Machine learning prediction of pathological complete response and overall survival of breast cancer patients in an underserved inner-city population.

BACKGROUND: Generalizability of predictive models for pathological complete response (pCR) and overall survival (OS) in breast cancer patients requires diverse datasets. This study employed four machine learning models to predict pCR and OS up to 7.5 years using data from a diverse and underserved inner-city population. METHODS: Demographics, staging, tumor subtypes, income, insurance status, and data from radiology reports were obtained from 475 breast cancer patients on neoadjuvant chemotherapy in an inner-city health system (01/01/2012 to 12/31/2021). Logistic regression, Neural Network, Random Forest, and Gradient Boosted Regression models were used to predict outcomes (pCR and OS) with fivefold cross validation. RESULTS: pCR was not associated with age, race, ethnicity, tumor staging, Nottingham grade, income, and insurance status (p > 0.05). ER-/HER2+ showed the highest pCR rate, followed by triple negative, ER+/HER2+, and ER+/HER2- (all p < 0.05), tumor size (p < 0.003) and background parenchymal enhancement (BPE) (p < 0.01). Machine learning models ranked ER+/HER2-, ER-/HER2+, tumor size, and BPE as top predictors of pCR (AUC = 0.74-0.76). OS was associated with race, pCR status, tumor subtype, and insurance status (p < 0.05), but not ethnicity and incomes (p > 0.05). Machine learning models ranked tumor stage, pCR, nodal stage, and triple-negative subtype as top predictors of OS (AUC = 0.83-0.85). When grouping race and ethnicity by tumor subtypes, neither OS nor pCR were different due to race and ethnicity for each tumor subtype (p > 0.05). CONCLUSION: Tumor subtypes and imaging characteristics were top predictors of pCR in our inner-city population. Insurance status, race, tumor subtypes and pCR were associated with OS. Machine learning models accurately predicted pCR and OS.

Similar Efficacy Observed for First-Line Immunotherapy in Racial/Ethnic Minority Patients With Metastatic NSCLC.

BACKGROUND: Limited data exist on the impact of immunotherapy use in ethnic minority patients with non-small cell lung cancer (NSCLC), because they have been underrepresented in immunotherapy trials. This study aims to evaluate race/ethnicity and other demographic, socioeconomic, and clinical factors of patients with metastatic NSCLC treated with first-line immunotherapy. METHODS: A retrospective cohort study of 5,920 patients diagnosed with lung cancer treated at Montefiore Einstein Cancer Center from January 1, 2013, to June 1, 2022, was used to identify patients with metastatic NSCLC without EGFR, ALK, or ROS1 alterations who underwent first-line immunotherapy (n=248). The primary endpoint was overall survival (OS), with secondary endpoints of progression-free survival (PFS) and time to discontinuation (TTD) from the start of immunotherapy. RESULTS: Among the 248 patients, median follow-up time was 12.0 months, median age at start of treatment was 66 years, and 39.1% were non-Hispanic Black, 30.2% were Hispanic, and 30.7% were non-Hispanic White. OS (P=.39), PFS (P=.29), and TTD (P=.98) were similar among racial/ethnic groups. Patients with an ECOG performance status (PS) of <2 at the start of immunotherapy had longer OS compared with those with ECOG PS of ≥2 (P<.0001). PD-L1 expression (<50% vs ≥50%; P=.03) and body mass index (BMI) (P=.01) were also found to be associated with PFS, and ECOG PS (P<.0001) and BMI (P=.02) were associated with TTD. In a multivariate analysis of OS and PFS, ECOG PS was the only variable found to be significant. CONCLUSIONS: Our study observed similar benefits of immunotherapy in patients with metastatic NSCLC in different racial and ethnic groups. Furthermore, ECOG PS was associated with OS, and PD-L1 expression and BMI were associated with PFS and TTD. These findings help identify potential factors associated with outcomes and care while patients are undergoing immunotherapy.

Breast cancer survivorship care during the COVID-19 pandemic within an urban New York Hospital System.

PURPOSE: To examine clinicodemographic determinants associated with breast cancer survivorship follow-up during COVID-19. METHODS: We performed a retrospective, population-based cohort study including early stage (Stage I-II) breast cancer patients who underwent resection between 2006 and 2018 in a New York City hospital system. The primary outcome was oncologic follow-up prior to and during the COVID-19 pandemic. Secondary analyses compared differences in follow-up by COVID-19 case rates stratified by ZIP code. RESULTS: A total of 2942 patients with early-stage breast cancer were available for analysis. 1588 (54%) of patients had attended follow-up in the year prior to the COVID-19 period but failed to continue to follow-up during the pandemic, either in-person or via telemedicine. 1242 (42%) patients attended a follow-up appointment during the COVID-19 pandemic. Compared with patients who did not present for follow-up during COVID-19, patients who continued their oncologic follow-up during the pandemic were younger (p = 0.049) more likely to have received adjuvant radiation therapy (p = 0.025), and have lower household income (p = 0.031) on multivariate modeling. When patients who live in Bronx, New York, were stratified by ZIP code, there was a modest negative association (r = -0.56) between COVID-19 cases and proportion of patients who continued to follow-up during the COVID-19 period. CONCLUSION: We observed a dramatic disruption in routine breast cancer follow-up during the COVID-19 pandemic. Providers and health systems should emphasize reintegrating patients who missed appointments during COVID-19 back into regular surveillance programs to avoid significant morbidity and mortality from missed breast cancer recurrences.

A mouse Fcgamma-Fcepsilon protein that inhibits mast cells through activation of FcgammaRIIB, SH2 domain-containing inositol phosphatase 1, and SH2 domain-containing protein tyrosine phosphatases.

BACKGROUND: A human Fcgamma-Fcepsilon fusion protein (GE2) designed to inhibit FcepsilonRI signaling by coaggregating FcepsilonRI with the inhibitory receptor FcgammaRIIB has been shown to inhibit mast cell activation and block cutaneous anaphylaxis. A critical issue remained as to whether the mechanism of GE2 inhibition is competition for IgE binding or inhibitory signaling through FcgammaRIIB. OBJECTIVE: Our aim was to define the in vitro and in vivo mechanism of action of a mouse homolog of GE2 (mGE) and to assess the potential of human GE2 (hGE2) for therapeutic administration. METHODS: The in vitro activity of mGE on mediator release and signaling pathways was characterized in IgE-sensitized bone marrow-derived mast cells (BMMCs). The in vivo activity of mGE was examined in mouse passive cutaneous and passive systemic anaphylaxis models, and the therapeutic activity of hGE2 was evaluated in Ascaris suum-sensitized cynomolgus monkeys. RESULTS: mGE inhibited release of histamine and cytokines by BMMCs from wild-type mice but not by BMMCs from FcgammaRIIB-deficient mice. In mice mGE blocked IgE-dependent anaphylaxis mediated by mast cells with sustained efficacy. In BMMCs mGE decreased spleen tyrosine kinase and extracellular signal-regulated kinases 1/2 phosphorylation and induced FcgammaRIIB phosphorylation and the subsequent recruitment of SH2 domain-containing inositol polyphosphate 5' phosphatase (SHIP) 1 and SH2 domain-containing protein tyrosine phosphatase (SHP) 1/2 phosphatases. When administered therapeutically, hGE2 protected sensitized monkeys from local anaphylaxis for 3 weeks. CONCLUSION: mGE-mediated inhibition of mast cell activation is associated with inhibitory signaling through FcgammaRIIB that results from activation of SHIP-1 and SHP-1/2 phosphatases.