A comparison of machine learning algorithms in predicting COVID-19 prognostics.

ML algorithms are used to develop prognostic and diagnostic models and so to support clinical decision-making. This study uses eight supervised ML algorithms to predict the need for intensive care, intubation, and mortality risk for COVID-19 patients. The study uses two datasets: (1) patient demographics and clinical data (n = 11,712), and (2) patient demographics, clinical data, and blood test results (n = 602) for developing the prediction models, understanding the most significant features, and comparing the performances of eight different ML algorithms. Experimental findings showed that all prognostic prediction models reported an AUROC value of over 0.92, in which extra tree and CatBoost classifiers were often outperformed (AUROC over 0.94). The findings revealed that the features of C-reactive protein, the ratio of lymphocytes, lactic acid, and serum calcium have a substantial impact on COVID-19 prognostic predictions. This study provides evidence of the value of tree-based supervised ML algorithms for predicting prognosis in health care.

A system safety approach to assessing risks in the sepsis treatment process.

In healthcare, most accidents occur as a result of inadequate interactions between system components rather than component failures. In such cases traditional risk analysis methods are of limited use for analysing system safety, so methods such as Systems Theoretic Process Analysis (STPA) and the Functional Resonance Analysis Method (FRAM) have been developed. This study uses STPA to assess risks in the sepsis treatment process, discusses the potential value STPA adds and compares the results of STPA with the results of another study that used FRAM. The findings indicate that STPA and FRAM have different strengths which reflect the different scientific approaches behind these two methods. FRAM facilitates an in-depth understanding of a system, while STPA allows for more comprehensive risk analysis by identifying more risks, scenarios and safety recommendations. Nevertheless, it is reasonable to say that not only does STPA provide more comprehensive risk analysis; its terminology and philosophy are also closer to the current safety management applications employed in complex systems.

Systems approach to health service design, delivery and improvement: a systematic review and meta-analysis.

OBJECTIVES: To systematically review the evidence base for a systems approach to healthcare design, delivery or improvement. DESIGN: Systematic review with meta-analyses. METHODS: Included were studies in any patients, in any healthcare setting where a systems approach was compared with usual care which reported quantitative results for any outcomes for both groups. We searched Medline, Embase, HMIC, Health Business Elite, Web of Science, Scopus, PsycINFO and CINAHL from inception to 28 May 2019 for relevant studies. These were screened, and data extracted independently and in duplicate. Study outcomes were stratified by study design and whether they reported patient and/or service outcomes. Meta-analysis was conducted with Revman software V.5.3 using ORs-heterogeneity was assessed using I2 statistics. RESULTS: Of 11 405 records 35 studies were included, of which 28 (80%) were before-and-after design only, five were both before-and-after and concurrent design, and two were randomised controlled trials (RCTs). There was heterogeneity of interventions and wide variation in reported outcome types. Almost all results showed health improvement where systems approaches were used. Study quality varied widely. Exploratory meta-analysis of these suggested favourable effects on both patient outcomes (n=14, OR=0.52 (95% CI 0.38 to 0.71) I2=91%), and service outcomes (n=18, OR=0.40 (95% CI 0.31 to 0.52) I2=97%). CONCLUSIONS: This study suggests that a systems approaches to healthcare design and delivery results in a statistically significant improvement to both patient and service outcomes. However, better quality studies, particularly RCTs are needed.PROSPERO registration numberCRD42017065920.

The effect of cefoperazone sulbactam and piperacillin tazobactam on mortality in Gram-negative nosocomial infections.

Cefoperazone-sulbactam (CS) and piperacillin-tazobactam (TZP) are used in the treatment of Gram-negative nosocomial infections (NIs). We aimed to compare the effects of these two antibiotics on mortality and treatment success. Patients treated with CS or TZP empirically for at least three days with suspicion of NI were included in this retrospective study. In total, 308 (154 patients in both treatment arms) patients were analyzed. Treatment success rate in CS and TZP group respectively (50% vs 51.2%, p = 0.18), 28-day mortality rate (46.1% vs 42.8%, p = 0.56) and antibiotic-related side effects (50.6% vs 46.1%, p = 0.42) were similar except prolonged prothrombin time (19.4% vs 6.4%; p = 0.001). According to this study results, CS and TZP have equal effectivity and safety for the empirical treatment of Gram-negative NIs. CS may be an appropriate alternative to TZP for antibiotic cycling or mixing strategy to reduce antibiotic resistance.

Effect of camera monitoring and feedback along with training on hospital infection rate in a neonatal intensive care unit.

