The main difference between artificial intelligence (AI) systems and simple automated algorithms is the ability to learn, synthesize and conclude. The AI system is trained on a set of examples, including pictures, characteristics of patients with a certain disease, then it allows to generalize a lot of such examples and get some general functional dependence, which brings in line the patient data and a certain diagnosis. The system can be named intelligent if this synthetizing ability is realized. Although the AI systems are now becoming more understood and accepted by doctors, a deeper understanding of «how it works» is needed. The article provides a detailed review of the application of methods and models of artificial intelligence in the diagnostics of cancer based on the of multimodal instrumental data. The basic concepts of artificial intelligence and directions of its development are presented. From the point of view of data processing, the stages of development of AI systems are identical. The stages of intellectual processing of diagnostic data are considered in the paper. They include the acquisition and use of training databases of oncological diseases, pre-processing of images, segmentation to highlight the studied objects of diagnosis and classification of these objects to determine whether they are malignant or benign. One of the problems limiting the acceptance of AI systems development by the medical community is the imperfection of the explainability of the results obtained by intelligent systems. Authors pay attention to importance of the development of so-called explanatory intelligence, because its absence currently significantly inhibits the introduction and use of intelligent diagnostic systems in medicine. In addition, the purpose of the article is a way to develop the interaction between a radiologists and data scientists.
The study demonstrated the correlation of the neuroradiological parameters with morphological changes. The abnormality of the FA and ADC parameters in the obstructive hydrocephalus represents a significant implication for the diagnostics and management of hydrocephalus in patients.
Background
Hepatitis C (HCV) cure is associated with changes in lipids and inflammatory biomarkers but its impact on clinical endpoints among treated HIV/HCV coinfected persons is unclear.
Methods
HIV-positive persons from EuroSIDA with known HCV status after January 2001 were classified into strata based on time-updated HCV-RNA measurements and HCV treatment: HCV antibody negative, spontaneously resolved HCV, chronic untreated HCV, cured HCV (HCV-RNA-negative), HCV treatment failures (HCV-RNA-positive). Poisson regression compared incidence rates between HCV groups for end-stage liver disease (ESLD; including hepatocellular carcinoma [HCC]), non-AIDS defining malignancy (NADM; excluding HCC) and cardiovascular disease (CVD).
Results
16618 persons were included (median follow-up 8.3 (interquartile range 3.1–13.7) years). There were 887 CVD, 902 NADM and 436 ESLD events; crude incidence rates/1000 person-years follow-up (95% confidence interval [CI]) were 6.4 (6.0–6.9) CVD, 6.5 (6.1–6.9) NADM and 3.1 (2.8–3.4) ESLD. After adjustment, there were no differences in incidence rates of NADM or CVD across the five groups. HCV-negative individuals (adjusted incidence rate ratio [aIRR] 0.22 95% CI 0.14–0.34) and those with spontaneous clearance (aIRR 0.61; 95% CI 0.36–1.02) had reduced rates of ESLD compared to cured individuals. Persons with chronic untreated HCV infection (aIRR 1.47; 95% CI 1.02–2.13) or treatment failure (aIRR 1.80; 95% CI 1.22–2.66) had significantly raised rates of ESLD compared to those cured.
Conclusions
Incidence of NADM or CVD was independent of HCV group whereas those cured had a substantially lower incidence of ESLD, underlining the importance of successful HCV treatment for reducing ESLD.
Androgen assessment is a key element for diagnosing polycystic ovary syndrome (PCOS), and defining a “normal” level of circulating androgens is critical for epidemiological studies. We determined the upper normal limits (UNLs) for androgens in a population-based group of premenopausal “healthy control” women, overall and by ethnicity (Caucasian and Asian), in the cross-sectional Eastern Siberia PCOS Epidemiology and Phenotype (ESPEP) Study (СlinicalTrials.gov ID: NCT05194384) conducted in 2016–2019. Overall, we identified a “healthy control” group consisting of 143 healthy premenopausal women without menstrual dysfunction, hirsutism, polycystic ovaries, or medical disorders. We analyzed serum total testosterone (TT) by using liquid chromatography with tandem mass spectrometry (LC-MS/MS), and DHEAS, sex-hormone-binding globulin (SHBG), TSH, prolactin, and 17-hydroxyprogesterone (17OHP) were assessed with an enzyme-linked immunosorbent assay (ELISA). The UNLs for the entire population for the TT, free androgen index (FAI), and DHEAS were determined as the 98th percentiles in healthy controls as follows: 67.3 (95% confidence interval (CI): 48.1, 76.5) ng/dl, 5.4 (3.5,14.0), and 355 (289, 371) μg/dl, respectively. The study results demonstrated that the UNLs for TT and FAI varied by ethnicity, whereas the DHEAS UNLs were comparable in the ethnicities studied.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.