Riscos à saúde dos trabalhadores em unidade de alimentação e nutrição de um Hospital Universitário

The Food and Nutrition Units (FNU) are designed to produce food for healthy and/or sick communities and need to be done in a way to ensure the quality of foodstuffs that were produced. In these units, in the working environment, in general, there is excessive noise, heat and physical condition with many adaptations, presence of obstacles, inadequate flows, as well as the ways of the working organization may represent risks for workers health and lead to errors during production and/or distribution of food. The main goal of this study was to analyse the working processes in the Food Production Unit of the university’s hospital and identify the workers' health risk factors, using for this the knowledge of ergonomics, specifically the method of Ergonomic Work Analysis (EWA). After this analysis it was possible to develop proposals that will bring improvements to the working conditions, minimizing health risk factors during the process of meals production. It’s crucial to reassert this method considers the work activity performed in real time and highlights the importance of listening and the engagement of the workers in the changing process. It is a descriptive research with a qualitative approach. In the field research were collected demographics data, employment characteristics of the individuals (age, education, stocking sector, the total length of service and length of service in the industry) and data related to their usual work (task analysis, activity analysis and Analysis of the working environment) in the FNU. The instruments that were used in this study were document analysis, global and systematic observations and semi structured interviews in order to identify the main complaints related to those activities developed by them. The study was based on data for the analysis of Bardin, 2011, so the documents have been selected and including those that treat issues related to risks to workers' health were selected. The result of semi-structured interviews, global and systematic observations took place a confrontation of this material to the theoretical framework, held the inference and the interpretation of results the light of the knowledge of ergonomics and legislation. Issues related to the risks and the perception of workers has crafted a table showing the frequency of responses to the physical, chemical and biological and even the risk of accidents and was made a descriptive analysis. The results of this analysis indicated that the unit in question presents several problems ambience of jobs, both in terms of physical structure, but also in the organization of work. Non-conformities that leads to a favourable environment to the development of disease and injury hazards and compromising the quality of food produced. It is necessary to comply with legislation and that short, medium and long-term measures are taken to ensure the physical integrity of workers and improve the working environment.

Avaliação dos impactos do uso do sistema de gestão hospitalar no Hospital Universitário Onofre Lopes

The object of this study was motivated by the need to know the possible causes of differences in results achieved in the implementation of a Computerised Management System (CMS) in a Federal University Hospital, located in northeastern Brazil, to understand the factors that influenced the results in different groups when was used the same systems implementation methodologies. Considering the implication of managers, health professionals, other professionals involved and the existing organizational structure in the period when implantation occurred, aimed to know the perception of these people about the development of CMS in the deployment process in your group or sector and also in the organization.The methodology used in this study was the content analysis which provides a rich set of methodological tools for evaluating speeches,enabling us to discourse from the unknown analysis and subjectivity, but with scientific rigor, allowing, at the end, to understand the disparity in results in the implementation of CMS.It was used as a research tool, a semi-structured interview, which exploits a qualitative approach, as suggested by the authors. It was used the approach of the episodic interview, to be more narrative about the experiences of the interview participants in their practical experience along the CMS deployment process in the hospital.Were interviewed three groups of professional and a group of managers, all with higher education in their professions and who participated in the entire implementation process from the beginning.It followed the Bardin's methodology (2009) in all the phases of treatment and interpretation of data, where emerged three categories: the "Thought and Knowledge"; the "Practices and Changes"; the "Obtained Results". From the category "Thought and Knowledge"emerged three subcategories: the "Administrative", the "Institutional" and the "IT Knowledge". From the category "Practices and Changes" emerged three subcategories: "Reality Prior to CMS"; "The IT Project and the implementation of CMS" and "Impacts of the CMS Implementation". From the category "Results Obtained" emerged three subcategories: "Benefits Promoted by CMS", "Dissatisfaction Observed" and "Level of Use and Understanding CMS ". It was observed that the lack of integration of the sectors was a determinant problem in the implementation of CMS. The CMS implementation project was not well dimensioned and divulged in the institution. Different models of leaderships and of objectives of the sectors influenced in the course of the CMS implementation process. We can mention that an CMS should be a consolidation of organizational practices tool already institutionalized and of integration amongthe sectors and not supporting to isolated practices and personalistsfrom sectors of the institution.