BACKGROUND: In terms of pediatric healthcare-associated infections (HAI), neonatal intensive care units (NICU) constitute the greatest risk. Contacting a health care personnel, either directly or indirectly, elevates NICU occurrence rate and risks other infants in the same unit. In this study, it is aimed to retrospectively analyze the effect of the training along with camera monitoring and feedback (CMAF) to control the infection following a small outbreak. METHODS: ESBL producing Klebsiella pneumoniae was detected on three infants in May 2014 at the isolation room of Sakarya University Hospital NICU. Precautions were taken to prevent further spread of the infection. The infected infants were isolated and the decolonization process was initiated. For this aspect, health care workers (HCWs) in NICU were trained for infection control measures. An infection control committee has monitored the HCWs. Before monitoring, an approval was obtained from the hospital management and HCWs were informed about the CMAF, who were then periodically updated. On a weekly basis, NICU workers were provided with the feedbacks. Epidemic period and post-epidemic control period (June-July-August 2014) were evaluated and p value < 0.05 was considered statistically significant. RESULTS: Healthcare-associated infection (HAI) density was 9.59% before the onset of the CMAF, whereas it was detected as 2.24% during the CMAF period (p < 0.05). Following the precautions, HAI and HAI density rates have reduced to 76.6% and 74.85%, respectively. Moreover, hand hygiene compliance of health care workers was found 49.0% before the outbreak, whereas this rate has elevated to 62.7% after CMAF. CONCLUSIONS: Healthcare workers should be monitored in order to increase their compliance for infection control measures. Here, we emphasized that that CMAF of health workers may contribute reducing the HAI rate in the NICU.

Evaluating inputs of failure modes and effects analysis in identifying patient safety risks.

PURPOSE: There is a growing awareness on the use of systems approaches to improve patient safety and quality. While earlier studies evaluated the validity of such approaches to identify and mitigate patient safety risks, so far only little attention has been given to their inputs, such as structured brainstorming and use of system mapping approaches (SMAs), to understand their impact in the risk identification process. To address this gap, the purpose of this paper is to evaluate the inputs of a well-known systems approach, failure modes and effects analysis (FMEA), in identifying patient safety risks in a real healthcare setting. DESIGN/METHODOLOGY/APPROACH: This study was conducted in a newly established adult attention deficit hyperactivity disorder service at Cambridge and Peterborough Foundation Trust in the UK. Three stakeholders of the chosen service together with the facilitators conducted an FMEA exercise along with a particular system diagram that was initially found as the most useful SMA by eight stakeholders of the service. FINDINGS: In this study, it was found that the formal structure of FMEA adds value to the risk identification process through comprehensive system coverage with the help of the system diagram. However, results also indicates that the structured brainstorming refrains FMEA participants from identifying and imagining new risks since they follow the process predefined in the given system diagram. ORIGINALITY/VALUE: While this study shows the potential contribution of FMEA inputs, it also suggests that healthcare organisations should not depend solely on FMEA results when identifying patient safety risks; and therefore prioritising their safety concerns.

A framework to support risk assessment in hospitals.

QUALITY PROBLEM OR ISSUE: A number of challenges have been identified with current risk assessment practice in hospitals, including: a lack of consultation with a sufficiently wide group of stakeholders; a lack of consistency and transparency; and insufficient risk assessment guidance. Consequently, risk assessment may not be fully effective as a means to ensure safety. INITIAL ASSESSMENT: We used a V system developmental model, in conjunction with mixed methods, including interviews and document analysis to identify user needs and requirements. CHOICE OF SOLUTION: One way to address current challenges is through providing good guidance on the fundamental aspects of risk assessment. We designed a risk assessment framework, comprising: a risk assessment model that depicts the main risk assessment steps; risk assessment explanation cards that provide prompts to help apply each step; and a risk assessment form that helps to systematize the risk assessment and document the findings. IMPLEMENTATION: We conducted multiple group discussions to pilot the framework through the use of a representative scenario and used our findings for the user evaluation. EVALUATION: User evaluation was conducted with 10 participants through interviews and showed promising results. LESSONS LEARNED: While the framework was recommended for use in practice, it was also proposed that it be adopted as a training tool. With its use in risk assessment, we anticipate that risk assessments would lead to more effective decisions being made and more appropriate actions being taken to minimize risks. Consequently, the quality and safety of care delivered could be improved.

A Review of Risk Matrices Used in Acute Hospitals in England.

