CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

OBJECTIVES: To develop a deep learning model combining CT scans and clinical information to predict overall survival in advanced hepatocellular carcinoma (HCC). METHODS: This retrospective study included immunotherapy-treated advanced HCC patients from 52 multi-national in-house centers between 2018 and 2022. A multi-modal prognostic model using baseline and the first follow-up CT images and 7 clinical variables was proposed. A convolutional-recurrent neural network (CRNN) was developed to extract spatial-temporal information from automatically selected representative 2D CT slices to provide a radiological score, then fused with a Cox-based clinical score to provide the survival risk. The model's effectiveness was assessed using a time-dependent area under the receiver operating curve (AUC), and risk group stratification using the log-rank test. Prognostic performances of multi-modal inputs were compared to models of missing modality, and the size-based RECIST criteria. RESULTS: Two-hundred seven patients (mean age, 61 years ± 12 [SD], 180 men) were included. The multi-modal CRNN model reached the AUC of 0.777 and 0.704 of 1-year overall survival predictions in the validation and test sets. The model achieved significant risk stratification in validation (hazard ratio [HR] = 3.330, p = 0.008), and test sets (HR = 2.024, p = 0.047) based on the median risk score of the training set. Models with missing modalities (the single-modal imaging-based model and the model incorporating only baseline scans) can still achieve favorable risk stratification performance (all p < 0.05, except for one, p = 0.053). Moreover, results proved the superiority of the deep learning-based model to the RECIST criteria. CONCLUSION: Deep learning analysis of CT scans and clinical data can offer significant prognostic insights for patients with advanced HCC. CRITICAL RELEVANCE STATEMENT: The established model can help monitor patients' disease statuses and identify those with poor prognosis at the time of first follow-up, helping clinicians make informed treatment decisions, as well as early and timely interventions. KEY POINTS: An AI-based prognostic model was developed for advanced HCC using multi-national patients. The model extracts spatial-temporal information from CT scans and integrates it with clinical variables to prognosticate. The model demonstrated superior prognostic ability compared to the conventional size-based RECIST method.

Landscape of cancer clinical trials in India - a comprehensive analysis of the Clinical Trial Registry-India.

Background: Cancer is one of the leading causes of morbidity and mortality in India. Clinical trials are critical for driving innovation in cancer therapy, diagnosis, and prevention. This study aims to depict the evolving landscape of cancer clinical trials in India by analysing the clinical trials registered in Clinical Trial Registry-India (CTRI). Methods: We identified cancer trials registered in CTRI (between 2007 and 2021) using search terms adapted from the cancer types defined by the National Cancer Institute (USA). We then collated and analysed the publicly available information from CTRI (cancer subtypes, type of trial, treatment intent, type of intervention, sponsor type, recruitment countries) and used descriptive statistics to illustrate the overall as well as year-to-year trend. Findings: In total, we identified 1988 cancer trials, the majority of which focused on treating cancer (63%) and rest of the trials aimed at optimising the operational aspects of surgery (19%), mitigating treatment-related toxicity (10.6%), or treating cancer-related symptoms (7.8%). Focusing on trials with the intent of treating cancer, we found that most were investigating solid tumours as opposed to haematological malignancies with the most prominent cancer subtypes being breast cancer (17%), head and neck cancer (9.8%), lung cancer (9.6%), and cervical cancer (6.6%). The number of trials conducted in a given cancer subtype from our analysis overall correlated to the incidence, mortality, and 5-year prevalence of the respective cancer subtype in India; however, head and neck cancer and cervical cancer were underrepresented in trials as compared with the disease burden. The most common type of intervention was investigational drugs. The most common sponsor types were global pharmaceutical industry (26%) and research institution and hospital (26%). Despite a relatively high cancer burden, the availability of cancer trials in the Northeastern states of India was limited. Interpretation: There is a pressing need for clinical cancer research in India to be better aligned with the nation's healthcare needs and disease burden, focusing on prevalent and deadly cancers while ensuring the availability of clinical trials across geographic regions and underserved populations. Funding: Pi Health USA, a fully owned subsidiary of BeiGene Ltd.

