Integrating Comorbidity Knowledge for Alzheimer's Disease Drug Repurposing using Multi-task Graph Neural Network.

Alzheimer's Disease (AD) is a multifactorial disease that shares common etiologies with its multiple comorbidities, especially vascular diseases. To predict repurposable drugs for AD utilizing the relatively well-investigated comorbidities' knowledge, we proposed a multi-task graph neural network (GNN)-based pipeline that incorporates the corresponding biomedical interactome of these diseases with their genetic markers and effective therapeutics. Our pipeline can accurately capture the interactions and disease classification in the network. Next, we predicted drugs that might interact with the AD module by the node embedding similarity. Our candidates are mostly BBB permeable, and literature evidence showed their potential for treating AD pathologies, accompanying symptoms, or cotreating AD pathology and its common comorbidities. Our pipeline demonstrated a workable strategy that predicts drug candidates with current knowledge of biological interplays between AD and several vascular diseases.

Synthesize heterogeneous biological knowledge via representation learning for Alzheimer's disease drug repurposing.

Developing drugs for treating Alzheimer's disease has been extremely challenging and costly due to limited knowledge of underlying mechanisms and therapeutic targets. To address the challenge in AD drug development, we developed a multi-task deep learning pipeline that learns biological interactions and AD risk genes, then utilizes multi-level evidence on drug efficacy to identify repurposable drug candidates. Using the embedding derived from the model, we ranked drug candidates based on evidence from post-treatment transcriptomic patterns, efficacy in preclinical models, population-based treatment effects, and clinical trials. We mechanistically validated the top-ranked candidates in neuronal cells, identifying drug combinations with efficacy in reducing oxidative stress and safety in maintaining neuronal viability and morphology. Our neuronal response experiments confirmed several biologically efficacious drug combinations. This pipeline showed that harmonizing heterogeneous and complementary data/knowledge, including human interactome, transcriptome patterns, experimental efficacy, and real-world patient data shed light on the drug development of complex diseases.

Hyperpolarized Magnetic Resonance and Artificial Intelligence: Frontiers of Imaging in Pancreatic Cancer.

BACKGROUND: There is an unmet need for noninvasive imaging markers that can help identify the aggressive subtype(s) of pancreatic ductal adenocarcinoma (PDAC) at diagnosis and at an earlier time point, and evaluate the efficacy of therapy prior to tumor reduction. In the past few years, there have been two major developments with potential for a significant impact in establishing imaging biomarkers for PDAC and pancreatic cancer premalignancy: (1) hyperpolarized metabolic (HP)-magnetic resonance (MR), which increases the sensitivity of conventional MR by over 10,000-fold, enabling real-time metabolic measurements; and (2) applications of artificial intelligence (AI). OBJECTIVE: Our objective of this review was to discuss these two exciting but independent developments (HP-MR and AI) in the realm of PDAC imaging and detection from the available literature to date. METHODS: A systematic review following the PRISMA extension for Scoping Reviews (PRISMA-ScR) guidelines was performed. Studies addressing the utilization of HP-MR and/or AI for early detection, assessment of aggressiveness, and interrogating the early efficacy of therapy in patients with PDAC cited in recent clinical guidelines were extracted from the PubMed and Google Scholar databases. The studies were reviewed following predefined exclusion and inclusion criteria, and grouped based on the utilization of HP-MR and/or AI in PDAC diagnosis. RESULTS: Part of the goal of this review was to highlight the knowledge gap of early detection in pancreatic cancer by any imaging modality, and to emphasize how AI and HP-MR can address this critical gap. We reviewed every paper published on HP-MR applications in PDAC, including six preclinical studies and one clinical trial. We also reviewed several HP-MR-related articles describing new probes with many functional applications in PDAC. On the AI side, we reviewed all existing papers that met our inclusion criteria on AI applications for evaluating computed tomography (CT) and MR images in PDAC. With the emergence of AI and its unique capability to learn across multimodal data, along with sensitive metabolic imaging using HP-MR, this knowledge gap in PDAC can be adequately addressed. CT is an accessible and widespread imaging modality worldwide as it is affordable; because of this reason alone, most of the data discussed are based on CT imaging datasets. Although there were relatively few MR-related papers included in this review, we believe that with rapid adoption of MR imaging and HP-MR, more clinical data on pancreatic cancer imaging will be available in the near future. CONCLUSIONS: Integration of AI, HP-MR, and multimodal imaging information in pancreatic cancer may lead to the development of real-time biomarkers of early detection, assessing aggressiveness, and interrogating early efficacy of therapy in PDAC.

Preparing for ICD-10-CM/PCS implementation: impact on productivity and quality.

Coding productivity is expected to drop significantly during the lead-up to and in the initial stages of ICD-10-CM/PCS implementation, now expected to be delayed until October 1, 2015. This study examined the differences in coding productivity between ICD-9-CM and ICD-10-CM/PCS for hospital inpatient cases matched for complexity and severity. Additionally, interrater reliability was calculated to determine the quality of the coding. On average, coding of an inpatient record took 17.71 minutes (69 percent) longer with ICD-10-CM/PCS than with ICD-9-CM. A two-tailed T-test for statistical validity for independent samples was significant (p = .001). No coder characteristics such as years of experience or educational level were found to be a significant factor in coder productivity. Coders who had received more extensive training were faster than coders who had received only basic training. Though this difference was not statistically significant, it provides a strong indication of significant return on investment for staff training time. Coder interrater reliability was substantial for ICD-9-CM but only moderate for ICD-10-CM/PCS, though some ICD-10-CM/PCS cases had complete interrater (coder) agreement. Time spent coding a case was negatively correlated with interrater reliability (-0.425 for ICD-10-CM and -0.349 for ICD-10-PCS). This finding signals that increased time per case does not necessarily translate to higher quality. Adequate training for coders, as well as guidance regarding time invested per record, is important. Additionally, these findings indicate that previous estimates of initial coder productivity loss with ICD-10-CM/PCS may have been understated.