Avaliação de qualidade da unidade de diálise no Hospital Universitário Onofre Lopes - HUOL

Over the years there has been a broader definition of the term health. At the same time it was found also an evolution of the concept of health care which in turn has led to changes in the approach to delivery of health services and hence in its management. In this regard, currently the nephrology services have been searching for quality technical and social need. In view of these innovations and the quest for quality, it elaborated the general objective: to develop a quality assessment protocol for dialysis service Onofre Lopes University Hospital. It is an intervention project effected through an action research, which consisted of 4 steps. Initially was identified through a literature search in scientific literature, which quality indicators would apply to a dialysis unit being selected as follows: infection rate in hemodialysis access site, microbiological control of water used for hemodialysis and Index User satisfaction. Through critical reflection on the theme researched in the previous step, it was drawn up three data collection instruments, interview form type, applied between the months of October and November 2015. In addition to the information obtained, also made up of the use of information retrieval technique. The results were organized in graphs and tables and analyzed using qualitative and exploratory technical approach. Then a reflective analysis of the data obtained and the diagnosis of reality studied was traced and confronted with the literature was performed. The data produced in this study revealed that the Dialysis Unit of HUOL is much to be desired, considering that some weaknesses have been identified in its structure. Faced with this finding have been proposed, as a contribution and aiming to guide the development of future actions, suggestions for improvement that should be implemented and monitored to be assured overcoming these difficulties, allowing an appropriate organizational restructuring, and resulting in improved service public offered. It was concluded that for hemodialysis treatment results are achieved and positive, it is necessary to have physical structure and adequate infrastructure, multidisciplinary team specialized, trained and in sufficient quantity, well designed processes for professionals to have standards to be followed decreasing the chance to err, and a risk management system to detect and control situations that endanger patient safety.

Avaliação de qualidade da unidade de diálise no Hospital Universitário Onofre Lopes - HUOL

Over the years there has been a broader definition of the term health. At the same time it was found also an evolution of the concept of health care which in turn has led to changes in the approach to delivery of health services and hence in its management. In this regard, currently the nephrology services have been searching for quality technical and social need. In view of these innovations and the quest for quality, it elaborated the general objective: to develop a quality assessment protocol for dialysis service Onofre Lopes University Hospital. It is an intervention project effected through an action research, which consisted of 4 steps. Initially was identified through a literature search in scientific literature, which quality indicators would apply to a dialysis unit being selected as follows: infection rate in hemodialysis access site, microbiological control of water used for hemodialysis and Index User satisfaction. Through critical reflection on the theme researched in the previous step, it was drawn up three data collection instruments, interview form type, applied between the months of October and November 2015. In addition to the information obtained, also made up of the use of information retrieval technique. The results were organized in graphs and tables and analyzed using qualitative and exploratory technical approach. Then a reflective analysis of the data obtained and the diagnosis of reality studied was traced and confronted with the literature was performed. The data produced in this study revealed that the Dialysis Unit of HUOL is much to be desired, considering that some weaknesses have been identified in its structure. Faced with this finding have been proposed, as a contribution and aiming to guide the development of future actions, suggestions for improvement that should be implemented and monitored to be assured overcoming these difficulties, allowing an appropriate organizational restructuring, and resulting in improved service public offered. It was concluded that for hemodialysis treatment results are achieved and positive, it is necessary to have physical structure and adequate infrastructure, multidisciplinary team specialized, trained and in sufficient quantity, well designed processes for professionals to have standards to be followed decreasing the chance to err, and a risk management system to detect and control situations that endanger patient safety.

The process of implementing a new baby-friendly hospital initiative for nurses: a grounded theory study

Maternity nursing practice is changing across Canada with the movement toward becoming “baby friendly.” The World Health Organization (WHO) recommends the Baby-Friendly Hospital Initiative (BFHI) as a standard of care in hospitals worldwide. Very little research has been conducted with nurses to explore the impact of the initiative on nursing practice. The purpose of this study, therefore, was to examine the process of implementing the BFHI for nurses. The study was carried out using Corbin and Strauss’s method of grounded theory. Theoretical sampling was employed, which resulted in recruiting and interviewing 13 registered nurses whose area of employment included neonatal intensive care, postpartum, and labour and delivery. The data analysis revealed a central category of resisting the BFHI. All of the nurses disagreed with some of the 10 steps to becoming a baby-friendly hospital as outlined by the WHO. Participants questioned the science and safety of aspects of the BFHI. Also, participants indicated that the implementation of this program did not substantially change their nursing practice. They empathized with new mothers and anticipated being collectively reprimanded by management should they not follow the initiative. Five conditions influenced their responses to the initiative, which were (a) an awareness of a pro-breastfeeding culture, (b) imposition of the BFHI, (c) knowledge of the health benefits of breastfeeding, (d) experiential knowledge of infant feeding, and (e) the belief in the autonomy of mothers to decide about infant feeding. The identified outcomes were moral distress and division between nurses. The study findings could guide decision making concerning the implementation of the BFHI.

