A full pipeline of diagnosis and prognosis the risk of chronic diseases using deep learning and Shapley values: The Ravansar county anthropometric cohort study.

Anthropometry is a Greek word that consists of the two words "Anthropo" meaning human species and "metery" meaning measurement. It is a science that deals with the size of the body including the dimensions of different parts, the field of motion and the strength of the muscles of the body. Specific individual dimensions such as heights, widths, depths, distances, environments and curvatures are usually measured. In this article, we investigate the anthropometric characteristics of patients with chronic diseases (diabetes, hypertension, cardiovascular disease, heart attacks and strokes) and find the factors affecting these diseases and the extent of the impact of each to make the necessary planning. We have focused on cohort studies for 10047 qualified participants from Ravansar County. Machine learning provides opportunities to improve discrimination through the analysis of complex interactions between broad variables. Among the chronic diseases in this cohort study, we have used three deep neural network models for diagnosis and prognosis of the risk of type 2 diabetes mellitus (T2DM) as a case study. Usually in Artificial Intelligence for medicine tasks, Imbalanced data is an important issue in learning and ignoring that leads to false evaluation results. Also, the accuracy evaluation criterion was not appropriate for this task, because a simple model that is labeling all samples negatively has high accuracy. So, the evaluation criteria of precession, recall, AUC, and AUPRC were considered. Then, the importance of variables in general was examined to determine which features are more important in the risk of T2DM. Finally, personality feature was added, in which individual feature importance was examined. Performing by Shapley Values, the model is tuned for each patient so that it can be used for prognosis of T2DM risk for that patient. In this paper, we have focused and implemented a full pipeline of Data Creation, Data Preprocessing, Handling Imbalanced Data, Deep Learning model, true Evaluation method, Feature Importance and Individual Feature Importance. Through the results, the pipeline demonstrated competence in improving the Diagnosis and Prognosis the risk of T2DM with personalization capability.

Effect of antiglaucoma agents on short-term intraocular pressure fluctuations after intravitreal bevacizumab injections.

PURPOSE: To evaluate the effect of prophylactic pressure-lowering medications on intraocular pressure (IOP) spikes after intravitreal injections (IVIs) METHODS: In this randomized double-blind clinical trial, 74 eyes that were candidates for intravitreal anti-vascular endothelial growth factor (VEGF) injection (IVI) (0.05 mL, 1.25 mg of bevacizumab) were enrolled and sorted randomly into five groups, group 1: topical timolol 0.5% (n = 16); group 2: topical brimonidin (n = 15); group 3: oral acetazolamide 250 mg (n = 14); group 4: intravenous mannitol (1.5 gr/kg) (n = 16); group 5: no intraocular pressure-lowering medication (n = 13). Medications were administered 30-60 min prior to injection. None of the patients had history of glaucoma. Intraocular pressure was measured before (baseline), 5 min after (T5), 10 min after (T10), 15 min after (T15) and 30 min after (T30) IVI using Goldmann Tonometer. RESULTS: There was a statistically significant, but relatively weak negative correlation between the amount of vitreous reflux post-IVI intraocular pressure elevation (Spearman's rho = -0.315, p = 0.006). There was no difference of the amount of vitreous reflux (P = 0.196) between study groups. The baseline mean IOP for Groups 1, 2, 3,4 and 5 were 11.19 ± 3.7, 10.07 ± 2.19, 11 ± 2.98, 10.13 ± 3.48 and12.54 ± 2.60 mmHg, respectively. (P = 0.214) There was no difference of peak IOP spike between groups at T5: 37 ± 19.7, 34.80 ± 15.76, 33.43 ± 18.29, 33.56 ± 16.88, 34.92 ± 9.99 mmHg (P = 0.977). There was also no difference of IOP at T10, T15 and T30 between study groups: P = 0.979, P = 0.994 and P = 0.692, respectively. CONCLUSION: Although it is advisable to prevent IOP spikes, our study showed that use of prophylactic pressure-lowering medications with every mechanism of action has no effect in IOP spikes following intravitreal bevacizumab injections in non-glaucomatous eyes. Trial registrationThe study was registered with clinicaltrails.gov (ID# NCT02140450). Trial registration date: 05.09.2014.