Objectives: Characterization of thrombus is important for guiding treatment in chronic thromboembolic pulmonary hypertension (CTEPH). This study presents a novel scoring system for visual assessment of CTEPH on CT pulmonary angiography (CTPA), incorporating both disease location and extent to determine the impact on survival outcomes. Methods: Patients with CTEPH were identified retrospectively from the Assessing the Spectrum of Pulmonary Hypertension Identified at a Referral Centre registry. The scoring system emphasizes disease based on their predominant location as central, segmental, and distal disease. Survival analysis was conducted using Cox-regression and Kaplan–Meier survival curves. Results: A total of 208 patients with CTEPH were included (mean age 66 ± 13.6 years, 52.4% female). Mosaic perfusion and infarction were commonly seen in patients with distal disease (92% and 88%). Patients with central and distal disease had more severe pulmonary hemodynamics and lower gas transfer (TLCO) than patients with segmental disease. Central and distal disease showed similar survival, whereas survival was worse in central compared to segmental disease for all patients (P < .001), including those undergoing (P < .04) and not undergoing endarterectomy (P < .001). Central disease was an independent predictor of mortality in those not undergoing endarterectomy (hazard ratio 1.9, P < .01). Conclusions: Our scoring system showed excellent interobserver agreement. Thromboembolic disease location was shown to be a predictor of mortality, with central disease independently associated with shorter survival in patients not undergoing pulmonary endarterectomy. Advances in knowledge: This is a novel scoring system for characterizing CTEPH on CTPA, considering disease location and extent. It provides disease location as a predictor of survival, introducing a new framework for patient stratification and clinical decision-making.
Background: Artificial intelligence (AI) may support clinical decision-making but introduce automation bias when incorrect recommendations influence users. This study aimed to determine the occurrence of harmful automation bias among undergraduate radiological sciences students during AI-assisted radiotherapy decision-making and to examine the influence of time pressure. Methods: In a controlled experiment, 54 final-year undergraduate radiological sciences students with no prior clinical radiotherapy placement experience completed 20 simulated radiotherapy decision-making scenarios with 13 correct and seven deliberately incorrect AI recommendations (1080 trials). Initial and final responses, AI advice acceptance, confidence, perceived workload, and attitudes toward AI verification were assessed. Students were assigned to time-pressure (n = 26) or no-time-pressure (n = 28) conditions. Harmful automation bias was operationally defined as switching from an initially correct response to an incorrect response matching AI advice. Results: Harmful automation bias occurred in 20/220 eligible trials (9.1%), affecting 15/54 students (27.8%). Incorrect AI advice was followed in 137/378 trials (36.2%). Overall accuracy remained similar before and after AI exposure (75.65% vs. 74.91%; p = 0.289). Time pressure increased workload, but no statistically significant association with harmful automation bias was observed (OR = 0.78; p = 0.654). Lower post-decision confidence was associated with harmful automation bias (OR = 0.599; p = 0.028). No statistically significant difference in harmful automation bias was observed between participants who supported AI verification and those who did not. Conclusions: Harmful automation bias can occur despite stable overall accuracy, suggesting that greater emphasis on critical appraisal, active verification, and independent judgement may be valuable in radiotherapy education.
Background/Objectives: Radiotherapy is an important component of rectal cancer treatment, but treatment-related toxicity varies considerably between patients, suggesting that patient-related factors may influence susceptibility. Pretreatment hemoglobin, leukocyte count, and body mass index (BMI) are routinely available measures, yet their associations with acute and late toxicity during and after radiotherapy remain unclear. This study evaluated these associations in patients with rectal cancer. Methods: A retrospective analysis included 67 patients with histologically confirmed rectal cancer who underwent radiotherapy. Acute toxicity occurred during radiotherapy or within 3 months after treatment completion, and late toxicity occurred thereafter. Toxicity was graded using the Common Terminology Criteria for Adverse Events (CTCAE) and dichotomized as Grades 0–1 or Grade ≥ 2. Pretreatment hemoglobin, total leukocyte count, and BMI were analyzed as continuous variables. Logistic regression examined associations with acute and late toxicity, with sequential adjustment for age, sex, and radiotherapy course. Results: Grade ≥ 2 acute toxicity occurred in 17 patients (25.4%), and Grade ≥ 2 late toxicity in 27 (40.3%). Higher pretreatment leukocyte count was associated with greater odds of acute toxicity in the fully adjusted model (OR 1.70, 95% CI 1.13–2.58; p = 0.012). Higher pretreatment hemoglobin was associated with lower odds of late toxicity in the fully adjusted model (OR 0.57, 95% CI 0.40–0.81; p = 0.002). No clear association was observed between BMI and either acute or late toxicity. Conclusions: Pretreatment leukocyte count was associated with acute toxicity, while pretreatment hemoglobin was associated with late toxicity. These inexpensive, routinely available measures may represent candidate markers of toxicity, although their clinical utility requires validation in larger, independent studies.