Epidemiology of medication discrepancies upon hospital admission in children - a systematic review

Objectives: NICE/NPSA excluded children under 16 from their guidance concerning medicines reconciliation (MR) upon admission.1 Our aims and objectives of conducting the literature review was to identify the epidemiology of medication discrepancies upon admission, transfer and discharge in children, and if they require MR. Method: Six bibliographical databases (Medline, Embase, CINAHL, International Pharmaceutical Abstracts, Web of Science and Biosis Previews) and selected key words were used to find epidemiological studies on medication discrepancies in children upon hospital admission, transfer and discharge (key words included ‘medication discrepancy’; ‘medication reconciliation’; ‘hospital admission’; ‘hospital discharge’; ‘hospital transfer’); studies where the data for children could be extracted were included. Results: From the 1239 articles found (in May 2011), eight of the articles had extractable paediatric information, (five from Canada, two from USA, one from UK). Five of the studies involved discrepancies on admission, one involved discrepancies on admission and transfer, one involved discrepancies at transfer and one considered discharge. The reference point used to compare against the admission, transfer and the discharge order differed in each of the studies. Four studies used a rating scale to assess the clinical significance of the discrepancies to demonstrate the potential adverse clinical outcome of patients in the absence of clinical intervention. Two studies2 3 used a rating scale that was used in adults.4 A study of paediatric neurosurgical patients found that initial hospital prescriptions for children differed from the preadmission prescriptions in 39% of occasions and 50% of all prescribing variations had the potential to cause moderate or severe discomfort or clinical deterioration.2 A study by Coffey et al in general paediatric admissions in Canada showed 22% of patients experienced at least one discrepancy and 29% of the discrepancies had the potential to cause moderate or severe discomfort or clinical deterioration.3 By comparison an epidemiological study in discrepancies in adults on admission had 38.6% of the discrepancies identified with a potential to cause moderate or severe discomfort or clinical deterioration.4 All the studies involved small samples or specific patient groups such as medically complex patients. However all of the studies demonstrated that discrepancies occurred among paediatric populations during transitions in care settings and mentioned MR as an intervention. Conclusion: The results have shown that discrepancies of medication upon hospital admission, transfer and discharge occur regularly in children. With only one published study in the UK looking at hospital admission in children, and no published articles on the incidence and epidemiology of medication discrepancies upon hospital transfer or discharge further research is required in a wider paediatric population. Further work is also required to define the required interventions to improve practice.

Outcomes and Predictors of Mortality in Neurosurgical Patients at Mbarara Regional Referral Hospital

Background:

Knowing the scope of neurosurgical disease at Mbarara Hospital is critical for infrastructure planning, education and training. In this study, we aim to evaluate the neurosurgical outcomes and identify predictors of mortality in order to potentiate platforms for more effective interventions and inform future research efforts at Mbarara Hospital.

Methods:

This is retrospective chart review including patients of all ages with a neurosurgical disease or injury presenting to Mbarara Regional Referral Hospital (MRRH) between January 2012 to September 2015. Descriptive statistics were presented. A univariate analysis was used to obtain the odds ratios of mortality and 95% confidence intervals. Predictors of mortality were determined using multivariate logistic regression model.

Results:

A total of 1876 charts were reviewed. Of these, 1854 (had complete data and were?) were included in the analysis. The overall mortality rate was 12.75%; the mortality rates among all persons who underwent a neurosurgical procedure was 9.72%, and was 13.68% among those who did not undergo a neurosurgical procedure. Over 50% of patients were between 19 and 40 years old and the majority of were males (76.10%). The overall median length of stay was 5 days. Of all neurosurgical admissions, 87% were trauma patients. In comparison to mild head injury, closed head injury and intracranial hematoma patients were 5 (95% CI: 3.77, 8.26) and 2.5 times (95% CI: 1.64,3.98) more likely to die respectively. Procedure and diagnostic imaging were independent negative predictors of mortality (P <0.05). While age, ICU admission, admission GCS were positive predictors of mortality (P <0.05).

