Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer.

Background: Androgen deprivation therapy (ADT) with radiotherapy can benefit patients with localized prostate cancer. However, ADT can negatively impact quality of life and there remain no validated predictive models to guide its use. Methods: Digital pathology image and clinical data from pre-treatment prostate tissue from 5,727 patients enrolled on five phase III randomized trials treated with radiotherapy +/- ADT were used to develop and validate an artificial intelligence (AI)-derived predictive model to assess ADT benefit with the primary endpoint of distant metastasis. After the model was locked, validation was performed on NRG/RTOG 9408 (n = 1,594) that randomized men to radiotherapy +/- 4 months of ADT. Fine-Gray regression and restricted mean survival times were used to assess the interaction between treatment and predictive model and within predictive model positive and negative subgroup treatment effects. Results: In the NRG/RTOG 9408 validation cohort (14.9 years of median follow-up), ADT significantly improved time to distant metastasis (subdistribution hazard ratio [sHR] = 0.64, 95%CI [0.45-0.90], p = 0.01). The predictive model-treatment interaction was significant (p-interaction = 0.01). In predictive model positive patients (n = 543, 34%), ADT significantly reduced the risk of distant metastasis compared to radiotherapy alone (sHR = 0.34, 95%CI [0.19-0.63], p < 0.001). There were no significant differences between treatment arms in the predictive model negative subgroup (n = 1,051, 66%; sHR = 0.92, 95%CI [0.59-1.43], p = 0.71). Conclusions: Our data, derived and validated from completed randomized phase III trials, show that an AI-based predictive model was able to identify prostate cancer patients, with predominately intermediate-risk disease, who are likely to benefit from short-term ADT.

Artificial Intelligence Predictive Model for Hormone Therapy Use in Prostate Cancer.

BACKGROUND: Androgen deprivation therapy (ADT) with radiotherapy can benefit patients with localized prostate cancer. However, ADT can negatively impact quality of life, and there remain no validated predictive models to guide its use. METHODS: We used digital pathology images from pretreatment prostate tissue and clinical data from 5727 patients enrolled in five phase 3 randomized trials, in which treatment was radiotherapy with or without ADT, as our data source to develop and validate an artificial intelligence (AI)­derived predictive patient-specific model that would determine which patients would develop the primary end point of distant metastasis. The model used baseline data to provide a binary output that a given patient will likely benefit from ADT or not. After the model was locked, validation was performed using data from NRG Oncology/Radiation Therapy Oncology Group (RTOG) 9408 (n=1594), a trial that randomly assigned men to radiotherapy plus or minus 4 months of ADT. Fine­Gray regression and restricted mean survival times were used to assess the interaction between treatment and the predictive model and within predictive model­positive, i.e., benefited from ADT, and ­negative subgroup treatment effects. RESULTS: Overall, in the NRG/RTOG 9408 validation cohort (14.9 years of median follow-up), ADT significantly improved time to distant metastasis. Of these enrolled patients, 543 (34%) were model positive, and ADT significantly reduced the risk of distant metastasis compared with radiotherapy alone. Of 1051 patients who were model negative, ADT did not provide benefit. CONCLUSIONS: Our AI-based predictive model was able to identify patients with a predominantly intermediate risk for prostate cancer likely to benefit from short-term ADT. (Supported by a grant [U10CA180822] from NRG Oncology Statistical and Data Management Center, a grant [UG1CA189867] from NCI Community Oncology Research Program, a grant [U10CA180868] from NRG Oncology Operations, and a grant [U24CA196067] from NRG Specimen Bank from the National Cancer Institute and by Artera, Inc. ClinicalTrials.gov numbers NCT00767286, NCT00002597, NCT00769548, NCT00005044, and NCT00033631.)

Fibroblast growth factor signalling influences homologous recombination-mediated DNA damage repair to promote drug resistance in ovarian cancer.

BACKGROUND: Ovarian cancer patients frequently develop chemotherapy resistance, limiting treatment options. We have previously shown that individuality in fibroblast growth factor 1 (FGF1) expression influences survival and chemotherapy response. METHODS: We used MTT assays to assess chemosensitivity to cisplatin and carboplatin following shRNA-mediated knockdown or heterologous over-expression of FGF1 (quantified by qRT-PCR and immunoblot analysis), and in combination with the FGFR inhibitors AZD4547 and SU5402, the ATM inhibitor KU55933 and DNA-PK inhibitor NU7026. Immunofluorescence microscopy was used to quantify the FGF1-dependent timecourse of replication protein A (RPA) and γH2AX foci formation. RESULTS: Pharmacological inhibition of FGF signalling reversed drug resistance in immortalised cell lines and in primary cell lines from drug-resistant ovarian cancer patients, while FGF1 over-expression induced resistance. Ataxia telangiectasia mutated (ATM) phosphorylation, but not DNA adduct formation was FGF1 dependent, following cisplatin or carboplatin challenge. Combining platinum drugs with the ATM inhibitor KU55933, but not with the DNA-PK inhibitor NU7026 re-sensitised resistant cells. FGF1 expression influenced the timecourse of damage-induced RPA and γH2AX nuclear foci formation. CONCLUSION: Drug resistance arises from FGF1-mediated differential activation of high-fidelity homologous recombination DNA damage repair. FGFR and ATM inhibitors reverse platinum drug resistance, highlighting novel combination chemotherapy approaches for future clinical trial evaluation.

Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials.

Prostate cancer is the most frequent cancer in men and a leading cause of cancer death. Determining a patient's optimal therapy is a challenge, where oncologists must select a therapy with the highest likelihood of success and the lowest likelihood of toxicity. International standards for prognostication rely on non-specific and semi-quantitative tools, commonly leading to over- and under-treatment. Tissue-based molecular biomarkers have attempted to address this, but most have limited validation in prospective randomized trials and expensive processing costs, posing substantial barriers to widespread adoption. There remains a significant need for accurate and scalable tools to support therapy personalization. Here we demonstrate prostate cancer therapy personalization by predicting long-term, clinically relevant outcomes using a multimodal deep learning architecture and train models using clinical data and digital histopathology from prostate biopsies. We train and validate models using five phase III randomized trials conducted across hundreds of clinical centers. Histopathological data was available for 5654 of 7764 randomized patients (71%) with a median follow-up of 11.4 years. Compared to the most common risk-stratification tool-risk groups developed by the National Cancer Center Network (NCCN)-our models have superior discriminatory performance across all endpoints, ranging from 9.2% to 14.6% relative improvement in a held-out validation set. This artificial intelligence-based tool improves prognostication over standard tools and allows oncologists to computationally predict the likeliest outcomes of specific patients to determine optimal treatment. Outfitted with digital scanners and internet access, any clinic could offer such capabilities, enabling global access to therapy personalization.

ABCB1 (MDR1) induction defines a common resistance mechanism in paclitaxel- and olaparib-resistant ovarian cancer cells.

BACKGROUND: Clinical response to chemotherapy for ovarian cancer is frequently compromised by the development of drug-resistant disease. The underlying molecular mechanisms and implications for prescription of routinely prescribed chemotherapy drugs are poorly understood. METHODS: We created novel A2780-derived ovarian cancer cell lines resistant to paclitaxel and olaparib following continuous incremental drug selection. MTT assays were used to assess chemosensitivity to paclitaxel and olaparib in drug-sensitive and drug-resistant cells±the ABCB1 inhibitors verapamil and elacridar and cross-resistance to cisplatin, carboplatin, doxorubicin, rucaparib, veliparib and AZD2461. ABCB1 expression was assessed by qRT-PCR, copy number, western blotting and immunohistochemical analysis and ABCB1 activity assessed by the Vybrant and P-glycoprotein-Glo assays. RESULTS: Paclitaxel-resistant cells were cross-resistant to olaparib, doxorubicin and rucaparib but not to veliparib or AZD2461. Resistance correlated with increased ABCB1 expression and was reversible following treatment with the ABCB1 inhibitors verapamil and elacridar. Active efflux of paclitaxel, olaparib, doxorubicin and rucaparib was confirmed in drug-resistant cells and in ABCB1-expressing bacterial membranes. CONCLUSIONS: We describe a common ABCB1-mediated mechanism of paclitaxel and olaparib resistance in ovarian cancer cells. Optimal choice of PARP inhibitor may therefore limit the progression of drug-resistant disease, while routine prescription of first-line paclitaxel may significantly limit subsequent chemotherapy options in ovarian cancer patients.

Small molecule antagonists of the sigma-1 receptor cause selective release of the death program in tumor and self-reliant cells and inhibit tumor growth in vitro and in vivo.

The acquisition of resistance to apoptosis, the cell's intrinsic suicide program, is essential for cancers to arise and progress and is a major reason behind treatment failures. We show in this article that small molecule antagonists of the sigma-1 receptor inhibit tumor cell survival to reveal caspase-dependent apoptosis. sigma antagonist-mediated caspase activation and cell death are substantially attenuated by the prototypic sigma-1 agonists (+)-SKF10,047 and (+)-pentazocine. Although several normal cell types such as fibroblasts, epithelial cells, and even sigma receptor-rich neurons are resistant to the apoptotic effects of sigma antagonists, cells that can promote autocrine survival such as lens epithelial and microvascular endothelial cells are as susceptible as tumor cells. Cellular susceptibility appears to correlate with differences in sigma receptor coupling rather than levels of expression. In susceptible cells only, sigma antagonists evoke a rapid rise in cytosolic calcium that is inhibited by sigma-1 agonists. In at least some tumor cells, sigma antagonists cause calcium-dependent activation of phospholipase C and concomitant calcium-independent inhibition of phosphatidylinositol 3'-kinase pathway signaling. Systemic administration of sigma antagonists significantly inhibits the growth of evolving and established hormone-sensitive and hormone-insensitive mammary carcinoma xenografts, orthotopic prostate tumors, and p53-null lung carcinoma xenografts in immunocompromised mice in the absence of side effects. Release of a sigma receptor-mediated brake on apoptosis may offer a new approach to cancer treatment.