Machine learning approaches for predicting 5-year breast cancer survival: A multicenter study.

The study used clinical data to develop a prediction model for breast cancer survival. Breast cancer prognostic factors were explored using machine learning techniques. We conducted a retrospective study using data from the Taipei Medical University Clinical Research Database, which contains electronic medical records from three affiliated hospitals in Taiwan. The study included female patients aged over 20 years who were diagnosed with primary breast cancer and had medical records in hospitals between January 1, 2009 and December 31, 2020. The data were divided into training and external testing datasets. Nine different machine learning algorithms were applied to develop the models. The performances of the algorithms were measured using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1-score. A total of 3914 patients were included in the study. The highest AUC of 0.95 was observed with the artificial neural network model (accuracy, 0.90; sensitivity, 0.71; specificity, 0.73; PPV, 0.28; NPV, 0.94; and F1-score, 0.37). Other models showed relatively high AUC, ranging from 0.75 to 0.83. According to the optimal model results, cancer stage, tumor size, diagnosis age, surgery, and body mass index were the most critical factors for predicting breast cancer survival. The study successfully established accurate 5-year survival predictive models for breast cancer. Furthermore, the study found key factors that could affect breast cancer survival in Taiwanese women. Its results might be used as a reference for the clinical practice of breast cancer treatment.

SMAD3 Hypomethylation as a Biomarker for Early Prediction of Colorectal Cancer.

The incidence and mortality rates of colorectal cancer (CRC) have been high in recent years. Prevention and early detection are crucial for decreasing the death rate. Therefore, this study aims to characterize the alteration patterns of mothers against decapentaplegic homolog 3 (SMAD3) in patients with CRC and its applications in early detection by using a genome-wide methylation array to identify an aberrant hypomethylation site in the intron position of the SMAD3 gene. Quantitative methylation-specific polymerase chain reaction showed that hypomethylated SMAD3 occurred in 91.4% (501/548) of Taiwanese CRC tissues and 66.6% of benign tubular adenoma polyps. In addition, SMAD3 hypomethylation was observed in 94.7% of patients with CRC from The Cancer Genome Atlas dataset. A decrease in circulating cell-free methylation SMAD3 was detected in 70% of CRC patients but in only 20% of healthy individuals. SMAD3 mRNA expression was low in 42.9% of Taiwanese CRC tumor tissues but high in 29.4% of tumors compared with paired adjacent normal tissues. Hypomethylated SMAD3 was found in cancers of the digestive system, such as liver cancer, gastric cancer, and colorectal cancer, but not in breast cancer, endometrial cancer, and lung cancer. In conclusion, SMAD3 hypomethylation is a potential diagnostic marker for CRC in Western and Asian populations.

Photoluminescence of self-assembled InAs quantum dots embedded in photonic crystal nanocavities with shifted air holes.

This study investigates the photoluminescence for self-assembled InAs quantum dots embedded in photonic crystal nanocavities as two of the air holes nearest the H1 cavity were shifted. A rapid decrease of resonant wavelength and quality factor for the cavity modes, in which the electric field patterns extended in the shifting direction, were found as the shift increased from 0.2 to 0.4 lattice constants. This phenomenon is interpreted as being caused by the formation of two point defects between the nearest and second nearest air holes.