Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 2 appraisals
Physics in medicine and biology
Deep learning based time series analysis for breathing phase prediction in phase-gated proton therapy
Objective. Phase gating is a critical technique to mitigate tumor motion during radiotherapy, particularly in spot-scanned particle therapy where internal motion can interfere with dynamic spot scanning patterns and, simultaneously, introducing substantial range uncertainties. However, the current commercial state of the art in real-time phase prediction is challenged by patient-specific breathing variability as well as detection and delivery system latencies. This leads to suboptimal efficiency, mis-timed radiation delivery and requires frequent manual intervention. This study aims to improve phase prediction accuracy using deep learning (DL)-based time series forecasting to enable more accurate dose delivery.Approach. Retrospective breathing waveforms from 69 proton therapy patients, sampled at 30 Hz, were labeled with inspiratory peaks and assigned subjective regularity scores (four levels). DL models with various architectures were trained using waveform amplitude to predict current or future breathing phases. Model performance was evaluated using mean squared error, phase binning accuracy, and timing deviation for radiation on/off events. Bayesian optimization was used for hyperparameter tuning. Results were compared between models and against a commercial algorithm currently in clinical use.Main Results. The curated waveform dataset included 165 242 s for training, 24 057 s for validation, and 30 322 s for testing, with an additional 40 604 s from separate patients for extended validation. The long short-term memory and temporal fusion transformer models significantly outperformed the commercial algorithm, improving phase prediction accuracy by nearly 20% and reducing timing deviations across all regularity levels.Significance. DL-based time series forecasting may substantially improve breathing phase prediction accuracy over current clinically available methods, offering a more precise and reliable approach to phase-gated radiation delivery.
2 July 2026
Read appraisal →Cancer chemotherapy and pharmacology
A randomized, open-label, two-way crossover clinical trial to evaluate the food effect on pharmacokinetics and safety of DHP107 in patients with advanced solid tumors: the FEEL study
PURPOSE: The phase 1, randomized, open-label, two-way crossover FEEL study assessed the effect of food on the pharmacokinetics of DHP107, an oral paclitaxel with a novel lipid formulation designed to be systemically absorbed without Cremophor EL, in patients with advanced solid tumors. METHODS: Patients were randomized 1:1 to DHP107 (200 mg/m2 orally twice daily on Days 1, 8, 15 every 28 days for two cycles) treatment sequences: fasted-fed (first DHP107 dose administered after overnight fast; n = 13) and fed-fasted (first DHP107 dose administered after a high-fat meal; n = 12). The primary objective was to evaluate the effect of food on DHP107 pharmacokinetics. The secondary objective was DHP107 safety; efficacy was also assessed (both in all patients regardless of dosing sequence). RESULTS: Mean systemic exposures were similar for paclitaxel and its metabolites under fed and fasted conditions. Geometric mean ratios (fed:fasted) for paclitaxel were: maximum concentration (Cmax), 101.00% (95% CI 91.93-110.95%); area under the curve (AUC0-72), 102.92% (95% CI 95.04-111.45%); and AUC0-inf 104.76% (95% CI 96.44-113.80%), meeting criteria for no food effect. Common adverse events across the study period included diarrhea (fasted-fed 61.5%; fed-fasted 41.7%), vomiting (fasted-fed 30.8%; fed-fasted 8.3%), and neutropenia (fasted-fed 23.1%; fed-fasted 16.7%). Two fed-fasted patients (16.7%) had partial responses and six had stable disease (50.0%); seven fasted-fed patients had stable disease (53.8%). CONCLUSION: This study suggests that the pharmacokinetics of DHP107 are unaffected by food and DHP107 can be taken with or without food. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov ID: NCT04675528; 107CS-7.
31 May 2026
Read appraisal →