Which are best for successful aging prediction? Bagging, boosting, or simple machine learning algorithms?

BACKGROUND: The worldwide society is currently facing an epidemiological shift due to the significant improvement in life expectancy and increase in the elderly population. This shift requires the public and scientific community to highlight successful aging (SA), as an indicator representing the quality of elderly people's health. SA is a subjective, complex, and multidimensional concept; thus, its meaning or measuring is a difficult task. This study seeks to identify the most affecting factors on SA and fed them as input variables for constructing predictive models using machine learning (ML) algorithms. METHODS: Data from 1465 adults aged ≥ 60 years who were referred to health centers in Abadan city (Iran) between 2021 and 2022 were collected by interview. First, binary logistic regression (BLR) was used to identify the main factors influencing SA. Second, eight ML algorithms, including adaptive boosting (AdaBoost), bootstrap aggregating (Bagging), eXtreme Gradient Boosting (XG-Boost), random forest (RF), J-48, multilayered perceptron (MLP), Naïve Bayes (NB), and support vector machine (SVM), were trained to predict SA. Finally, their performance was evaluated using metrics derived from the confusion matrix to determine the best model. RESULTS: The experimental results showed that 44 factors had a meaningful relationship with SA as the output class. In total, the RF algorithm with sensitivity = 0.95 ± 0.01, specificity = 0.94 ± 0.01, accuracy = 0.94 ± 0.005, and F-score = 0.94 ± 0.003 yielded the best performance for predicting SA. CONCLUSIONS: Compared to other selected ML methods, the effectiveness of the RF as a bagging algorithm in predicting SA was significantly better. Our developed prediction models can provide, gerontologists, geriatric nursing, healthcare administrators, and policymakers with a reliable and responsive tool to improve elderly outcomes.

An evaluation of adherence to society of pharmacists' standards care in pharmacy information systems in Iran.

INTRODUCTION: Pharmacy information system (PIS) is a complex computerized system used for collecting, storing, and managing the medication therapy data in the course of patients' care. The purpose of this study was to evaluate the level of adherence to the standards established by the societies of pharmacists in the PISs employed in the hospitals in Isfahan, Iran. METHODS: The present study was an applied, descriptive-analytical study conducted on the PISs of 19 teaching, private and social insurance hospitals in Isfahan in 2011. Study population consisted of the PISs available in the hospitals under study. Study sample was the same as the study population. The data collection instrument was a self-developed checklist based on the guidelines of the American Society of Health-System Pharmacists and Pharmaceutical Society of Australia, whose validity was assessed and confirmed by expert professors' views. Having been collected by observation and interview methods, data were analyzed by SPSS 18 software using Mann-Whitney statistical test. RESULTS: The findings of the study revealed that the highest rank in adherence to the standards of societies of pharmacists was obtained by social services hospitals (32.75%), while the private hospitals obtained the lowest rank (23.32%). CONCLUSIONS: Based on the findings, in the PISs in the hospitals under study, some standards of the society of pharmacists were ignored. Hence, prior to designing and implementing PIS, a needs analysis is required to increase its users' motivation to identify the system potentialities and to allow the system development in compliance with the world technology advancement.

Effect of diet education on blood pressure changes and interdialytic weight in hemodialysis patients admitted in hajar hospital in shahrekord.

BACKGROUND AND AIM: Nutrition is a key factor in the treatment of patients with chronic kidney disease because kidney burden decrease causes uremic reduction and its side effects. The aim of this research is to examine the effect of diet education on blood pressure changes and interdialytic weight in Hemodialysis patients admitted to Hemodialysis ward of Hajar hospital in Shahrekord. METHODS: This quasi-experimental and interventional study of 100 dialysis patients referred to Hemodialysis ward of Hajar hospital was performed in a pre-test and post-test in 2011. Diet education, including face to face training with instruction booklets, were conducted in the two sessions. Having carried out the educational program, blood pressure and interdialytic weight gain were measured and recorded one month before and during three stages and after the educational program by researcher-designed checklists. The data were analyzed through SPSS 16 software by Paired t-test and ANOVA. RESULTS: The results showed that mean of primary weight of the patients increase from 66.15±15.10 to 64.43±14.67. Mean of Systolic and diastolic blood pressure in patients in three stages were reduced to 6.65±1.51 mmg 2.24±1.82 mmg respectively. There was a significant difference between the creatinine amount in patients before and after of training (p≤0.01) but no meaningful difference was observed between the BUN amount before and after of training (p≤0.031). CONCLUSION: training to patients underwent hemodialysis in order to observe diet and its effects on improvement in treatment are of significant importance.

