Genomic features of rapid versus late relapse in triple negative breast cancer.

BACKGROUND: Triple-negative breast cancer (TNBC) is a heterogeneous disease and we have previously shown that rapid relapse of TNBC is associated with distinct sociodemographic features. We hypothesized that rapid versus late relapse in TNBC is also defined by distinct clinical and genomic features of primary tumors. METHODS: Using three publicly-available datasets, we identified 453 patients diagnosed with primary TNBC with adequate follow-up to be characterized as 'rapid relapse' (rrTNBC; distant relapse or death ≤2 years of diagnosis), 'late relapse' (lrTNBC; > 2 years) or 'no relapse' (nrTNBC: > 5 years no relapse/death). We explored basic clinical and primary tumor multi-omic data, including whole transcriptome (n = 453), and whole genome copy number and mutation data for 171 cancer-related genes (n = 317). Association of rapid relapse with clinical and genomic features were assessed using Pearson chi-squared tests, t-tests, ANOVA, and Fisher exact tests. We evaluated logistic regression models of clinical features with subtype versus two models that integrated significant genomic features. RESULTS: Relative to nrTNBC, both rrTNBC and lrTNBC had significantly lower immune signatures and immune signatures were highly correlated to anti-tumor CD8 T-cell, M1 macrophage, and gamma-delta T-cell CIBERSORT inferred immune subsets. Intriguingly, lrTNBCs were enriched for luminal signatures. There was no difference in tumor mutation burden or percent genome altered across groups. Logistic regression mModels that incorporate genomic features significantly outperformed standard clinical/subtype models in training (n = 63 patients), testing (n = 63) and independent validation (n = 34) cohorts, although performance of all models were overall modest. CONCLUSIONS: We identify clinical and genomic features associated with rapid relapse TNBC for further study of this aggressive TNBC subset.

Aggressive Subsets of Metastatic Triple Negative Breast Cancer.

BACKGROUND: Relative to other metastatic breast cancer subtypes, metastatic triple-negative breast cancer (mTNBC) has a shorter duration of response to therapy and worse overall survival. Among patients with mTNBC, it is hypothesized that inflammatory breast cancer (IBC) and young women have particularly aggressive phenotypes. We investigated clinical and cell-free DNA (cfDNA) characteristics of inflammatory-mTNBC and young-mTNBC. PATIENTS AND METHODS: We evaluated 158 patients with mTNBC who were stratified into 3 groups: (1) IBC; (2) patients aged 45 years or younger at primary diagnosis without IBC (non-IBC young); and (3) patients over age 45 at diagnosis without IBC. We evaluated clinicopathologic characteristics, sites of metastasis, survival outcomes, and the fraction of DNA in circulation derived from tumor (TFx). RESULTS: Analysis of metastatic sites revealed that young patients without IBC had the most frequent lung metastases (P = .002). cfDNA analyses of first sample showed that TFx was highest in the non-IBC young group but not elevated in the IBC group (analysis of variance P = .056 for first TFx). Individually, median overall survival from metastatic diagnosis for the IBC group was 15.2 months; for the non-IBC young group, 21.2 months, and for the non-IBC over 45 group, 31.2 months. Patients with IBC and young patients without IBC had worse prognosis relative to patients over 45 without IBC (log-rank P = .023). CONCLUSIONS: Among patients with mTNBC in this single-institution cohort, patients with IBC and young patients without IBC had significantly worse overall survival compared with patients over 45 without IBC. Young patients without IBC had significantly higher cfDNA TFx, whereas patients with IBC did not have elevated TFx despite a poor prognosis. These findings demonstrate that further analyses of mTNBC subsets are warranted.

Decoding phonation with artificial intelligence (DeP AI): Proof of concept.

OBJECTIVE: Acoustic analysis of voice has the potential to expedite detection and diagnosis of voice disorders. Applying an image-based, neural-network approach to analyzing the acoustic signal may be an effective means for detecting and differentially diagnosing voice disorders. The purpose of this study is to provide a proof-of-concept that embedded data within human phonation can be accurately and efficiently decoded with deep learning neural network analysis to differentiate between normal and disordered voices. METHODS: Acoustic recordings from 10 vocally-healthy speakers, as well as 70 patients with one of seven voice disorders (n = 10 per diagnosis), were acquired from a clinical database. Acoustic signals were converted into spectrograms and used to train a convolutional neural network developed with the Keras library. The network architecture was trained separately for each of the seven diagnostic categories. Binary classification tasks (ie, to classify normal vs. disordered) were performed for each of the seven diagnostic categories. All models were validated using the 10-fold cross-validation technique. RESULTS: Binary classification averaged accuracies ranged from 58% to 90%. Models were most accurate in their classification of adductor spasmodic dysphonia, unilateral vocal fold paralysis, vocal fold polyp, polypoid corditis, and recurrent respiratory papillomatosis. Despite a small sample size, these findings are consistent with previously published data utilizing deep neural networks for classification of voice disorders. CONCLUSION: Promising preliminary results support further study of deep neural networks for clinical detection and diagnosis of human voice disorders. Current models should be optimized with a larger sample size. LEVELS OF EVIDENCE: Level III.