Conclusions:

The majority of hospital admissions were TBI patients, with RTIs being the most common mechanism of injury. Age, ICU admission, admission GCS, diagnostic imaging and undergoing surgery were independent predictors of mortality. Going forward, further exploration of patient characteristics is necessary to fully describe mortality outcomes and implement resource appropriate interventions that ultimately improve morbidity and mortality.

Characteristics of hospital-treated intentional drug overdose in Ireland and Northern Ireland

OBJECTIVES This study compared the profile of intentional drug overdoses (IDOs) presenting to emergency departments in Ireland and in the Western Trust Area of Northern Ireland between 2007 and 2012. Specifically the study aimed to compare characteristics of the patients involved, to explore the factors associated with repeated IDO and to report the prescription rates of common drug types in the population. METHODS We utilised data from two comparable registries which monitor the incidence of hospital-treated self-harm, recording data from deliberate self-harm presentations involving an IDO to all hospital emergency departments for the period 1 January 2007 to 31 December 2012. RESULTS Between 2007 and 2012 the registries recorded 56,494 self-harm presentations involving an IDO. The study showed that hospital-treated IDO was almost twice as common in Northern Ireland than in Ireland (278 vs 156/100,000, respectively). CONCLUSIONS Despite the overall difference in the rates of IDO, the profile of such presentations was remarkably similar in both countries. Minor tranquillisers were the drugs most commonly involved in IDOs. National campaigns are required to address the availability and misuse of minor tranquillisers, both prescribed and non-prescribed.

Use of analgesics in intentional drug overdose presentations to hospital before and after the withdrawal of distalgesic from the Irish market

BACKGROUND: Distalgesic, the prescription-only analgesic compound of paracetamol (325 mg) and dextropropoxyphene (32.5 mg) known as co-proxamol in the UK, was withdrawn from the Irish market as of January 2006. This study aimed to evaluate the impact of the withdrawal of distalgesic in terms of intentional drug overdose (IDO) presentations to hospital emergency departments (EDs) nationally. METHODS: A total of 42,849 IDO presentations to 37 of the 40 hospitals EDs operating in Ireland in 2003-2008 were recorded according to standardised procedures. Data on sales of paracetamol-containing drugs to retail pharmacies for the period 1998-2008 were obtained from IMS Health. RESULTS: The withdrawal of distalgesic from the Irish market resulted in an immediate reduction in sales to retail pharmacies from 40 million tablets in 2005 to 500,000 tablets in 2006 while there was a 48% increase in sales of other prescription compound analgesics. The rate of IDO presentations to hospital involving distalgesic in 2006- 2008 was 84% lower than in the three years before it was withdrawn (10.0 per 100,000). There was a 44% increase in the rate of IDO presentations involving other prescription compound analgesics but the magnitude of this rate increase was five times smaller than the magnitude of the decrease in distalgesic-related IDO presentations. There was a decreasing trend in the rate of presentations involving any paracetamol-containing drug that began in the years before the distalgesic withdrawal. CONCLUSIONS: The withdrawal of distalgesic has had positive benefits in terms of IDO presentations to hospital in Ireland and provides evidence supporting the restriction of availability of means as a prevention strategy for suicidal behaviour.

Post-cesarean Section Peritonitis at a Referral Hospital in Rwanda: Factors Associated with Maternal Morbidity and Mortality

Background: Post-cesarean section peritonitis is the leading cause of maternal morbidity and mortality at the main referral hospital in Rwanda. Published data on the management of post-cesarean section peritonitis is limited. This study examined predictors of maternal morbidity and mortality for post-cesarean peritonitis.

Methods: We performed a prospective observational cohort study at the University Teaching Hospital Kigali (CHUK) from January 1 until December 31 2015, followed by a retrospective chart review of all subjects with post-cesarean section peritonitis admitted to CHUK from January 1 until December 31, 2014. All patients admitted with the diagnosis of post-cesarean section peritonitis undergoing exploratory laparotomy at CHUK were enrolled. Patients were followed to either discharge or death. Study variables included baseline demographic/clinical characteristics, admission physical exam, intraoperative findings, and management. Data were analyzed using STATA version 14.

