Identification of diagnostic biomarkers for idiopathic pulmonary hypertension with metabolic syndrome by bioinformatics and machine learning.

Idiopathic pulmonary hypertension (IPAH) is a condition that affects various tissues and organs and the metabolic and inflammatory systems. The most prevalent metabolic condition is metabolic syndrome (MS), which involves insulin resistance, dyslipidemia, and obesity. There may be a connection between IPAH and MS, based on a plethora of studies, although the underlying pathogenesis remains unclear. Through various bioinformatics analyses and machine learning algorithms, we identified 11 immune- and metabolism-related potential diagnostic genes (EVI5L, RNASE2, PARP10, TMEM131, TNFRSF1B, BSDC1, ACOT2, SAC3D1, SLA2, P4HB, and PHF1) for the diagnosis of IPAH and MS, and we herein supply a nomogram for the diagnosis of IPAH in MS patients. Additionally, we discovered IPAH's aberrant immune cells and discuss them here.

Assessment of patients' preferences for new anticancer drugs in China: a best-worst discrete choice experiment on three common cancer types.

OBJECTIVES: Despite the advancement in anticancer drug therapies, cancer treatment decisions are often complex and preference-sensitive, making them well suited for studying shared decision-making (SDM). Our study aimed to assess preferences for new anticancer drugs among three common types of patients with cancer to inform SDM. DESIGN: We identified five attributes of new anticancer drugs and used a Bayesian-efficient design to generate choice sets for a best-worst discrete choice experiment (BWDCE). The mixed logit regression model was applied to estimate patient-reported preferences for each attribute. The interaction model was used to investigate preference heterogeneity. SETTING: The BWDCE was conducted in Jiangsu province and Hebei province in China. PARTICIPANTS: Patients aged 18 years or older, who had a definite diagnosis of lung cancer, breast cancer or colorectal cancer were recruited. RESULTS: Data from 468 patients were available for analysis. On average, the most valued attribute was the improvement in health-related quality of life (HRQoL) (p<0.001). The low incidence of severe to life-threatening side effects, prolonged progression-free survival and the low incidence of mild to moderate side effects were also positive predictors of patients' preferences (p<0.001). Out-of-pocket cost was a negative predictor of their preferences (p<0.001). According to subgroup analysis by type of cancer, the improvement in HRQoL remained the most valuable attribute. However, the relative importance of other attributes varied by type of cancer. Whether patients were newly diagnosed or previously diagnosed cancer cases played a dominant role in the preference heterogeneity within each subgroup. CONCLUSIONS: Our study can assist in the implementation of SDM by providing evidence on patients' preferences for new anticancer drugs. Patients should be informed of the multiattribute values of new drugs and encouraged to make decisions reflecting their values.

Identication and validation of cell senescence biomarkers in idiopathic pulmonary hypertension via integrated transcriptome analyses and machine learning.

BACKGROUND: Idiopathic pulmonary hypertension (IPAH) is a rare and severe disease that affects the pulmonary vasculature. As the diagnosis of IPAH requires invasive right heart catheterization surgery, early detection of this condition is notoriously challenging. Therefore, it is of utmost importance to investigate biomarkers present in peripheral blood that could aid physicians in the early identification and management of IPAH. METHOD: We speculate that cellular senescence may be involved in the occurrence and development of IPAH through various pathways. In this study, we utilized integrated transcriptome analyses and machine learning-based approach to develop a diagnostic model for IPAH cell senescence. To select genetic features, we employed two machine learning algorithms: the Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest (RF). Additionally, we validated our findings through both external data sets and qRT-PCR experiments. RESULTS: The resulting diagnostic nomogram was able to identify five important biomarkers that can aid in the diagnosis of IPAH, including TNFRSF1B, CCL16, GCLM, IL15, and SOD1. These genes are primarily associated with the immune system, as well as with cell senescence and apoptosis. CONCLUSION: Our study demonstrates the utility of machine learning algorithms in making accurate diagnoses of IPAH, providing clinicians with a more directed approach to the diagnosis and treatment of this disease.