Remote Monitoring and Data Collection for Decentralized Clinical Trials.

Importance: Less than 5% of patients with cancer enroll in a clinical trial, partly due to financial and logistic burdens, especially among underserved populations. The COVID-19 pandemic marked a substantial shift in the adoption of decentralized trial operations by pharmaceutical companies. Objective: To assess the current global state of adoption of decentralized trial technologies, understand factors that may be driving or preventing adoption, and highlight aspirations and direction for industry to enable more patient-centric trials. Design, Setting, and Participants: The Bloomberg New Economy International Cancer Coalition, composed of patient advocacy, industry, government regulator, and academic medical center representatives, developed a survey directed to global biopharmaceutical companies of the coalition from October 1 through December 31, 2022, with a focus on registrational clinical trials. The data for this survey study were analyzed between January 1 and 31, 2023. Exposure: Adoption of decentralized clinical trial technologies. Main Outcomes and Measures: The survey measured (1) outcomes of different remote monitoring and data collection technologies on patient centricity, (2) adoption of these technologies in oncology and all therapeutic areas, and (3) barriers and facilitators to adoption using descriptive statistics. Results: All 8 invited coalition companies completed the survey, representing 33% of the oncology market by revenues in 2021. Across nearly all technologies, adoption in oncology trials lags that of all trials. In the current state, electronic diaries and electronic clinical outcome assessments are the most used technology, with a mean (SD) of 56% (19%) and 51% (29%) adoption for all trials and oncology trials, respectively, whereas visits within local physician networks is the least adopted at a mean (SD) of 12% (18%) and 7% (9%), respectively. Looking forward, the difference between the current and aspired adoption rate in 5 years for oncology is large, with respondents expecting a 40% or greater absolute adoption increase in 8 of the 11 technologies surveyed. Furthermore, digitally enabled recruitment, local imaging capabilities, and local physician networks were identified as technologies that could be most effective for improving patient centricity in the long term. Conclusions and Relevance: These findings may help to galvanize momentum toward greater adoption of enabling technologies to support a new paradigm of trials that are more accessible, less burdensome, and more inclusive.

Decoding kinase-adverse event associations for small molecule kinase inhibitors.

Small molecule kinase inhibitors (SMKIs) are being approved at a fast pace under expedited programs for anticancer treatment. In this study, we construct a multi-domain dataset from a total of 4638 patients in the registrational trials of 16 FDA-approved SMKIs and employ a machine-learning model to examine the relationships between kinase targets and adverse events (AEs). Internal and external (datasets from two independent SMKIs) validations have been conducted to verify the usefulness of the established model. We systematically evaluate the potential associations between 442 kinases with 2145 AEs and made publicly accessible an interactive web application "Identification of Kinase-Specific Signal" ( https://gongj.shinyapps.io/ml4ki ). The developed model (1) provides a platform for experimentalists to identify and verify undiscovered KI-AE pairs, (2) serves as a precision-medicine tool to mitigate individual patient safety risks by forecasting clinical safety signals and (3) can function as a modern drug development tool to screen and compare SMKI target therapies from the safety perspective.

Dose dependence of treatment-related adverse events for immune checkpoint inhibitor therapies: a model-based meta-analysis.

Programmed cell death-1 (PD-1) and/or cytotoxic T lymphocyte-associated antigen 4 (CTLA-4) immune checkpoint inhibitor (ICI) treatments are associated with adverse events (AEs), which may be dependent on ICI dose. Applying a model-based meta-analysis to evaluate safety data from published clinical trials from 2005 to 2018, we analyzed the dose/exposure dependence of ICI treatment-related AE (trAE) and immune-mediated AE (imAE) rates. Unlike with PD-1 inhibitor monotherapy, CTLA-4 inhibitor monotherapy exhibited a dose/exposure dependence on most AE types evaluated. Furthermore, combination therapy with PD-1 inhibitor significantly strengthened the dependence of trAE and imAE rates on CTLA-4 inhibitor dose/exposure.