In healthcare, patient safety has received substantial attention and, in turn, a number of approaches to managing safety have been adopted from other high-risk industries. One of these has been risk assessment, predominantly through the use of risk matrices. However, while other industries have criticized the design and use of these risk matrices, the applicability of such criticism has not been investigated formally in healthcare. This study examines risk matrices as used in acute hospitals in England and the guidance provided for their use. It investigates the applicability of criticisms of risk matrices from outside healthcare through a document analysis of the risk assessment policies, procedures, and strategies used in English hospitals. The findings reveal that there is a large variety of risk matrices used, where the design of some might increase the chance of risk misprioritization. Additionally, findings show that hospitals may provide insufficient guidance on how to use risk matrices as well as what to do in response to the existing criticisms of risk matrices. Consequently, this is likely to lead to variation in the quality of risk assessment and in the subsequent deployment of resources to manage the assessed risk. Finally, the article outlines ways in which hospitals could use risk matrices more effectively.

Positive effect of restrictions on antibiotic consumption

Background/aim: This study aimed to examine the change in the etiology of hospital infections with restricting and releasing of group 2 carbapenems (G2C) (meropenem/imipenem/doripenem). Materials and methods: This study was planned in three periods. Study period 1 (SP-1): Carbapenems were prescribed without restriction by infectious disease specialists. SP-2: G2C prescription was restricted. SP-3: Carbapenem prescription was released. Results: In total, 4443 cases [1053 in SP-1 (23.7%), 1332 in SP-2 (29.9%), and 2085 in SP-3 (46.9%)] were included in the study. Infection rates were 11%, 6.5%, and 7.9% in SP-1, SP-2, and SP-3, respectively (P = 0.001). Acinetobacter spp.-related hospital infection rates were 3.9%, 1.2%, and 1.8%, in SP-1, SP-2, and SP-3, respectively (P = 0.0001). Infection related mortality in SP-1, SP-2, and SP-3 was 7.3%, 5%, and 3.8%, respectively (P = 0.001). Conclusion: Hospital-acquired Acinetobacter infections, antibiotic consumption, and infection-related mortality were decreased significantly with the restriction of G2C. Positive behaviors that were obtained during the restricted period were continued with release of restriction.

Antibiotic consumption in Turkish hospitals; a multi-centre point prevalence study.

This multi-centre study aimed to determine the antibiotic consumption in Turkish hospitals by point prevalence. Antibiotic consumption of 14 centres was determined using the DDD method. Among hospitalized patients, 44.8% were using antibiotics and the total antibiotic consumption was 674.5 DDD/1000 patient-days (DPD). 189.6 (28%) DPD of the antibiotic consumption was restricted while 484.9 (72%) DPD was unrestricted. Carbapenems (24%) and beta lactam/beta lactamase inhibitors (ampicillin-sulbactam or amoxicillin-clavulanate; 22%) were the most commonly used restricted and unrestricted antibiotics. Antibiotics were most commonly used in intensive care units (1307.7 DPD). Almost half of the hospitalized patients in our hospitals were using at least one antibiotic. Moreover, among these antibiotics, the most commonly used ones were carbapenems, quinolones and cephalosporins, which are known to cause collateral damage. We think that antibiotic resistance, which is seen at considerably high rates in our hospitals, is associated with this level of consumption.

Prevalence and genotype distribution of human papillomavirus in non-neoplastic cervical tissue lesion: cervical erosion.

Human papillomavirus (HPV) infection is the commonest sexually transmitted infection, which is associated with various clinical conditions, ranging from asymptomatic infection to malignant disease of the cervix. The aim of this study was to evaluate the prevalence and genotypic distribution of HPV in women with cervical erosion and to compare the results with those in women with a clinically normal cervix. A further aim was to establish the association between HPV infection and cervical cytology results in women with and without cervical erosion. Cervical samples were collected by liquid-based method and consecutively evaluated for the presence of HPV DNA and for cervical cytology. HPV DNA was tested by a nested polymerase chain reaction (PCR) and typed by reverse dot blot genotyping. Cytological classification was made according to Bethesda 2001 criteria. The overall HPV prevalence was 16.9%; HPV DNA was positive in 20.2% of women with cervical erosion and 12.8% in women with normal cervix (P < 0.05). Multiple infections were found in 34.1% of the HPV-positive women. Commonest types were HPV 18 (32.9%), HPV 16 (29.5%), HPV 54 (20.5%), and HPV 6 (17%). Cervical cytology results were abnormal for 5.2% of women with cervical erosion and for 1.3% with clinically normal cervix (P < 0.05). This study detected a high prevalence of HPV infection in women with cervical erosion compared to women with a normal cervix. This data may contribute to the HPV epidemiology in the southeastern Turkey. It is recommended that women with cervical erosion should be given priority in HPV screening programs.