A Survey on the Users' Satisfaction with the Hospital Information Systems (HISs) based on DeLone and McLean's Model in the Medical-Teaching Hospitals in Isfahan City.

BACKGROUND AND PURPOSE: The user's satisfaction with information system in fact denotes the extent the user is satisfied with the system's achievement in fulfilling his/her information requirements. This study tries to explore the users' satisfaction with hospital information systems (HISs) based on DeLone and McLean's model focusing on the medical-teaching hospitals of Isfahan city. METHODOLOGY: This study which was applied and descriptive-analytical in nature was carried out in the medical-teaching hospitals of Isfahan city in 2009. Research population consisted of the system users from which a sample was selected using random sampling method. The size of the sample was 228. Data collection instrument was a self-developed questionnaire produced based on the satisfaction criterion in the DeLone and McLean's model. Its content validity was assessed based on the opinions given by the computer sciences professionals with its estimated Cronbach's alpha found to be 92.2%. The data were analyzed using SPSS software. FINDINGS: As the findings of the study showed, the differences among the mean scores obtained for the satisfaction with different kinds of HISs in use in the hospitals were statistically significant (p value≤0.05). Generally, Kowsar System (old version) and Pouya Samaneh Diva system gained the highest and lowest mean scores for the criterion in question, respectively. The overall mean score for the satisfaction was 54.6% for different types of systems and 55.6% among the hospitals. CONCLUSION: Given the findings of the study, it can be argued that based on the used model, the level of users' satisfaction with the systems in question was relatively good. However, to achieve the total optimum condition, when designing the system, the factors affecting the enhancement of the users' satisfaction and the type of hospital activity and specialty must be given special consideration.

Evaluation of pharmacy information system in teaching, private and social services Hospitals in 2011.

OBJECTIVE: Supporting a therapeutic approach and medication therapy management, the pharmacy information system (PIS) acts as one of the pillars of hospital information system. This ensures that medication therapy is being supported with an optimal level of safety and quality similar to other treatments and services. MATERIALS AND METHODS: The present study is an applied, cross-sectional study conducted on the PIS in use in selected hospitals. The research population included all users of PIS. The research sample is the same as the research population. The data collection instrument was the self-designed checklist developed from the guidelines of the American Society of Health System Pharmacists, Australia pharmaceutical Society and Therapeutic guidelines of the Drug Commission of the German Medical Association. The checklist validity was assessed by research supervisors and PIS users and pharmacists. FINDINGS: The findings of this study were revealed that regarding the degree of meeting the standards given in the guidelines issued by the Society of Pharmacists, the highest rank in observing input standards belonged to Social Services hospitals with a mean score of 32.75. Although teaching hospitals gained the highest score both in process standards with a mean score of 29.15 and output standards with a mean score of 43.95, the private hospitals had the lowest mean score of 23.32, 17.78, 24.25 in input, process and output standards, respectively. CONCLUSION: Based on the findings, it can be claimed that the studied hospitals had a minimal compliance with the input, output and processing standards related to the PIS.

Effect of diet education on blood pressure changes and interdialytic weight in hemodialysis patients admitted in hajar hospital in shahrekord.

BACKGROUND AND AIM: Nutrition is a key factor in the treatment of patients with chronic kidney disease because kidney burden decrease causes uremic reduction and its side effects. The aim of this research is to examine the effect of diet education on blood pressure changes and interdialytic weight in Hemodialysis patients admitted to Hemodialysis ward of Hajar hospital in Shahrekord. METHODS: This quasi-experimental and interventional study of 100 dialysis patients referred to Hemodialysis ward of Hajar hospital was performed in a pre-test and post-test in 2011. Diet education, including face to face training with instruction booklets, were conducted in the two sessions. Having carried out the educational program, blood pressure and interdialytic weight gain were measured and recorded one month before and during three stages and after the educational program by researcher-designed checklists. The data were analyzed through Spss16 software by Paired t-test and ANOVA. RESULTS: The results showed that mean of primary weight of the patients increase from 66.15±15.10 to 64.43±14.67. Mean of Systolic and diastolic blood pressure in patients in three stages were reduced to 6.65±1.51 mmg 2.24±1.82 mmg respectively. There was a significant difference between the creatinine amount in patients before and after of training (p≤0.01) but no meaningful difference was observed between the BUN amount before and after of training (p≤0.031). CONCLUSION: Training to patients underwent hemodialysis in order to observe diet and its effects on improvement in treatment are of significant importance.

