Predicting Reduction Mammaplasty Total Resection Weight With Machine Learning.

BACKGROUND: Machine learning (ML) is a form of artificial intelligence that has been used to create better predictive models in medicine. Using ML algorithms, we sought to create a predictive model for breast resection weight based on anthropometric measurements. METHODS: We analyzed 237 patients (474 individual breasts) who underwent reduction mammoplasty at our institution. Anthropometric variables included body surface area (BSA), body mass index, sternal notch-to-nipple (SN-N), and nipple-to-inframammary fold values. Four different ML algorithms (linear regression, ridge regression, support vector regression, and random forest regression) either including or excluding the Schnur Scale prediction for the same data were trained and tested on their ability to recognize the relationship between the anthropometric variables and total resection weights. Resection weight prediction accuracy for each model and the Schnur scale alone were evaluated based on using mean absolute error (MAE). RESULTS: In our cohort, mean age was 40.36 years. Most patients (71.61%) were African American. Mean BSA was 2.0 m 2 , mean body mass index was 33.045 kg/m 2 , mean SN-N was 35.0 cm, and mean nipple-to-inframammary fold was 16.0 cm. Mean SN-N was found to have the greatest variable importance. All 4 models made resection weight predictions with MAE lower than that of the Schnur Scale alone in both the training and testing datasets. Overall, the random forest regression model without Schnur scale weight had the lowest MAE at 186.20. CONCLUSION: Our ML resection weight prediction model represents an accurate and promising alternative to the Schnur Scale in the setting of reduction mammaplasty consultations.

Cell-free DNA alterations in the AR enhancer and locus predict resistance to AR-directed therapy in patients with metastatic prostate cancer.

PURPOSE: Cell-free DNA (cfDNA) and circulating tumor cell (CTC) based liquid biopsies have emerged as potential tools to predict responses to androgen receptor (AR)-directed therapy in metastatic prostate cancer. However, due to complex mechanisms and incomplete understanding of genomic events involved in metastatic prostate cancer resistance, current assays (e.g. CTC AR-V7) demonstrate low sensitivity and remain underutilized. The recent discovery of AR enhancer amplification in >80% of metastatic patients and its association with disease resistance presents an opportunity to improve upon current assays. We hypothesized that tracking AR/enhancer genomic alterations in plasma cfDNA would detect resistance with high sensitivity and specificity. METHODS: We developed a targeted sequencing and analysis method as part of a new assay called Enhancer and neighboring loci of Androgen Receptor Sequencing (EnhanceAR-Seq). We applied EnhanceAR-Seq to plasma collected from 40 patients with metastatic prostate cancer treated with AR-directed therapy to monitor AR/enhancer genomic alterations and correlate these events with therapy resistance, progression-free survival (PFS) and overall survival (OS). RESULTS: EnhanceAR-Seq identified genomic alterations in the AR/enhancer locus in 45% of cases, including a 40% rate of AR enhancer amplification. Patients with AR/enhancer alterations had significantly worse PFS and OS than those without (6-month PFS: 30% vs. 71%, P=0.0002; 6-month OS: 59% vs. 100%, P=0.0015). AR/enhancer alterations in plasma cfDNA detected 18 of 23 resistant cases (78%) and outperformed the CTC AR-V7 assay which was also run on a subset of patients. CONCLUSION: cfDNA-based AR locus alterations, including of the enhancer, are strongly associated with resistance to AR-directed therapy and significantly worse survival. cfDNA analysis using EnhanceAR-Seq may enable more precise risk stratification and personalized therapeutic approaches for metastatic prostate cancer.