Search NASA⌕ Search

SEARCH · Search NASA

Results for “Cancer”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,045 records · Page 58

Compositions and methods for cancer treatment using targeted carbon nanotubes

The present invention is a method for detecting and destroying cancer tumors. The method is based on the concept of associating a linking protein or linking peptide such as, but not limited to, annexin V or other annexins to carbon nanotubes such as single-walled carbon nanotubes (SWNTs) to form a protein-CNT complex. Said linking protein or peptide can selectively bind to cancerous cells, especially tumor vasculature endothelial cells, rather than to healthy ones by binding to cancer-specific external receptors such as anionic phospholipids including phosphatidylserine expressed on the outer surfaces of cancer cells only. Irradiation of bound CNTs with one or more specific electromagnetic wavelengths is then used to detect and destroy those cells to which the CNTs are bound via the linking protein or peptide thereby destroying the tumor or cancer cells and preferably an immunostimulant is provided to the patient to enhance the immune response against antigens released from the tumor or cancer cells.

60 APPLIED LIFE SCIENCES↗

Role for DNA methylation in the regulation of miR-200c and miR-141 expression in normal and cancer cells

BACKGROUND: The microRNA-200 family participates in the maintenance of an epithelial phenotype and loss of its expression can result in epithelial to mesenchymal transition (EMT). Furthermore, the loss of expression of miR-200 family members is linked to an aggressive cancer phenotype. Regulation of the miR-200 family expression in normal and cancer cells is not fully understood. METHODOLOGY/ PRINCIPAL FINDINGS: Epigenetic mechanisms participate in the control of miR-200c and miR-141 expression in both normal and cancer cells. A CpG island near the predicted mir-200c/mir-141 transcription start site shows a striking correlation between miR-200c and miR-141 expression and DNA methylation in both normal and cancer cells, as determined by MassARRAY technology. The CpG island is unmethylated in human miR-200/miR-141 expressing epithelial cells and in miR-200c/miR-141 positive tumor cells. The CpG island is heavily methylated in human miR-200c/miR-141 negative fibroblasts and miR-200c/miR-141 negative tumor cells. Mouse cells show a similar inverse correlation between DNA methylation and miR-200c expression. Enrichment of permissive histone modifications, H3 acetylation and H3K4 trimethylation, is seen in normal miR-200c/miR-141-positive epithelial cells, as determined by chromatin immunoprecipitation coupled to real-time PCR. In contrast, repressive H3K9 dimethylation marks are present in normal miR-200c/miR-141-negative fibroblasts and miR-200c/miR-141 negative cancer cells and the permissive histone modifications are absent. The epigenetic modifier drug, 5-aza-2'-deoxycytidine, reactivates miR-200c/miR-141 expression showing that epigenetic mechanisms play a functional role in their transcriptional control. CONCLUSIONS/ SIGNIFICANCE: We report that DNA methylation plays a role in the normal cell type-specific expression of miR-200c and miR-141 and this role appears evolutionarily conserved, since similar results were obtained in mouse. Aberrant DNA methylation of the miR-200c/141 CpG island is closely linked to their inappropriate silencing in cancer cells. Since the miR-200c cluster plays a significant role in EMT, our results suggest an important role for DNA methylation in the control of phenotypic conversions in normal cells.

59 BASIC BIOLOGICAL SCIENCES↗

Matrix Metalloproteinases as Candidate Antigenic Determinants for Anti‐Tumor Autoantibodies in Human Ovarian Cancer: A Post Hoc Analysis

Circulating antibodies in patients with cancer can facilitate the identification of accessible epitopes on autoantigens expressed by tumors. To identify previously unrecognized protein targets in ovarian cancer, we computationally assessed a heptapeptide consensus motif (VPELGHE, flanked by two cysteine residues yielding a cyclic nonapeptide under oxidizing conditions) previously discovered via phage display-based epitope mapping of autoantibodies in patients. Eight proteins associated with ovarian cancer encompass amino acid sequences similar to the consensus motif and were, therefore, considered as candidate native autoantigens. Among these candidate targets, however, matrix metalloproteinase 14 (MMP14) demonstrates gene expression that is both high and negatively correlated with survival in ovarian cancer patient cohorts. MMP14 protein levels are also stable in tumor versus non-tumor tissues. Moreover, the corresponding heptapeptide mimic in MMP14 occurs within an α-helical secondary structural element observed in its catalytic domain. These findings demonstrate that a subset of patient-derived autoantibodies may interact with a previously unknown antigenic epitope found in MMP14 and other MMPs, thereby providing opportunities for the development of new targeted agents.

