Artificial intelligence in healthcare: past, present and future.

Artificial intelligence (AI) aims to mimic human cognitive functions. It is bringing a paradigm shift to healthcare, powered by increasing availability of healthcare data and rapid progress of analytics techniques. We survey the current status of AI applications in healthcare and discuss its future. AI can be applied to various types of healthcare data (structured and unstructured). Popular AI techniques include machine learning methods for structured data, such as the classical support vector machine and neural network, and the modern deep learning, as well as natural language processing for unstructured data. Major disease areas that use AI tools include cancer, neurology and cardiology. We then review in more details the AI applications in stroke, in the three major areas of early detection and diagnosis, treatment, as well as outcome prediction and prognosis evaluation. We conclude with discussion about pioneer AI systems, such as IBM Watson, and hurdles for real-life deployment of AI.

[The changes in secretory function of pulmonary intravascular macrophages after challenge of lipopolysaccharide].

OBJECTIVE: To investigate the role of pulmonary intravascular macrophages (PIMs) in the pathogenesis of acute lung injury (ALI) due to infection. METHODS: Porcine pulmonary blood vessels were flushed by modified Morton method, and PIMs were isolated and cultured. The adhered PIMs were collected with adhesion method and incubated in RPMI 1640 medium. They were challenged with lipopolysaccharide (LPS, 10 mg/L). The activity of interleukin-1ß (IL-1ß), and contents of IL 6 and IL 8 in the culture supernatant were measured by method of thymocyte proliferation and enzyme linked immunoadsorbent assay (ELISA). RESULTS: The released contents of IL-1ß, IL-6 and IL-8 from PIMs were increased significantly compared with those before LPS challenge , and they peaked at 2 hours [IL-1ß activity: (10 400 ± 2 389) scintillant count/min], 4 hours [IL-6 content: (0.80 ± 0.36) µg/L], and 6 hours [IL-8 content: (4.94 ± 1.19) µg/L ] after LPS challenge , and the differences were significant compared with hose before LPS challenge [IL-1ß activity: (213 ± 85) scintillant count/min, IL-6 content: (0.27 ± 0.12) µg/L, IL-8 content: (1.84 ± 0.53) µg/L, all P <0.01]. CONCLUSION: Among the cytokines released from PIMs after LPS challenge , the increase in IL-1ß occurred earlier in comparison with that of IL-6 and IL-8, suggesting that the former might play an important role at the early stage of ALI; on the other hand, though the increase in IL-6 and IL-8 contents occurred later than that of IL- 1ß but it lasted for a longer duration, suggesting that they might be associated with the advancement of ALI. The Results also suggested that interaction of these cytokines played a more important role in the pathogenesis of ALI.