US Food and Drug Administration Pooled Analysis to Assess the Impact of Bone-Only Metastatic Breast Cancer on Clinical Trial Outcomes and Radiographic Assessments.

Purpose The outcome and proportion of patients with bone-only (BO) metastatic breast cancer (MBC) has not been well described. We sought to describe the differential outcomes of patients with BO MBC in clinical trials and explore whether there was a discrepancy in radiographic reads between investigator and blinded independent central review. Methods We pooled and analyzed data on 10,521 patients from 13 prospective trials submitted for MBC treatment in initial or supplemental New Drug or Biologics License Applications from 2005. Three subsets were evaluated: BO, bone with other metastases (BWO), and no bone metastases (NBM). Early discordance rate and late discordance rate were calculated from 3,733 and 2,813 patients subject to a blinded independent central review, respectively. Results Bone metastases were identified in 49% (range: 42% to 73%) of patients across trials. BO disease was present in 12.5% (range: 4% to 26%), dependent on subtype. Investigator-assessed progression-free survival (PFS) and overall survival (OS) for the pooled trials demonstrated improved outcomes for the BO subgroup compared with other subgroups (BO v BWO PFS hazard ratio [HR], 0.64; 95% CI, 0.591 to 0.696; BO v NBM PFS HR, 0.70; 95% CI, 0.65 to 0.76; BO v BWO OS HR, 0.56; 95% CI, 0.50 to 0.61; BO v NBM OS HR, 0.68; 95% CI, 0.61 to 0.76). The BO subgroup has a higher early discordance rate and lower late discordance rate than the BWO and NBM subgroups. Conclusion To our knowledge, this review is the largest analysis to date of the BO subgroup of MBC and suggests this subgroup may have a distinct natural history. There also seems to be a difference in how the local investigators assessed progression events in the BO subgroup when compared with the other two groups.

FDA Approval Summary: Rucaparib for the Treatment of Patients with Deleterious BRCA Mutation-Associated Advanced Ovarian Cancer.

On December 19, 2016, the FDA granted accelerated approval to rucaparib (RUBRACA; Clovis Oncology, Inc.) for the treatment of patients with deleterious BRCA mutation (germline and/or somatic)-associated advanced ovarian cancer who have been treated with two or more chemotherapies. The FDA also approved the FoundationFocus CDx BRCA test (Foundation Medicine, Inc.), the first next-generation sequencing-based companion diagnostic, for identifying patients with advanced ovarian cancer eligible for treatment with rucaparib based on detection of deleterious BRCA1 and/or BRCA2 mutations in tumor tissue. Rucaparib's approval was based primarily on efficacy data from 106 patients with BRCA mutation-associated ovarian cancer who had prior treatment with two or more chemotherapies and safety data from 377 patients with ovarian cancer treated with rucaparib 600 mg orally twice daily on two open-label, single-arm trials. Investigator-assessed objective response rate was 54% [57/106; 95% confidence interval (CI), 44-64], and median duration of response was 9.2 months (95% CI, 6.6-11.7). The approved companion diagnostic verified tumor BRCA mutation status retrospectively in 96% (64/67) of patients. Common adverse reactions (≥20%) to rucaparib were nausea, fatigue, vomiting, anemia, abdominal pain, dysgeusia, constipation, decreased appetite, diarrhea, thrombocytopenia, and dyspnea. This article summarizes the FDA review and data supporting rucaparib's accelerated approval. Clin Cancer Res; 23(23); 7165-70. ©2017 AACRSee related commentary by Kohn et al., p. 7155.

U.S. Food and Drug Administration Approval Summary: Atezolizumab for Metastatic Non-Small Cell Lung Cancer.

