RESUMEN
OBJECTIVE: Colorectal cancer (CRC) is the fourth most common site for cancer death in the Republic of Korea. The aim of this study was to describe the trends of colorectal cancer mortality by region. METHODS: CRC mortality trends in Republic of Korea were described by region using a Joinpoint regression model in both sexes. The annual percent changes (APCs) were calculated for each segment. Visualization of the changes in mortality rate of colorectal cancer death rates by 16 geographic areas in both sexes between 2000-2004 and 2009-2013 were also conducted. RESULTS: CRC mortality rates of men showed decreasing trend after increase in Daegu, Gyeongsangnam-do, and Chungcheongbuk-do between 2000 and 2013 based on the joinpoint model, while Gwangju, Jeollabuk-do, Jeollanam-do, and Gyeongsangbuk-do showed increase in CRC mortality during the same period. For women, CRC mortality of Seoul, Incheon, Daejeon, and Gyeongsangnam-do started to decrease in 2005, 2003, 2007, and 2006, respectively. The mortality rate for CRC in the eastern regions, which had relatively low rates of CRC among men in 2000 through 2004, reached a level similar to that in the northwestern regions of 2009 through 2013, while the highest CRC mortality rates in women was observed in Chungcheongbuk-do. CONCLUSIONS: Reduction in CRC mortality varied across 16 metropolitan cities and provinces in men, and the visualization pattern showed that the east side of South Korea had the least progress in mortality reduction.
Asunto(s)
Neoplasias Colorrectales/mortalidad , Salud Rural/estadística & datos numéricos , Salud Urbana/estadística & datos numéricos , Adulto , Anciano , Femenino , Sistemas de Información Geográfica , Humanos , Masculino , Persona de Mediana Edad , Mortalidad/tendencias , República de Corea/epidemiología , Población Rural , Distribución por Sexo , Población UrbanaRESUMEN
The first aim of this study was to develop a prothrombin time international normalized ratio (PT INR) prediction model. The second aim was to develop a warfarin maintenance dose decision support system as a precise warfarin dosing platform. Data of 19,719 inpatients from three institutions was analyzed. The PT INR prediction algorithm included dense and recurrent neural networks, and was designed to predict the 5th-day PT INR from data of days 1-4. Data from patients in one hospital (n = 22,314) was used to train the algorithm which was tested with the datasets from the other two hospitals (n = 12,673). The performance of 5th-day PT INR prediction was compared with 2000 predictions made by 10 expert physicians. A generator of individualized warfarin dose-PT INR tables which simulated the repeated administration of varying doses of warfarin was developed based on the prediction model. The algorithm outperformed humans with accuracy terms of within ± 0.3 of the actual value (machine learning algorithm: 10,650/12,673 cases (84.0%), expert physicians: 1647/2000 cases (81.9%), P = 0.014). In the individualized warfarin dose-PT INR tables generated by the algorithm, the 8th-day PT INR predictions were within 0.3 of actual value in 450/842 cases (53.4%). An artificial intelligence-based warfarin dosing algorithm using a recurrent neural network outperformed expert physicians in predicting future PT INRs. An individualized warfarin dose-PT INR table generator which was constructed based on this algorithm was acceptable.