Anthony Nguyen

Context: Resveratrol exhibits colon cancer prevention activity in animal models; it is purported to have this activity in humans and inhibit a key signaling pathway involved in colon cancer initiation, the Wnt pathway, in vitro . Design: A phase I pilot study in patients with colon cancer was performed to evaluate the effects of a low dose of plant-derived resveratrol formulation and resveratrol-containing freeze-dried grape powder (GP) on Wnt signaling in the colon. Eight patients were enrolled and normal colonic mucosa and colon cancer tissue were evaluated by Wnt pathway-specific microarray and quantitative real-time polymerase chain reaction (qRT-PCR) pre- and post-exposure to resveratrol/GP. Results: Based on the expression of a panel of Wnt target genes, resveratrol/GP did not inhibit the Wnt pathway in colon cancer but had significant (p < 0.03) activity in inhibiting Wnt target gene expression in normal colonic mucosa. The greatest effect on Wnt target gene expression was seen following ingestion of 80 g of GP per day (p < 0.001). These results were confirmed with qRT-PCR of cyclinD1 and axinII . The inhibitory effect of GP on Wnt signal throughput was confirmed in vitro with a normal colonic mucosa-derived cell line. Conclusions: These data suggest that GP, which contains low dosages of resveratrol in combination with other bioactive components, can inhibit the Wnt pathway in vivo and that this effect is confined to the normal colonic mucosa. Further study of dietary supplementation with resveratrol-containing foods such as whole grapes or GP as a potential colon cancer preventive strategy is warranted. Trial registration: NCT00256334. Keywords: resveratrol, clinical trial, colon cancer, Wnt signaling, grapes, cancer prevention

OBJECTIVE: To classify automatically lung tumor-node-metastases (TNM) cancer stages from free-text pathology reports using symbolic rule-based classification. DESIGN: By exploiting report substructure and the symbolic manipulation of systematized nomenclature of medicine-clinical terms (SNOMED CT) concepts in reports, statements in free text can be evaluated for relevance against factors relating to the staging guidelines. Post-coordinated SNOMED CT expressions based on templates were defined and populated by concepts in reports, and tested for subsumption by staging factors. The subsumption results were used to build logic according to the staging guidelines to calculate the TNM stage. MEASUREMENTS: The accuracy measure and confusion matrices were used to evaluate the TNM stages classified by the symbolic rule-based system. The system was evaluated against a database of multidisciplinary team staging decisions and a machine learning-based text classification system using support vector machines. RESULTS: Overall accuracy on a corpus of pathology reports for 718 lung cancer patients against a database of pathological TNM staging decisions were 72%, 78%, and 94% for T, N, and M staging, respectively. The system's performance was also comparable to support vector machine classification approaches. CONCLUSION: A system to classify lung TNM stages from free-text pathology reports was developed, and it was verified that the symbolic rule-based approach using SNOMED CT can be used for the extraction of key lung cancer characteristics from free-text reports. Future work will investigate the applicability of using the proposed methodology for extracting other cancer characteristics and types.

ICD coding is a process of assigning the International Classification of Disease diagnosis codes to clinical/medical notes documented by health professionals (e.g. clinicians). This process requires significant human resources, and thus is costly and prone to error. To handle the problem, machine learning has been utilized for automatic ICD coding. Previous state-of-the-art models were based on convolutional neural networks, using a single/several fixed window sizes. However, the lengths and interdependence between text fragments related to ICD codes in clinical text vary significantly, leading to the difficulty of deciding what the best window sizes are. In this paper, we propose a new label attention model for automatic ICD coding, which can handle both the various lengths and the interdependence of the ICD code related text fragments. Furthermore, as the majority of ICD codes are not frequently used, leading to the extremely imbalanced data issue, we additionally propose a hierarchical joint learning mechanism extending our label attention model to handle the issue, using the hierarchical relationships among the codes. Our label attention model achieves new state-of-the-art results on three benchmark MIMIC datasets, and the joint learning mechanism helps improve the performances for infrequent codes.