On October 18, 2016, the FDA approved atezolizumab (TECENTRIQ; Genentech, Inc.) for treatment of patients with metastatic non-small cell lung cancer (mNSCLC) whose disease progressed during or following platinum-containing chemotherapy. Approval was based on demonstration of clinically meaningful improvements in overall survival (OS) and an acceptable safety profile in two randomized clinical trials (OAK and POPLAR). Median OS in OAK, a phase III trial, was 13.8 months [95% confidence interval (CI), 11.8-15.7] in the atezolizumab arm compared with 9.6 months (95% CI, 8.6-11.2) in the docetaxel arm [hazard ratio (HR) = 0.74; 95% CI, 0.63-0.87; P = 0.0004]. Median OS in POPLAR, a phase II trial, was 12.6 months (95% CI, 9.7-16.0) and 9.7 months (95% CI, 8.6-12.0; HR = 0.69; 95% CI, 0.52-0.92) for the atezolizumab and docetaxel arms, respectively. In patients treated with atezolizumab, the most common (≥20%) adverse reactions were fatigue, decreased appetite, dyspnea, cough, nausea, musculoskeletal pain, and constipation; the most common (≥2%) grade 3 to 4 adverse events were dyspnea, pneumonia, hypoxia, hyponatremia, fatigue, anemia, musculoskeletal pain, aspartate aminotransferase increase, alanine aminotransferase increase, dysphagia, and arthralgia. Clinically significant immune-related adverse events for patients receiving atezolizumab included 1.4% incidence each of grade 3 to 4 pneumonitis, hepatitis, colitis, and thyroid disease. Clin Cancer Res; 23(16); 4534-9. ©2017 AACR.

Regulatory considerations on endpoints in ovarian cancer drug development.

Ovarian cancer remains a disease entity that is responsible for considerable morbidity and mortality among women worldwide. Modern drug research pipelines and accelerated drug development timelines applied to other disease entities have begun to make an impact on treatment options for patients with advanced ovarian cancer, as exemplified by the recent accelerated approval of 2 agents for this disease as the forerunners of a growing number of registrational trials. Regulatory flexibility for this serious and life-threatening condition spurs the consideration of intermediate endpoints for regulatory trial design, including potential applications in the development of newer therapeutic classes such as targeted therapies and immunotherapies for patients with advanced ovarian cancer. Cancer 2017;123:2604-8. © 2017 American Cancer Society.

FDA Approval Summary: Atezolizumab for the Treatment of Patients with Progressive Advanced Urothelial Carcinoma after Platinum-Containing Chemotherapy.

Until recently in the United States, no products were approved for second-line treatment of advanced urothelial carcinoma. On May 18, 2016, the U.S. Food and Drug Administration approved atezolizumab for the treatment of patients with locally advanced or metastatic urothelial carcinoma whose disease progressed during or following platinum-containing chemotherapy or within 12 months of neoadjuvant or adjuvant treatment with platinum-containing chemotherapy. Atezolizumab is a programmed death-ligand 1 (PD-L1) blocking antibody and represents the first approved product directed against PD-L1. This accelerated approval was based on results of a single-arm trial in 310 patients with locally advanced or metastatic urothelial carcinoma who had disease progression after prior platinum-containing chemotherapy. Patients received atezolizumab 1,200 mg intravenously every 3 weeks until disease progression or unacceptable toxicity. Key efficacy measures were objective response rate (ORR), as assessed by Independent Review per RECIST 1.1, and duration of response (DoR). With a median follow-up of 14.4 months, confirmed ORR was 14.8% (95% CI: 11.1, 19.3) in all treated patients. Median DoR was not reached and response durations ranged from 2.1+ to 13.8+ months. Of the 46 responders, 37 patients had an ongoing response for ≥ 6 months. The most common adverse reactions (≥20%) were fatigue, decreased appetite, nausea, urinary tract infection, pyrexia, and constipation. Infection and immune-related adverse events also occurred, including pneumonitis, hepatitis, colitis, endocrine disorders, and rashes. Overall, the benefit-risk assessment was favorable to support accelerated approval. The observed clinical benefits need to be verified in confirmatory trial(s). IMPLICATIONS FOR PRACTICE: This accelerated approval of atezolizumab for second-line use in advanced urothelial carcinoma provides patients with an effective, novel treatment option for the management of their disease. This represents the first immunotherapy approved in this disease setting.

FDA Approval Summary: Nivolumab in Advanced Renal Cell Carcinoma After Anti-Angiogenic Therapy and Exploratory Predictive Biomarker Analysis.

