship should be conducted.
PURPOSE: Cancer clinical trial enrollment remains critically low at 5%-7% of adult patients despite exponential growth in available trials. Manual patient-trial matching represents a fundamental bottleneck, whereas current artificial intelligence (AI) and machine learning patient-trial matching systems lack data standardization and compatibility across health systems. We developed and validated a semiautomated clinical trial patient matching (CTPM) tool to improve recruitment efficiency and scalability. METHODS: We created a hybrid rules–based and natural language processing (NLP)–based pipeline that automatically screens patients using structured and unstructured electronic health record data standardized to the Observational Medical Outcomes Partnership (OMOP) common data model. CTPM performance was first evaluated on one metastatic colorectal cancer (CRC) trial by comparing CTPM accuracy and efficiency to manual chart review. Following the single-trial validation, we then implemented the system across 29 clinical trials spanning multiple cancer specialties and phases. RESULTS: For the single CRC trial, CTPM achieved 94% retrospective and 88% prospective accuracy, matching gold standard clinical chart review with 100% sensitivity. Implementation reduced chart review workload 10-fold and screening time by 41% (3.1 to 1.8 minutes per chart) for those patients who did undergo review. Since September 2022, the system has screened 98,348 patients across 29 trials, identifying 825 eligible candidates and facilitating 117 patient enrollments with 9%-37% consent rates. CONCLUSION: This AI and NLP tool demonstrates improved efficiency in clinical trial recruitment by enabling research teams to focus on qualified candidates rather than exhaustive chart reviews. The OMOP-based framework supports scalability across health systems, with potential to address enrollment challenges that limit patient access to clinical trials.
Schwannomas of the gastrointestinal tract are rare spindle cell tumors that account for 2–6% of mesenchymal tumors. An elderly male was found to have a left colon mass on CT scan and colonoscopy with pathology of fibrotic tissue. A laparoscopic-assisted left hemi-colectomy with primary anastomosis was performed. Pathology demonstrated spindle cell neoplasm arranged in short fascicles that were strongly and diffusely positive for S100. An elderly female was found to have a submucosal lesion on surveillance colonoscopy in the proximal transverse colon. Biopsy with jumbo forceps revealed spindle cell neoplasm positive for S100. Patient underwent an uncomplicated limited non-oncologic segmental transverse colectomy. We report only the ninth case of left and sixth in the transverse colon described in the literature. As is true for other mesenchymal tumors, mucosal biopsy is usually inconclusive and deep biopsy or submucosal resection is required, making pre-operative surgical decision difficult.