The role of evaluation pharmacy information system in management of medication related complications.

INTRODUCTION: As a natural phenomenon in the patient's medication therapy, medication clinical complications potentially or concretely interrupt medical care consequential productivity for the patients. Medication related clinical complications include drug errors, drug side effects, drug interactions and drug usage-related challenges. The present research intends to explore the role that the Pharmacy Information System (PIS) may play in the management of medication complications with reference to the pharmaceutical societies of America and Australia in selected teaching, private and social services hospitals of the city of Isfahan. METHODOLOGY: As an applied, descriptive-analytical study, this study has been conducted in teaching, private and social services hospitals situated in the city of Isfahan in 2011. The research population consisted of the PISs used in the hospitals under study. Research sample was the same as the population. The data collection instrument used was a self-designed checklist developed based on the guidelines of the American Society of Health System Pharmacists and Pharmaceutical Society of Australia validity of which was assessed by expert professors' views. The data, collected by observation and interview methods, were put into SPSS 18 software to be analyzed. FINDINGS: The findings of the study revealed that among the 19 hospitals in question, the highest and lowest ranks in observing the societies of the pharmacists' established standards related to medication therapy, i.e. registration of drug use status and drug interactions belonged to social services hospitals (mean score of %10.1) and private hospitals (mean score of %6.24), respectively. CONCLUSION: Based on the findings, it can be claimed that the hospitals in question did not pay due attention to standards established by the societies of pharmacists regarding the medication therapy including register of drug usage status, drug interactions and drug side effects in their PISs. Hence, more thought must be given to the capabilities of the PIS in supporting the medication-related decisions and drug errors management so as to promote the treatment quality and satisfy medication therapy goals.

Assessment of pharmacy information system performance in selected hospitals in isfahan city during 2011.

BACKGROUND: In supporting a therapeutic approach and medication therapy management, pharmacy information system acts as one of the central pillars of information system. This ensures that medication therapy is being supported and evaluated with an optimal level of safety and quality similar to other treatments and services. OBJECTIVES: This research aims to evaluate the performance of pharmacy information system in three types of teaching, private and social affiliated hospitals. PATIENTS AND METHODS: The present study is an applied, descriptive and analytical study which was conducted on the pharmacy information system in use in the selected hospitals. The research population included all the users of pharmacy information systems in the selected hospitals. The research sample is the same as the research population. Researchers collected data using a self-designed checklist developed following the guidelines of the American Society of Health-System Pharmacists, Australia pharmaceutical Society and Therapeutic guidelines of the Drug Commission of the German Medical Association. The checklist validity was assessed by research supervisors and pharmacy information system pharmacists and users. To collect data besides observation, the questionnaires were distributed among pharmacy information system pharmacists and users. Finally, the analysis of the data was performed using the SPSS software. RESULTS: Pharmacy information system was found to be semi-automated in 16 hospitals and automated in 3 ones. Regarding the standards in the guidelines issued by the Society of Pharmacists, the highest rank in observing the input standards belonged to the Social Services associated hospitals with a mean score of 32.75. While teaching hospitals gained the highest score both in processing standards with a mean score of 29.15 and output standards with a mean score of 43.95, and the private hospitals had the lowest mean scores of 23.32, 17.78, 24.25 in input, process and output standards respectively. CONCLUSIONS: Based on the findings, the studied hospitals had minimal compliance with the input, output and processing standards related to the pharmacy information system. It is suggested that the establishment of a team composed of operational managers, computer fields experts, health information managers, pharmacists as well as physicians may contribute to the promotion of the capabilities of pharmacy information system to be able to focus on health care practitioners' and users' requirements.