Biochemistry & Molecular Biology↗

A hidden Markov model for population-level cervical cancer screening data

The Cancer Registry of Norway has been administrating a national cervical cancer screening program since 1992 by coordinating triennial cytology exam screenings for the female population between 25 and 69 years of age. Up to 80% of cancers are prevented through mass screening, but this comes at the expense of considerable screening activity and leads to overtreatment of clinically asymptomatic precancers. Here, we present a continuous-time, time-inhomogeneous hidden Markov model which was developed to understand the screening process and cervical cancer carcinogenesis in detail. By leveraging 1.7 million individual's multivariate time-series of medical exams performed over a 25-year period, we simultaneously estimate all model parameters. We show that an age-dependent model reflects the Norwegian screening program by comparing empirical survival curves from observed registry data and data simulated from the proposed model. The model can be generalized to include more detailed individual-level covariates as well as new types of screening exams. By utilizing individual screening histories and covariate data, the proposed model shows potential for improving strategies for cancer screening programs by personalizing recommended screening intervals.

59 BASIC BIOLOGICAL SCIENCES↗

Subclonal diversification of primary breast cancer revealed by multiregion sequencing

Sequencing cancer genomes may enable tailoring of therapeutics to the underlying biological abnormalities driving a particular patient's tumor. However, sequencing-based strategies rely heavily on representative sampling of tumors. To understand the subclonal structure of primary breast cancer, we applied whole-genome and targeted sequencing to multiple samples from each of 50 patients' tumors (303 samples in total). The extent of subclonal diversification varied among cases and followed spatial patterns. No strict temporal order was evident, with point mutations and rearrangements affecting the most common breast cancer genes, including PIK3CA, TP53, PTEN, BRCA2 and MYC, occurring early in some tumors and late in others. In 13 out of 50 cancers, potentially targetable mutations were subclonal. Landmarks of disease progression, such as resistance to chemotherapy and the acquisition of invasive or metastatic potential, arose within detectable subclones of antecedent lesions. These findings highlight the importance of including analyses of subclonal structure and tumor evolution in clinical trials of primary breast cancer.

59 BASIC BIOLOGICAL SCIENCES↗

In search of autophagy biomarkers in breast cancer: Receptor status and drug agnostic transcriptional changes during autophagy flux in cell lines

Autophagy drives drug resistance and drug-induced cancer cell cytotoxicity. Targeting the autophagy process could greatly improve chemotherapy outcomes. The discovery of specific inhibitors or activators has been hindered by challenges with reliably measuring autophagy levels in a clinical setting. We investigated drug-induced autophagy in breast cancer cell lines with differing ER/PR/Her2 receptor status by exposing them to known but divergent autophagy inducers each with a unique molecular target, tamoxifen, trastuzumab, bortezomib or rapamycin. Differential gene expression analysis from total RNA extracted during the earliest sign of autophagy flux showed both cell- and drug-specific changes. We analyzed the list of differentially expressed genes to find a common, cell- and drug-agnostic autophagy signature. Twelve mRNAs were significantly modulated by all the drugs and 11 were orthogonally verified with Q-RT-PCR (Klhl24, Hbp1, Crebrf, Ypel2, Fbxo32, Gdf15, Cdc25a, Ddit4, Psat1, Cd22, Ypel3). The drug agnostic mRNA signature was similarly induced by a mitochondrially targeted agent, MitoQ. In-silico analysis on the KM-plotter cancer database showed that the levels of these mRNAs are detectable in human samples and associated with breast cancer prognosis outcomes of Relapse-Free Survival in all patients (RSF), Overall Survival in all patients (OS), and Relapse-Free Survival in ER + Patients (RSF ER + ). High levels of Klhl24, Hbp1, Crebrf, Ypel2, CD22 and Ypel3 were correlated with better outcomes, whereas lower levels of Gdf15, Cdc25a, Ddit4 and Psat1 were associated with better prognosis in breast cancer patients. This gene signature uncovers candidate autophagy biomarkers that could be tested during preclinical and clinical studies to monitor the autophagy process.