On November 23, 2015, the U.S. Food and Drug Administration approved nivolumab (OPDIVO, Bristol-Myers Squibb Company) for patients with advanced renal cell carcinoma (RCC) who have received prior anti-angiogenic therapy. The approval was based on efficacy and safety data demonstrated in an open-label, randomized study of 821 patients with advanced RCC who progressed after at least one anti-angiogenic therapy. Patients were randomized to nivolumab or everolimus and followed for disease progression. The primary end point was overall survival. Subsequent therapies, including everolimus for patients who developed progressive disease on the nivolumab arm, were allowed, but no cross-over was permitted. The median overall survival was 25.0 months on the nivolumab arm and 19.6 months on everolimus arm (hazard ratio: 0.73; 95% confidence interval: 0.60-0.89). The confirmed response rates were 21.5% versus 3.9%; median durations of response were 23.0 versus 13.7 months, and median times to response were 3.0 versus 3.7 months in the nivolumab and everolimus arms, respectively. A statistically significant improvement in progression-free survival was not observed in this trial. The safety profile of nivolumab in renal cell cancer was similar to that in other disease settings. However, the incidence of immune-mediated nephritis appeared to be higher in patients with RCC. The Oncologist 2017;22:311-317 IMPLICATIONS FOR PRACTICE: The overall benefit/risk profile demonstrated in trial CA209025 supported the approval of nivolumab as an additional treatment option for patients with advanced renal cell carcinoma after anti-angiogenic therapy. The use of nivolumab in patients who had received vascular endothelial growth factor-targeted therapy resulted in a 5.4 month improvement in median overall survival compared with the everolimus arm. This difference is statistically significant and clinically meaningful.

U.S. Food and Drug Administration Approval: Cabozantinib for the Treatment of Advanced Renal Cell Carcinoma.

On April 25, 2016, the FDA approved cabozantinib (Cabometyx; Exelixis, Inc.) for the treatment of advanced renal cell carcinoma (RCC) in patients who have received prior antiangiogenic therapy. The approval was based on data from one randomized, open-label, multicenter study in which patients with RCC who had received prior antiangiogenic therapy were treated with either cabozantinib 60 mg orally once daily (n = 330) or everolimus 10 mg orally once daily (n = 328). The major efficacy outcome measure was progression-free survival (PFS) as assessed by a blinded independent radiology review committee in the first 375 randomized patients. A statistically significant improvement in PFS was seen, with a median PFS of 7.4 and 3.8 months in the cabozantinib and everolimus arms, respectively [hazard ratio (HR), 0.58; 95% confidence interval (CI), 0.45-0.74; P < 0.0001]. At a second interim analysis, a statistically significant improvement in overall survival (OS) in the intent-to-treat population was also demonstrated, with a median OS of 21.4 and 16.5 months in the cabozantinib and everolimus arms, respectively (HR, 0.66; 95% CI, 0.53-0.83; P = 0.0003). The most common (greater than or equal to 25%) adverse reactions included diarrhea, fatigue, nausea, decreased appetite, palmar-plantar erythrodysesthesia syndrome, hypertension, vomiting, weight loss, and constipation. Clin Cancer Res; 23(2); 330-5. ©2016 AACR.

An FDA Perspective on the Regulatory Implications of Complex Signatures to Predict Response to Targeted Therapies.

As technologies evolve, and diagnostics move from detection of single biomarkers toward complex signatures, an increase in the clinical use and regulatory submission of complex signatures is anticipated. However, to date, no complex signatures have been approved as companion diagnostics. In this article, we will describe the potential benefit of complex signatures and their unique regulatory challenges, including analytic performance validation, complex signature simulation, and clinical performance evaluation. We also will review the potential regulatory pathways for clearance, approval, or acceptance of complex signatures by the FDA. These regulatory pathways include regulations applicable to in vitro diagnostic devices, including companion diagnostic devices, the potential for labeling as a complementary diagnostic, and the biomarker qualification program. Clin Cancer Res; 23(6); 1368-72. ©2016 AACR.