Tehran University Medical Journal

Background: Peritoneal dialysis is one of the most commonly used treatment methods for the patients with end stage renal failure. In recent years, the mortality rate of patients under this treatment has decreased; however, long-term survival is still an important challenge for health systems. The present study aimed to predict the survival of continuous ambulatory peritoneal dialysis patients.
Methods: In this retrospective study, according to the difference of relative importance of demographic characteristics, laboratory data, dialysis adequacy parameters and nutritional status in various patients, the factors affecting the survival of peritoneal dialysis patients have been identified by random forest algorithm. Then, the clinical and laboratory data of patients undergoing continuous ambulatory peritoneal dialysis treatment were evaluated retrospectively from July 1996 to April 2014 in 18 peritoneal dialysis centers, using multi-class one against all support vector machine (OAA-SVM) and multi-space mapped binary tree support vector machine (MBT-SVM) algorithms.
Results: 3097 patients were studied with the mean age of 50.63±15.67 years and average follow-up time of 24.48±19.13 months. The results of the random forest algorithm have identified 35 factors as the most important predictors of peritoneal dialysis patient’s survival. Then, the prediction of peritoneal dialysis patients’ survival status was evaluated using one against all support vector machine and multi-space mapped binary tree support vector machine algorithms in 5 classes of patients including “still on peritoneal dialysis”, “transferred to hemodialysis”, “received a kidney transplant”, “died” and “improved kidney function”. The reliability of survival prediction algorithms were 51.99% and 89.57% respectively.
Conclusion: An accurate prediction model would be a potentially useful way to evaluate patients’ survival at peritoneal dialysis that increased clinical scrutiny and timely intervention could be brought to bear. So, in this research, the multi-space mapped binary tree support vector machine algorithm has a high precision in predicting the survival of continuous ambulatory peritoneal dialysis patients considering multiple evaluation indices and different class distribution functions.

Background: Pseudomonas aeruginosa is an opportunistic pathogen and one of the important factors of hospital infection. It causes many issues such as urinary tract infections, respiratory infection in cystic fibrosis patients, and wound infection in burn patients, septicemia and meningitis. Antibiotic resistance through various mechanisms is one of the challenges for the treatment of pseudomonad-caused infections. According to the inherent and acquired capacity of this bacterium in creating resistance against the antimicrobial factors, it is very important to identify a pattern for its antibiotic resistance. The aim of this study was to deliberate the frequency of pattern antibiotic resistance of pseudomonas aeruginosa strains.
Methods: In this cross-sectional study, 200 pseudomonas aeruginosa isolations (from 86 males and 114 females) were collected from different samples such as urine, blood, wound, catheter and other samples from teaching hospitals in Zahedan City during nine-month period in 2017. After conducting biochemical tests and confirming bacterium type, based on Clinical Laboratory Standards Institute (CLSI), the antibiotic resistance of strains for 10 antibiotics was determined using disk diffusion method. In addition, the minimum inhibitory concentration of three antibiotics such as imipenem, piperacillin/tazobactam and ceftazidime were determined through E-test. The Chi-square test was used for statistical analysis through the SPSS software, version 16 (IBM SPSS, Armonk, NY, USA).
Results: Out of 200 pseudomonas aeruginosa isolations (from 86 males and 114 females), the maximum resistance was related to ciprofloxacin (37%) and gentamicin (28.5%). The minimum resistance was related to piperacillin/tazobactam (6.5%) and ceftazidime (6%). The highest separated strain was from urine sample (54%), blood sample (23.5%) and wound sample (10.5%). Additionally all strains were sensitive to colistin. In this study, the percentage of multidrug-resistance (MDR) and extensively drug-resistant (XDR) strains were investigated, which were 13% and 5.5%, respectively.
Conclusion: In this study, pseudomonas aeruginosa isolates had the lowest resistance to ceftazidime which this antibiotic could be the main treatment option. The high prevalence of MDR strains is a serious warning.