60 APPLIED LIFE SCIENCES↗

Pan-cancer evaluation of clinical value of mitotic network activity index (MNAI) and its predictive value for immunotherapy

Increased mitotic activity is associated with the genesis and aggressiveness of many cancers. To assess the clinical value of mitotic activity as prognostic biomarker, we performed a pan-cancer study on the mitotic network activity index (MNAI) constructed based on 54-gene mitotic apparatus network. Our pan-cancer assessment on TCGA (33 tumor types, 10,061 patients) and validation on other publicly available cohorts (23 tumor types, 9,209 patients) confirmed the significant association of MNAI with overall survival, progression-free survival, and other prognostic endpoints in multiple cancer types, including lower-grade gliomas (LGG), breast invasive carcinoma (BRCA), as well as many others. We also showed significant association between MNAI and genetic instability, which provides a biological explanation of its prognostic impact at pan-cancer landscape. Our association analysis revealed that patients with high MNAI benefitted more from anti-PD-1 and Anti-CTLA-4 treatment. In addition, we demonstrated that multimodal integration of MNAI and the AI-empowered Cellular Morphometric Subtypes (CMS) significantly improved the predictive power of prognosis compared to using MNAI and CMS alone. Our results suggest that MNAI can be used as a potential prognostic biomarker for different tumor types toward different clinical endpoints, and multimodal integration of MNAI and CMS exceeds individual biomarker for precision prognosis.

60 APPLIED LIFE SCIENCES↗

PET Imaging Agents (FES, FFNP, and FDHT) for Estrogen, Androgen, and Progesterone Receptors to Improve Management of Breast and Prostate Cancers by Functional Imaging

Many breast and prostate cancers are driven by the action of steroid hormones on their cognate receptors in primary tumors and in metastases, and endocrine therapies that inhibit hormone production or block the action of these receptors provide clinical benefit to many but not all of these cancer patients. Because it is difficult to predict which individuals will be helped by endocrine therapies and which will not, positron emission tomography (PET) imaging of estrogen receptor (ER) and progesterone receptor (PgR) in breast cancer, and androgen receptor (AR) in prostate cancer can provide useful, often functional, information on the likelihood of endocrine therapy response in individual patients. This review covers our development of three PET imaging agents, 16α-[ 18 F]fluoroestradiol (FES) for ER, 21-[ 18 F]fluoro-furanyl-nor-progesterone (FFNP) for PgR, and 16β-[ 18 F]fluoro-5α-dihydrotestosterone (FDHT) for AR, and the evolution of their clinical use. For these agents, the pathway from concept through development tracks with an emerging understanding of critical performance criteria that is needed for successful PET imaging of these low-abundance receptor targets. Progress in the ongoing evaluation of what they can add to the clinical management of breast and prostate cancers reflects our increased understanding of these diseases and of optimal strategies for predicting the success of clinical endocrine therapies.

60 APPLIED LIFE SCIENCES↗

NCAPH drives breast cancer progression and identifies a gene signature that predicts luminal a tumour recurrence

Luminal A tumours generally have a favourable prognosis but possess the highest 10-year recurrence risk among breast cancers. Additionally, a quarter of the recurrence cases occur within 5 years post-diagnosis. Identifying such patients is crucial as long-term relapsers could benefit from extended hormone therapy, while early relapsers might require more aggressive treatment. We conducted a study to explore non-structural chromosome maintenance condensin I complex subunit H’s (NCAPH) role in luminal A breast cancer pathogenesis, both in vitro and in vivo, aiming to identify an intratumoural gene expression signature, with a focus on elevated NCAPH levels, as a potential marker for unfavourable progression. Our analysis included transgenic mouse models overexpressing NCAPH and a genetically diverse mouse cohort generated by backcrossing. A least absolute shrinkage and selection operator (LASSO) multivariate regression analysis was performed on transcripts associated with elevated intratumoural NCAPH levels. We found that NCAPH contributes to adverse luminal A breast cancer progression. The intratumoural gene expression signature associated with elevated NCAPH levels emerged as a potential risk identifier. Transgenic mice overexpressing NCAPH developed breast tumours with extended latency, and in Mouse Mammary Tumor Virus (MMTV)-NCAPH ErbB2 double-transgenic mice, luminal tumours showed increased aggressiveness. High intratumoural Ncaph levels correlated with worse breast cancer outcome and subpar chemotherapy response. A 10-gene risk score, termed Gene Signature for Luminal A 10 (GSLA10), was derived from the LASSO analysis, correlating with adverse luminal A breast cancer progression. The GSLA10 signature outperformed the Oncotype DX signature in discerning tumours with unfavourable outcomes, previously categorised as luminal A by Prediction Analysis of Microarray 50 (PAM50) across three independent human cohorts. This new signature holds promise for identifying luminal A tumour patients with adverse prognosis, aiding in the development of personalised treatment strategies to significantly improve patient outcomes.

