Implementation of a machine learning model in acute coronary syndrome and stroke risk assessment for patients with lower urinary tract symptoms.

OBJECTIVE: The global population is aging and the burden of lower urinary tract symptoms (LUTS) is expected to increase. According to the National Health Insurance Research Database, our previous studies have showed LUTS may predispose patients to cardiovascular disease. However, it is difficult to provide a personalized risk assessment in the context of "having acute coronary syndrome (ACS) and stroke." This study aimed to develop an artificial intelligence (AI)-based prediction model for patients with LUTS. MATERIAL AND METHODS: We retrospectively reviewed the electronic medical records of 1799 patients with LUTS at Chi Mei Medical Center between January 1, 2001 and December, 31, 2018. Features with >10 cases and high correlations with outcomes were imported into six machine learning algorithms. The study outcomes included ACS and stroke. Model performances was evaluated using the area under the receiver operating characteristic curve (AUC). The model with the highest AUC was used to implement the clinical risk prediction application. RESULTS: Age, systemic blood pressure, diastolic blood pressure, creatinine, glycated hemoglobin, hypertension, diabetes mellitus and hyperlipidemia were the most relevant features that affect the outcomes. Based on the AUC, our optimal model was built using multilayer perception (AUC = 0.803) to predict ACS and stroke events within 3 years. CONCLUSION: We successfully built an AI-based prediction system that can be used as a prediction model to achieve time-saving, precise, personalized risk evaluation; it can also be used to offer warning, enhance patient adherence, early intervention and better health care outcomes.

Favorable breast cancer mortality-to-incidence ratios of countries with good human development index rankings and high health expenditures.

OBJECTIVE: Breast cancer is the most frequently diagnosed cancer among women worldwide. Mortality-to-incidence ratio (MIR) is a marker that reflects the efficacy and availability of screening interventions and treatment outcomes. MIR can be used to influence public health strategy. The association between the MIRs for breast cancer among countries with different economic statuses and health expenditure is important yet has been investigated. This study was aimed to elucidate the association between the breast cancer MIRs and the human development and health expenditure among different countries. MATERIALS AND METHODS: Cancer incidence and mortality rates were obtained from the GLOBOCAN database. The MIRs were calculated by dividing the crude rate of mortality to the incidence. Associations among the MIR and variants of human development index (HDI) and current health expenditure (CHE) in 50 countries were estimated via linear regression. RESULTS: Breast cancer had a higher incidence rate, but lower mortality rate, in developed countries (high HDI, CHE per capita, CHE/GDP), as compared with developing countries. Favorable MIRs were associated with a high HDI and high health expenditure countries (presented by high CHE per capita, and CHE/GDP) (both p < 0.001) CONCLUSION: The MIR for breast cancer is reversely correlated with the development and healthcare disparities among different countries. This implies that allocating more resources to healthcare systems for breast cancer screening and treatment can improve disease outcomes. Our report may be helpful for public health policy making.

Favorable cervical cancer mortality-to-incidence ratios of countries with good human development index rankings and high health expenditures.

BACKGROUND: Cervical cancer is highly preventable. The mortality-to-incidence ratio (MIR) is a marker that reflects the available screening interventions and clinical outcomes of cancer treatments. The association between the MIR for cervical cancer and cancer screening disparities among countries is an interesting issue but rarely investigated. The present study sought to understand the association between the cervical cancer MIR and the Human Development Index (HDI). METHODS: Cancer incidence and mortality rates were obtained from the GLOBOCAN database. The MIR was defined as the ratio of the crude mortality rate to the incidence rate. We used linear regression to analyze the correlation of MIRs with the HDI and current health expenditure (CHE) in 61 countries selected based on data quality. RESULTS: The results showed lower incidence and mortality rates and MIRs in more developed regions. In terms of regional categories, Africa had the highest incidence and mortality rates and MIRs. The incidence and mortality rates and MIRs were lowest in North America. Furthermore, favorable MIRs were correlated with a good HDI and high CHE as a percentage of gross domestic product (CHE/GDP) (both p < 0.0001). CONCLUSIONS: The MIR variation for cervical cancer is associated with the ranking of the health system and health expenditure, which further supports the role of cancer screening and treatment disparities in clinical outcomes. The promotion of cancer screening programs can reduce the cervical cancer global incidence and mortality rates and MIRs.