Results: Of the 167 patients enrolled, 81 survived without requiring hysterectomy (49%), 49 survived requiring hysterectomy (29%), and 36 died (22%). In the multivariate analysis, severe sepsis was the most significant predictor of mortality (RR=4.0 [2.2-7.7]) and uterine necrosis was the most significant predictor of hysterectomy (RR=6.3 [1.6-25.2]). There were high rates of antimicrobial resistance (AMR) among the bacterial isolates cultured from intra-abdominal pus, with 52% of bacteria resistant to third-generation cephalosporins.

Conclusions: Post-cesarean section peritonitis carries a high mortality rate in Rwanda. It is also associated with a high rate of hysterectomy. Understanding the disease process and identifying factors associated with outcomes can help guide management during admission.

A study of primary teeth restored by intracoronal restorations in children participating in an undergraduate teaching programme at Cork University Dental School and Hospital, Ireland

Aim: To study the outcomes for restored primary molar teeth; to examine outcomes in relation to tooth type involved, intracoronal restoration complexity and to the material used. Materials and methods: Design: Retrospective study of primary molar teeth restored by intracoronal restorations. A series of restored primary molar teeth for children aged 6-12 years was studied. The principal outcome measure was failure of initial restoration (re-restoration or extraction). Three hundred patient records were studied to include three equal groups of primary molar teeth restored with amalgam, composite or glass ionomer, respectively. Restorative materials, the restoration type, simple (single surface) or complex (multi-surface) restoration, and tooth notation were recorded. Subsequent interventions were examined. Data were coded and entered into a Microsoft Excel database and analysis undertaken using SPSS v.18. Statistical differences were tested using the c2 test of statistical significance. Results: Of the 300 teeth studied, 61 restoration failures were recorded with 11 of those extracted. No significant differences were found between outcomes for upper first, upper second, lower first or lower second primary molars. Outcomes for simple primary teeth restored by intracoronal restorations were significantly better than those for complex intracoronal restorations (P = 0.042). Teeth originally restored with amalgam accounted for 19.7% of the 61 failures, composite for 29.5%, while teeth restored with glass ionomer represented 50.8% of all restoration failures. The differences were significant (P = 0.012). Conclusions: The majority (79.7%) of the 300 restored primary teeth studied were successful, and 3.7% teeth were extracted. Restorations involving more than one surface had almost twice the failure rate of single surface restorations. The difference was significant. Significant differences in failure rates for the three dental materials studied were recorded. Amalgam had the lowest failure rate while the failure rate with glass ionomer was the highest.

Potential Cost-effectiveness of Early Identification of Hospital-acquired Infection in Critically Ill Patients.

RATIONALE: Limitations in methods for the rapid diagnosis of hospital-acquired infections often delay initiation of effective antimicrobial therapy. New diagnostic approaches offer potential clinical and cost-related improvements in the management of these infections. OBJECTIVES: We developed a decision modeling framework to assess the potential cost-effectiveness of a rapid biomarker assay to identify hospital-acquired infection in high-risk patients earlier than standard diagnostic testing. METHODS: The framework includes parameters representing rates of infection, rates of delayed appropriate therapy, and impact of delayed therapy on mortality, along with assumptions about diagnostic test characteristics and their impact on delayed therapy and length of stay. Parameter estimates were based on contemporary, published studies and supplemented with data from a four-site, observational, clinical study. Extensive sensitivity analyses were performed. The base-case analysis assumed 17.6% of ventilated patients and 11.2% of nonventilated patients develop hospital-acquired infection and that 28.7% of patients with hospital-acquired infection experience delays in appropriate antibiotic therapy with standard care. We assumed this percentage decreased by 50% (to 14.4%) among patients with true-positive results and increased by 50% (to 43.1%) among patients with false-negative results using a hypothetical biomarker assay. Cost of testing was set at $110/d. MEASUREMENTS AND MAIN RESULTS: In the base-case analysis, among ventilated patients, daily diagnostic testing starting on admission reduced inpatient mortality from 12.3 to 11.9% and increased mean costs by $1,640 per patient, resulting in an incremental cost-effectiveness ratio of $21,389 per life-year saved. Among nonventilated patients, inpatient mortality decreased from 7.3 to 7.1% and costs increased by $1,381 with diagnostic testing. The resulting incremental cost-effectiveness ratio was $42,325 per life-year saved. Threshold analyses revealed the probabilities of developing hospital-acquired infection in ventilated and nonventilated patients could be as low as 8.4 and 9.8%, respectively, to maintain incremental cost-effectiveness ratios less than $50,000 per life-year saved. CONCLUSIONS: Development and use of serial diagnostic testing that reduces the proportion of patients with delays in appropriate antibiotic therapy for hospital-acquired infections could reduce inpatient mortality. The model presented here offers a cost-effectiveness framework for future test development.