60 APPLIED LIFE SCIENCES↗

Mathematical modeling in cancer nanomedicine: a review

Cancer continues to be among the leading healthcare problems worldwide, and efforts continue not just to find better drugs, but also better drug delivery methods. The need for delivering cytotoxic agents selectively to cancerous cells, for improved safety and efficacy, has triggered the application of nanotechnology in medicine. This effort has provided drug delivery systems that can potentially revolutionize cancer treatment. Nanocarriers, due to their capacity for targeted drug delivery, can shift the balance of cytotoxicity from healthy to cancerous cells. The field of cancer nanomedicine has made significant progress, but challenges remain that impede its clinical translation. Several biophysical barriers to the transport of nanocarriers to the tumor exist, and a much deeper understanding of nano-bio interactions is necessary to change the status quo. Mathematical modeling has been instrumental in improving our understanding of the physicochemical and physiological underpinnings of nanomaterial behavior in biological systems. Here, we present a comprehensive review of literature on mathematical modeling works that have been and are being employed towards a better understanding of nano-bio interactions for improved tumor delivery efficacy.

60 APPLIED LIFE SCIENCES↗

Analysis of tumor-immune functional responses in a mathematical model of neoantigen cancer vaccines

Cancer neoantigen vaccines have emerged as a promising approach to stimulating the immune system to fight cancer. We propose a simple model including key elements of cancer-immune interactions and conduct a phase plane analysis to understand the immunological mechanisms of cancer neoantigen vaccines. Analytical results are obtained for two widely used functional forms that represent the killing rate of tumor cells by immune cells: the law of mass action (LMA) and the dePillis-Radunskaya Law (LPR). Using the LMA, our results reveal that a slowly growing tumor can escape the immune surveillance and that there is a unique periodic solution. The LPR offers richer dynamics, in which tumor elimination and uncontrolled tumor growth are both present. We show that tumor elimination requires sufficient number of initial activated T cells in relationship to the malignant cells, which lends support to using the neoantigen cancer vaccine as an adjuvant therapy after the primary tumor is surgically removed or treated using radiotherapy. We also derive a sufficient condition for uncontrolled tumor growth under the assumption of the LPR. Here, the juxtaposition of analyses with these two different choices for the killing rate function highlights their importance on model behavior and biological implications, by which we hope to spur further theoretical and experimental work to understand mechanisms underlying different functional forms for the killing rate.

60 APPLIED LIFE SCIENCES↗

OvAd1, a Novel, Potent, and Selective Chimeric Oncolytic Virus Developed for Ovarian Cancer by 3D-Directed Evolution

Effective therapeutics for ovarian cancer continue to be urgently needed, particularly for chemotherapy-resistant cases. Here we present both a 3D-Matrigel culture-based expansion of our directed evolution method for generation of oncolytic virotherapies and two promising ovarian-cancer targeted oncolytic viruses, OvAd1 and OvAd2. OvAd1 was developed using Matrigel cell cultures, whereas OvAd2 was developed in parallel using traditional monolayer tissue culture methods. Both viruses are potent against a panel of platinum-resistant ovarian cancer cell lines and are attenuated on normal cells in vitro, resulting in therapeutic windows of ~200-fold. We observed two benefits of the use of Matrigel-based cultures for directed evolution of these oncolytics: (1) use of Matrigel generated a bioselected pool that was more strongly attenuated on normal cells while retaining its potency against ovarian cancer cells, and (2) in an ovarian carcinomatosis model, the Matrigel-derived virus OvAd1 suppressed all tumor growth while the non-Matrigelderived virus was 50% effective. Neither virus stimulated formation of peritoneal adhesions as seen for Ad5-based therapies. Consequently, these viruses are novel candidates for development as new effective treatments for aggressive ovarian cancer.

