Faculty of Communication, Arts and Sciences
Permanent URI for this community
This community includes articles, book chapters, and conferences published by the Faculty of Communication, Arts, and Sciences faculty members.
Browse
Browsing Faculty of Communication, Arts and Sciences by Author "Al Dulaimi, Saeed Hameed Kurdi"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Application of machine learning risk prediction mathematical model in the diagnosis of Escherichia coli infection in patients with septic shock by cardiovascular color doppler ultrasound(Elsevier B.V., 2021-07) Shen, Hualiang; Hu, Yinfeng; Liu, Xiatian; Jiang, Zhenzhen; Ye, Hongwei; Takshe, Aseel A.; Al Dulaimi, Saeed Hameed Kurdithis study was to explore the diagnosis of septic shock patients with Escherichia coli (E. coli) infection based on cardiovascular color Doppler ultrasound (CCDUS) images under the machine learning risk prediction mathematical model (risk prediction model). 120 septic shock patients with Escherichia coli (E. coli) infection, admitted to xxx hospital were selected as research subjects, and they were randomly divided into experimental group and control group, including 76 males and 44 females, with an average age of (45.47 ± 11.35) years old. The prediction model, random forest mathematical model (RF model), and feature combination were trained and applied in the CCDUS. The error rate, F1-score, and area under the curve (AUC) were compared. It was found that the prediction effect of the risk prediction model was better (P < 0.05). The receiver operating characteristic curve (ROC) was drawn based on the risk prediction model, and it was found that the AUC was 0.924, and the best cutoff value was 0.247. The consistency test between the predicted death result and the actual result showed that Kappa = 0.824, which was higher than 0.75. The pathogenic microorganisms of the patients were mainly Gram-positive bacteria (GPB) in 32 cases (53.33%). There were 19 cases whose pathogenic bacteria was E. coli, and 11 cases (57.9%) of which were acquired in the intensive care unit (ICU). The patient mortality rate was 41.67%. Finally, the acute physiology and chronic health II (APACH II) score and D-dimer of the patients were substituted into the Logistic regression model. The effect of the risk prediction model was better than the RF model and feature combination; the measurement results based on the risk prediction model had good consistency; the D-dimer and APACH II score were independent factors for death of the septic shock. © 2021 The Author(s)Item Postoperative drug-resistant bacteria infection in patients with acute Stanford type A aortic dissection under two-fluid numerical simulation model(Elsevier B.V., 2021-07) Zang, Sheng; Zhang, Yu; Xu, Jiarui; Du, Yaming; Issa, Sahar; Al Dulaimi, Saeed Hameed KurdiObjective: This study was to investigate the characteristics and related factors of postoperative drug-resistant bacteria infection (DRBI) in patients with acute Stanford A aortic dissection (AD) (AAAD) based on a two-fluid numerical simulation model (TFNS model). Methods: 50 patients with AAAD admitted to our hospital from July 2018 to October 2020 were selected as the research objects. The patients were rolled into an infection group and a non-infection group according to whether DRBI occurred after surgery. There were 21 patients in the infected group and 29 patients in the non-infected group. The clinical data of the patients were collected, including preoperative, intraoperative, and postoperative conditions. A TFNS model was constructed. The construction of vascular physical model could be completed by the construction of fluid area and solid area. The blood flows through the fluid area and the blood vessel wall was located in the solid area. The model was adopted to study the characteristics of DRBI. The data of the patients were analyzed to explore the relationship of the multi-DRBI to intraoperative blood loss, postoperative complications, intensive care unit (ICU) stay time, invasive procedures, and use of antibiotics. In addition, the multi-factor postoperative multi-DRBI was performed with the regression analysis. Results: There was no significant difference between the infected group and the non-infected group in antibiotics used such as cephalosporin, penicillin, glycopeptide, and quinolones (P > 0.05). The time spent on antibiotics was greatly lower in the infected group than in the non-infected group (P < 0.05). The ICU stay time in the infected group was 17.78 ± 11.55, and that in the non-infected group was 6.67 ± 4.36, without notable difference between the two groups (P < 0.05). In addition, there was no significant difference between the two groups in the time to transfer to the ICU, while there was one case infected with Staphylococcus aureus, Pseudomonas aeruginosa, and Enterobacter cloacae. The excessive plasma loss (odds ratio (OR) = 3.823, 95% confidential interval (CI) = 1.643–8.897), renal insufficiency (OR = 1.855, 95% CI = 1.076–3.199), ICU stay time (OR = 5.089, 95% CI = 1.507–17.187), indwelling time of nasal feeding tube (NFT) (OR = 3.225, 95% CI = 1.332–7.807), assisted ventilation (OR = 3.077, 95% CI = 1.640–5.773), tracheal intubation (OR = 5.078, 95% CI = 1.415–18.227), tracheotomy (OR = 0.073, 95% CI = 0.013–0.382), continuous renal replacement (CRR) therapy (OR = 0.111, 95% CI = 0.023–0.476), use time of antibiotics (OR = 1.089, 95% CI = 1.038–1.143) were independent risk factors for postoperative multi-DRBI. Conclusion: postoperative multi-DRBI was characterized by Acinetobacter baumannii infection with the largest proportion, followed by Klebsiella pneumoniae; excessive plasma loss, renal insufficiency, ICU stay time, indwelling time of NFT, assisted ventilation, tracheal intubation, tracheotomy, CRR therapy, and use time of antibiotics were all independent risk factors of postoperative multi-DRBI. In the postoperative care of AAAD patients, the inducing factors had to be informed to the patient, and relative measures should be taken to prevention and treatment, which was conductive to reducing the incidence of infection and promote the recovery of AAAD. © 2021 The Author(s)Item Risk factors for diagnosis of Escherichia coli infection after flexible ureteroscope holmium laser lithotripsy by imaging information technology under Nomogram mathematical model(Elsevier B.V., 2021-06) Zhang, Yuelong; Zhang, Qi; Lv, Jia; Zhang, Dahong; Kaddouri, Meriem; Al Dulaimi, Saeed Hameed KurdiThe evaluation value of Nomogram mathematical model was investigated for risk factors of Escherichia coli infection after flexible ureteroscope holmium laser lithotripsy (f-URL) under the diagnosis of imaging information technology. A total of 124 cases with upper urinary tract calculi (UUTC) were selected as the research objects, and they were rolled into an infection group (41 cases) and a control group (83 cases) according to whether Escherichia coli infection occurred after the surgery. The difference of surgical indicators between the two groups was compared, and the Nomogram mathematical prediction model was established based on Logistic regression risk factors. Besides, the predictive ability of the Nomogram mathematical model was analyzed with indicators such as the integrated discrimination improvement (IDI), the area under the curve (AUC), and GiViTI calibration curve band. The results found that age, diabetes, stone size, surgical time, and antibiotic use time were all risk factors for Escherichia coli infection after surgery. The AUC of the different risk factors of the Nomogram mathematical model was between 0.752 and 0.814, the sensitivity was 57.45%, the specificity was 97.96%, the C-index was 0.734 (95% confidence interval (CI): 0.631–0.837). Both the 80% and 95% CI regions of the Giviti calibration curve band did not cross the 45° diagonal bisector, and P = 0.518. Moreover, the Nomogram model showed an increase of 8.9% (95% CI: 0.061–1.1874 and P = 0.043) compared with the Logistic regression analysis model. Therefore, these results indicated that the Nomogram mathematical model can markedly improve the prediction ability of Escherichia coli infection risk after f-URL, which had great value in the assessment and early diagnosis and treatment of Escherichia coli infection after f-URL. © 2021 The Authors