Measuring the impact of a quality improvement collaboration to decrease maternal mortality in a Ghanaian regional hospital.

OBJECTIVE: To evaluate the performance of a continuous quality improvement collaboration at Ridge Regional Hospital, Accra, Ghana, that aimed to halve maternal and neonatal deaths. METHODS: In a quasi-experimental, pre- and post-intervention analysis, system deficiencies were analyzed and 97 improvement activities were implemented from January 2007 to December 2011. Data were collected on outcomes and implementation rates of improvement activities. Severity-adjustment models were used to calculate counterfactual mortality ratios. Regression analysis was used to determine the association between improvement activities, staffing, and maternal mortality. RESULTS: Maternal mortality decreased by 22.4% between 2007 and 2011, from 496 to 385 per 100000 deliveries, despite a 50% increase in deliveries and five- and three-fold increases in the proportion of pregnancies complicated by obstetric hemorrhage and hypertensive disorders of pregnancy, respectively. Case fatality rates for obstetric hemorrhage and hypertensive disorders of pregnancy decreased from 14.8% to 1.6% and 3.1% to 1.1%, respectively. The mean implementation score was 68% for the 97 improvement processes. Overall, 43 maternal deaths were prevented by the intervention; however, risk severity-adjustment models indicated that an even greater number of deaths was averted. Mortality reduction was correlated with 26 continuous quality improvement activities, and with the number of anesthesia nurses and labor midwives. CONCLUSION: The implementation of quality improvement activities was closely correlated with improved maternal mortality.

Walking in hospital is associated with a shorter length of stay in older medical inpatients

Evidence suggests that inactivity during a hospital stay is associated with poor health outcomes in older medical inpatients. We aimed to estimate the associations of average daily step-count (walking) in hospital with physical performance and length of stay in this population. Medical in-patients aged ⩾65 years, premorbidly mobile, with an anticipated length of stay ⩾3 d, were recruited. Measurements included average daily step-count, continuously recorded until discharge, or for a maximum of 7 d (Stepwatch Activity Monitor); co-morbidity (CIRS-G); frailty (SHARE F-I); and baseline and end-of-study physical performance (short physical performance battery). Linear regression models were used to estimate associations between step-count and end-of-study physical performance or length of stay. Length of stay was log transformed in the first model, and step-count was log transformed in both models. Similar models were used to adjust for potential confounders. Data from 154 patients (mean 77 years, SD 7.4) were analysed. The unadjusted models estimated for each unit increase in the natural log of stepcount, the natural log of length of stay decreased by 0.18 (95% CI −0.27 to −0.09). After adjustment of potential confounders, while the strength of the inverse association was attenuated, it remained significant (βlog(steps) = −0.15, 95%CI −0.26 to −0.03). The back-transformed result suggested that a 50% increase in step-count was associated with a 6% shorter length of stay. There was no apparent association between step-count and end-of-study physical performance once baseline physical performance was adjusted for. The results indicate that step-count is independently associated with hospital length of stay, and merits further investigation.

Modeling Hospital Readmissions in Dalarna County, Sweden

Unplanned hospital readmissions increase health and medical care costs and indicate lower the lower quality of the healthcare services. Hence, predicting patients at risk to be readmitted is of interest. Using administrative data of patients being treated in the medical centers and hospitals in the Dalarna County, Sweden, during 2008 – 2016 two risk prediction models of hospital readmission are built. The first model relies on the logistic regression (LR) approach, predicts correctly 2,648 out of 3,392 observed readmission in the test dataset, reaching a c-statistics of 0.69. The second model is built using random forests (RF) algorithm; correctly predicts 2,183 readmission (out of 3,366) and 13,198 non-readmission events (out of 18,982). The discriminating ability of the best performing RF model (c-statistic 0.60) is comparable to that of the logistic model. Although the discriminating ability of both LR and RF risk prediction models is relatively modest, still these models are capable to identify patients running high risk of hospital readmission. These patients can then be targeted with specific interventions, in order to prevent the readmission, improve patients’ quality of life and reduce health and medical care costs.