3D cell culture↗

Logic-based analysis of gene expression data predicts association between TNF, TGFB1 and EGF pathways in basal-like breast cancer

For breast cancer, clinically important subtypes are well characterized at the molecular level in terms of gene expression profiles. In addition, signaling pathways in breast cancer have been extensively studied as therapeutic targets due to their roles in tumor growth and metastasis. However, it is challenging to put signaling pathways and gene expression profiles together to characterize biological mechanisms of breast cancer subtypes since many signaling events result from post-translational modifications, rather than gene expression differences. We designed a logic-based computational framework to explain the differences in gene expression profiles among breast cancer subtypes using Pathway Logic and transcriptional network information. Pathway Logic is a rewriting-logic-based formal system for modeling biological pathways including post-translational modifications. Our method demonstrated its utility by constructing subtype-specific path from key receptors (TNFR, TGFBR1 and EGFR) to key transcription factor (TF) regulators (RELA, ATF2, SMAD3 and ELK1) and identifying potential association between pathways via TFs in basal-specific paths, which could provide a novel insight on aggressive breast cancer subtypes. Lastly, codes and results are available at http://epigenomics.snu.ac.kr/PL/.

59 BASIC BIOLOGICAL SCIENCES↗

Structure-Based Optimization of a Novel Class of Aldehyde Dehydrogenase 1A (ALDH1A) Subfamily-Selective Inhibitors as Potential Adjuncts to Ovarian Cancer Chemotherapy

Aldehyde dehydrogenase (ALDH) activity is commonly used as a marker to identify cancer stem-like cells. The three ALDH1A isoforms have all been individually implicated in cancer stem-like cells and in chemoresistance; however, which isoform is preferentially expressed varies between cell lines. In this work, we sought to explore the structural determinants of ALDH1A isoform selectivity in a series of small-molecule inhibitors in support of research into the role of ALDH1A in cancer stem cells. An SAR campaign guided by a cocrystal structure of the HTS hit CM39 (7) with ALDH1A1 afforded first-in-class inhibitors of the ALDH1A subfamily with excellent selectivity over the homologous ALDH2 isoform. We also discovered the first reported modestly selective single isoform 1A2 and 1A3 inhibitors. Two compounds, 13g and 13h, depleted the CD133+ putative cancer stem cell pool, synergized with cisplatin, and achieved efficacious concentrations in vivo following IP administration. Compound 13h additionally synergized with cisplatin in a patient-derived ovarian cancer spheroid model.

60 APPLIED LIFE SCIENCES↗

Discovery of Potent Myeloid Cell Leukemia-1 (Mcl-1) Inhibitors That Demonstrate in Vivo Activity in Mouse Xenograft Models of Human Cancer

Overexpression of myeloid cell leukemia-1 (Mcl-1) in cancers correlates with high tumor grade and poor survival. Further, Mcl-1 drives intrinsic and acquired resistance to many cancer therapeutics, including B cell lymphoma 2 family inhibitors, proteasome inhibitors, and antitubulins. Therefore, Mcl-1 inhibition could serve as a strategy to target cancers that require Mcl-1 to evade apoptosis. Herein, we describe the use of structure-based design to discover a novel compound (42) that robustly and specifically inhibits Mcl-1 in cell culture and animal xenograft models. Compound 42 binds to Mcl-1 with picomolar affinity and inhibited growth of Mcl-1-dependent tumor cell lines in the nanomolar range. Compound 42 also inhibited the growth of hematological and triple negative breast cancer xenografts at well-tolerated doses. These findings highlight the use of structure-based design to identify small molecule Mcl-1 inhibitors and support the use of 42 as a potential treatment strategy to block Mcl-1 activity and induce apoptosis in Mcl-1-dependent cancers.

60 APPLIED LIFE SCIENCES↗

Poly( N -vinylpyrrolidone)- block -Poly(dimethylsiloxane)- block -Poly( N -vinylpyrrolidone) Triblock Copolymer Polymersomes for Delivery of PARP1 siRNA to Breast Cancers

