With an increased number of medical data generated every day, there is a strong need for reliable, automated evaluation tools. With high hopes and expectations, machine learning has the potential to revolutionize many fields of medicine, helping to make faster and more correct decisions and improving current standards of treatment. Today, machines can analyze, learn, communicate, and understand processed data and are used in health care increasingly. This review explains different models and the general process of machine learning and training the algorithms. Furthermore, it summarizes the most useful machine learning applications and tools in different branches of medicine and health care (radiology, pathology, pharmacology, infectious diseases, personalized decision making, and many others). The review also addresses the futuristic prospects and threats of applying artificial intelligence as an advanced, automated medicine tool.

Background: Transmembrane proteins (TMEM) constitute a large family of proteins spanning the entirety of the lipid bilayer. However, there is still a lack of knowledge about their function or mechanism of action. In this study, we analyzed the expression of selected TMEM genes in patients with head and neck squamous cell carcinoma (HNSCC) to learn their role in tumor formation and metastasis. Materials and Methods: Using TCGA data, we analyzed the expression levels of different TMEMs in both normal and tumor samples and compared those two groups depending on clinical-pathological parameters. We selected four TMEMs whose expression was highly correlated with patient survival status and subjected them to further analysis. The pathway analysis using REACTOME and the gene set enrichment analysis (GSEA) were performed to evaluate the association of those TMEMs with genes involved in hallmarks of cancer as well as in oncogenic and immune-related pathways. In addition, the fractions of different immune cell subpopulations depending on TMEM expression were estimated in analyzed patients. The results for selected TMEMs were validated using GEO data. All analyses were performed using the R package, Statistica, and Graphpad Prism. Results: We demonstrated that 73% of the analyzed TMEMs were dysregulated in HNSCC and depended on tumor localization, smoking, alcohol consumption, or HPV infection. The expression levels of ANO1, TMEM156, TMEM173, and TMEM213 correlated with patient survival. The four TMEMs were also upregulated in HPV-positive patients. The elevated expression of those TMEMs correlated with the enrichment of genes involved in cancer-related processes, including immune response. Specifically, overexpression of TMEM156 and TMEM173 was associated with immune cell mobilization and better survival rates, while the elevated ANO1 expression was linked with metastasis formation and worse survival. Conclusions: In this work, we performed a panel of in silico analyses to discover the role of TMEMs in head and neck squamous cell carcinoma. We found that ANO1, TMEM156, TMEM173, and TMEM213 correlated with clinical status and immune responses in HNSCC patients, pointing them as biomarkers for a better prognosis and treatment. This is the first study describing such the role of TMEMs in HNSCC. Future clinical trials should confirm the potential of those genes as targets for personalized therapy of HNSCC.

No abstract