Machine Learning to Predict the Need for Postmastectomy Radiotherapy after Immediate Breast Reconstruction.

Background: Post mastectomy radiotherapy (PMRT) is an independent predictor of reconstructive complications. PMRT may alter the timing and type of reconstruction recommended. This study aimed to create a machine learning model to predict the probability of requiring PMRT after immediate breast reconstruction (IBR). Methods: In this retrospective study, breast cancer patients who underwent IBR from January 2017 to December 2020 were reviewed and data were collected on 81 preoperative characteristics. Primary outcome was recommendation for PMRT. Four algorithms were compared to maximize performance and clinical utility: logistic regression, elastic net (EN), logistic lasso, and random forest (RF). The cohort was split into a development dataset (75% of cohort for training-validation) and 25% used for the test set. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), precision-recall curves, and calibration plots. Results: In a total of 800 patients, 325 (40.6%) patients were recommended to undergo PMRT. With the training-validation dataset (n = 600), model performance was logistic regression 0.73 AUC [95% confidence interval (CI) 0.65-0.80]; RF 0.77 AUC (95% CI, 0.74-0.81); EN 0.77 AUC (95% CI, 0.73-0.81); logistic lasso 0.76 AUC (95% CI, 0.72-0.80). Without significantly sacrificing performance, 81 predictive factors were reduced to 12 for prediction with the EN method. With the test dataset (n = 200), performance of the EN prediction model was confirmed [0.794 AUC (95% CI, 0.730-0.858)]. Conclusion: A parsimonious accurate machine learning model for predicting PMRT after IBR was developed, tested, and translated into a clinically applicable online calculator for providers and patients.

Toward a Skin Dose-Area Metric Predictive of Moist Desquamation Using In Vivo Skin Dosimetry and Skin Assessments.

Purpose: Moist desquamation (MD) is a concerning acute side effect of radiation therapy for breast cancer, often seen in skin folds for patients having large or pendulous breasts. In vivo skin dosimetry, clinical assessments, and patient-reported skin reactions were used to determine a relationship between dose-area metrics and the development of MD, to lend insight into skin tolerances and possibly guide future treatment planning dose constraints. Methods and Materials: Skin dose was measured using GafChromic film on the inner surface of an early prototype carbon-fiber accessory for breast support to remove the inframammary fold in 20 patients at high risk of developing MD undergoing adjuvant whole breast radiation therapy. Prescribed doses were 42.5 Gray (Gy) in 16 fractions or 50 Gy in 25 fractions using 6 to 15 MV x-rays. To account for fraction size differences, analysis was performed using the equivalent dose in 2 Gy fractions using α/ß = 11 (EQD211). MD was assessed out to 2 weeks post radiation therapy by trained therapists and by a patient-reported outcome questionnaire. Results: Statistically significant differences in areas receiving 30 to 48 Gy (EQD211) were observed between patients who did and did not develop MD in the inframammary area. Patients receiving EQD211 maximum dose ≤ 46 Gy and ≥ 38 Gy to ≤ 50 cm2 of their breast skin did not develop MD. Conclusions: The findings of this study offer insight into the relationship between skin toxicity and areas of skin irradiated to doses up to 50 Gy. Potential skin dose constraints to test in future studies to prevent MD are suggested.

Protocol for a systematic review with prospective individual patient data meta-analysis in EGFR-mutant NSCLC with brain metastases to assess the effect of SRS+osimertinib compared to osimertinib alone: the STARLET Collaboration.

BACKGROUND: Patients with advanced non-small-cell lung cancer (NSCLC) with activating mutations in the epidermal growth factor receptor (EGFR) gene are a heterogeneous population who often develop brain metastases (BM). The optimal management of patients with asymptomatic brain metastases is unclear given the activity of newer-generation targeted therapies in the central nervous system. We present a protocol for an individual patient data (IPD) prospective meta-analysis to evaluate whether the addition of stereotactic radiosurgery (SRS) before osimertinib treatment will lead to better control of intracranial metastatic disease. This is a clinically relevant question that will inform practice. METHODS: Randomised controlled trials will be eligible if they include participants with BM arising from EGFR-mutant NSCLC and suitable to receive osimertinib both in the first-line and second-line settings (P); comparisons of SRS followed by osimertinib versus osimertinib alone (I, C) and intracranial disease control included as an endpoint (O). Systematic searches of Medline (Ovid), Embase (Ovid), Cochrane Central Register of Controlled Trials (CENTRAL), CINAHL (EBSCO), PsychInfo, ClinicalTrials.gov and the WHO's International Clinical Trials Registry Platform's Search Portal will be undertaken. An IPD meta-analysis will be performed using methodologies recommended by the Cochrane Collaboration. The primary outcome is intracranial progression-free survival, as determined by response assessment in neuro-oncology-BM criteria. Secondary outcomes include overall survival, time to whole brain radiotherapy, quality of life, and adverse events of special interest. Effect differences will be explored among prespecified subgroups. ETHICS AND DISSEMINATION: Approved by each trial's ethics committee. Results will be relevant to clinicians, researchers, policymakers and patients, and will be disseminated via publications, presentations and media releases. PROSPERO REGISTRATION: CRD42022330532.