Machine Learning in Prediction of Second Primary Cancer and Recurrence in Colorectal Cancer.

BACKGROUND: Colorectal cancer (CRC) is the third commonly diagnosed cancer worldwide. Recurrence of CRC (Re) and onset of a second primary malignancy (SPM) are important indicators in treating CRC, but it is often difficult to predict the onset of a SPM. Therefore, we used mechanical learning to identify risk factors that affect Re and SPM. PATIENT AND METHODS: CRC patients with cancer registry database at three medical centers were identified. All patients were classified based on Re or no recurrence (NRe) as well as SPM or no SPM (NSPM). Two classifiers, namely A Library for Support Vector Machines (LIBSVM) and Reduced Error Pruning Tree (REPTree), were applied to analyze the relationship between clinical features and Re and/or SPM category by constructing optimized models. RESULTS: When Re and SPM were evaluated separately, the accuracy of LIBSVM was 0.878 and that of REPTree was 0.622. When Re and SPM were evaluated in combination, the precision of models for SPM+Re, NSPM+Re, SPM+NRe, and NSPM+NRe was 0.878, 0.662, 0.774, and 0.778, respectively. CONCLUSIONS: Machine learning can be used to rank factors affecting tumor Re and SPM. In clinical practice, routine checkups are necessary to ensure early detection of new tumors. The success of prediction and early detection may be enhanced in the future by applying "big data" analysis methods such as machine learning.

Gallic acid inhibits gastric cancer cells metastasis and invasive growth via increased expression of RhoB, downregulation of AKT/small GTPase signals and inhibition of NF-κB activity.

Our previous study demonstrated the therapeutic potential of gallic acid (GA) for controlling tumor metastasis through its inhibitory effect on the motility of AGS cells. A noteworthy finding in our previous experiment was increased RhoB expression in GA-treated cells. The aim of this study was to evaluate the role of RhoB expression on the inhibitory effects of GA on AGS cells. By applying the transfection of RhoB siRNA into AGS cells and an animal model, we tested the effect of GA on inhibition of tumor growth and RhoB expression. The results confirmed that RhoB-siRNA transfection induced GA to inhibit AGS cells' invasive growth involving blocking the AKT/small GTPase signals pathway and inhibition of NF-κB activity. Finally, we evaluated the effect of GA on AGS cell metastasis by colonization of tumor cells in nude mice. It showed GA inhibited tumor cells growth via the expression of RhoB. These data support the inhibitory effect of GA which was shown to inhibit gastric cancer cell metastasis and invasive growth via increased expression of RhoB, downregulation of AKT/small GTPase signals and inhibition of NF-κB activity. Thus, GA might be a potential agent in treating gastric cancer.

Anti-metastasis effects of gallic acid on gastric cancer cells involves inhibition of NF-kappaB activity and downregulation of PI3K/AKT/small GTPase signals.

Polyphenols are natural antioxidants that are thought to contribute to prevention of cardiovascular disease and malignancy. Although many studies have been carried out to investigate the chemopreventive role of flavonoids, less attention has been focused on phenolic acids. In this study, the aim was to investigate the effect of phenolic acids found abundantly in vegetables, i.e. gallic acid (GA), caffeic acid (CA) and protocatechuic acid (PCA), on the inhibition of gastric adenocarcinoma (AGS) cell metastasis. The results showed 0.01 mM GA induced the same level of cell toxicity as 4.0mM PCA. Using wound-healing assay and Boyden chamber assay, GA had potent inhibitory effects on AGS cell migration. The expression of MMP-2/9 of AGS cells was inhibited by 2.0 microM of GA. It is possible that the suppressive effect of GA on MMP-2/9 might involve the inhibition of NF-kappaB activity. Multiple proteins involved in metastasis and the cytoskeletal reorganization signal pathway, including Ras, Cdc42, Rac1, RhoA, RhoB, PI3K and p38MAPK, were also inhibited by GA. Furthermore, immunoreactivity assay of cytoskeletal F-actin demonstrated a significant inhibitory effect of GA treatment. In conclusion, GA may have the potential to be an effective agent for prevention and treatment of gastric cancer metastasis.

The etiology and clinical characteristics of acute lower gastrointestinal bleeding in patients hospitalized for comorbid illnesses.

BACKGROUND/AIMS: To determine whether there are different causes of acute lower gastrointestinal bleeding and different clinical courses in patients (a) with comorbid illnesses vs. (b) patients with only severe hematochezia. METHODOLOGY: From January 2001 to December 2003, 107 hospitalized patients with acute lower gastrointestinal bleeding were evaluated by urgent colonoscopy. Our analyses compared the etiology and clinical characteristics of bleeding in patients with (group A) and without (group B) one or more comorbid illnesses. RESULTS: Group A patients tended to have longer hospital stays, more severe anemic conditions, and more transfusion requirements. The overall mortality rate was 29.5% in group A and 4.3% in group B (p < 0.05). Bleeding-related mortality was not significantly different between groups. Colitis, rectal ulcer, and angiodysplasia were the leading causes of lower gastrointestinal bleeding in group A. Rectal ulcer was a more common cause of bleeding in group A (16.4%) than in group B (2.1%) (p < 0.05), and it resulted in longer hospital stays and more severe anemia and leukocytosis compared to patients with other causes of lower gastrointestinal bleeding. CONCLUSIONS: Patients with acute lower gastrointestinal bleeding that starts after hospitalization for other comorbid illnesses have distinctive etiologies and clinical characteristics compared with ordinary patients admitted to the hospital with only bleeding. Rectal ulcer is an important but obscure cause of acute lower gastrointestinal bleeding in elderly patients with significant comorbid diseases.

Bedside colonoscopy for critically ill patients with acute lower gastrointestinal bleeding.

OBJECTIVE: To determine the clinical impact of bedside colonoscopy for critically ill patients with acute lower gastrointestinal (GI) bleeding. DESIGN AND SETTING: A 3-year retrospective analysis (chart review). Medical intensive care unit (ICU) of a 1,312-bed tertiary-care center in Taiwan. PATIENTS AND PARTICIPANTS: Fifty-five people undergoing bedside colonoscopy for lower GI bleeding that developed while in the ICU. INTERVENTIONS: Bedside colonoscopy. MEASUREMENTS AND RESULTS: Colonoscopy was successful in diagnosing the source of bleeding in 37 patients. Among them, colitis (15 patients, including ischemic, pseudomembranous, or radiation-induced) and acute hemorrhagic rectal ulcer (nine patients) were the most frequent confirmed causes. In seven patients, fresh blood was noticed above the colonoscopically accessible area and considered to originate from the small bowel. No adverse event was associated with colonoscopy. Spontaneous cessation of bleeding was noted in 29 (29/55, 53%) patients, whereas 16 (16/55, 29%) achieved endoscopic hemostasis. Ten (10/55, 18%) patients failed primary hemostasis or localization. Overall in-hospital mortality was 53% (29/55); however, hemorrhage-related death occurred in only two patients. CONCLUSIONS: ICU patients with acute lower GI bleeding have distinctive causes. Bedside colonoscopy is effective for diagnosis in two-thirds of patients, but only a minority of them needs endoscopic hemostasis.