Nearly 20% of HER2-positive breast cancers develop resistance to HER2-targeted therapies requiring the use of advanced therapies. Silencing RNA therapy may be a powerful modality for treating resistant HER2 cancers due to its high specificity and low toxicity. However, the systemic administration of siRNAs requires a safe and efficient delivery platform because of siRNA’s low stability in physiological fluids, inefficient cellular uptake, immunoreactivity, and rapid clearance. We have developed theranostic polymeric vesicles to overcome these hurdles for encapsulation and delivery of small functional molecules and PARP1 siRNA for in vivo delivery to breast cancer tumors. The 100 nm polymer vesicles were assembled from biodegradable and non-ionic poly(N-vinylpyrrolidone) 14 -block-poly(dimethylsiloxane) 47 -block-poly(N-vinylpyrrolidone) 14 triblock copolymer PVPON 14 -PDMS 47 -PVPON 14 using nanoprecipitation and thin-film hydration. We demonstrated that the vesicles assembled from the copolymer covalently tagged with the Cy5.5 fluorescent dye for in vivo imaging could also encapsulate the model drug with high loading efficiency (40%). The dye-loaded vesicles were accumulated in tumors after 18 h circulation in 4TR breast tumor-bearing mice via passive targeting. We found that PARP1 siRNA encapsulated into the vesicles was released intact (13%) into solution by the therapeutic ultrasound treatment as quantified by gel electrophoresis. Additionally, the PARP1 siRNA-loaded polymersomes inhibited the proliferation of MDA-MB-361TR cells by 34% after 6 days of treatment by suppressing the NF-kB signaling pathway, unlike their scrambled siRNA-loaded counterparts. Finally, the treatment by PARP1 siRNA-loaded vesicles prolonged the survival of the mice bearing 4T1 breast cancer xenografts, with the 4-fold survival increase, unlike the untreated mice after 3 weeks following the treatment. These biodegradable, non-ionic PVPON 14 -PDMS 47 -PVPON 14 polymeric nanovesicles capable of the efficient encapsulation and delivery of PARP1 siRNA to successfully knock down PARP1 in vivo can provide an advanced platform for the development of precision-targeted therapeutic carriers, which could help develop highly effective drug delivery nanovehicles for breast cancer gene therapy.

60 APPLIED LIFE SCIENCES↗

Superhydrophobic Array Devices for the Enhanced Formation of 3D Cancer Models

During the metastatic cascade, cancer cells travel through the bloodstream as circulating tumor cells (CTCs) to a secondary site. Clustered CTCs have greater shear stress and treatment resistance, yet their biology remains poorly understood. We therefore engineered a tunable superhydrophobic array device (SHArD). The SHArD-C was applied to culture a clinically relevant model of CTC clusters. Using our device, we cultured a model of cancer cell aggregates of various sizes with immortalized cancer cell lines. These exhibited higher E-cadherin expression and are significantly more capable of surviving high fluid shear stress-related forces compared to single cells and model clusters grown using the control method, helping to explain why clustering may provide a metastatic advantage. Additionally, the SHArD-S, when compared with the AggreWell 800 method, provides a more consistent spheroid-forming device culturing reproducible sizes of spheroids for multiple cancer cell lines. Overall, we designed, fabricated, and validated an easily tunable engineered device which grows physiologically relevant three-dimensional (3D) cancer models containing tens to thousands of cells.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Survival analysis of localized prostate cancer with deep learning

In recent years, data-driven, deep-learning-based models have shown great promise in medical risk prediction. By utilizing the large-scale Electronic Health Record data found in the U.S. Department of Veterans Affairs, the largest integrated healthcare system in the United States, we have developed an automated, personalized risk prediction model to support the clinical decision-making process for localized prostate cancer patients. This method combines the representative power of deep learning and the analytical interpretability of parametric regression models and can implement both time-dependent and static input data. To collect a comprehensive evaluation of model performances, we calculate time-dependent C-statistics C td over 2-, 5-, and 10-year time horizons using either a composite outcome or prostate cancer mortality as the target event. The composite outcome combines the Prostate-Specific Antigen (PSA) test, metastasis, and prostate cancer mortality. Our longitudinal model Recurrent Deep Survival Machine (RDSM) achieved C td 0.85 (0.83), 0.80 (0.83), and 0.76 (0.81), while the cross-sectional model Deep Survival Machine (DSM) attained C td 0.85 (0.82), 0.80 (0.82), and 0.76 (0.79) for the 2-, 5-, and 10-year composite (mortality) outcomes, respectively. In addition to estimating the survival probability, our method can quantify the uncertainty associated with the prediction. The uncertainty scores show a consistent correlation with the prediction accuracy. We find PSA and prostate cancer stage information are the most important indicators in risk prediction. Our work demonstrates the utility of the data-driven machine learning model in prostate cancer risk prediction, which can play a critical role in the clinical decision system.

60 APPLIED LIFE SCIENCES↗