Prediciton of emergency events: a multi-task multi-label learning approach

Prediction of patient outcomes is critical to plan resources in an hospital emergency department. We present a method to exploit longitudinal data from Electronic Medical Records (EMR), whilst exploiting multiple patient outcomes. We divide the EMR data into segments where each segment is a task, and all tasks are associated with multiple patient outcomes over a 3, 6 and 12 month period. We propose a model that learns a prediction function for each task-label pair, interacting through two subspaces: the first subspace is used to impose sharing across all tasks for a given label. The second subspace captures the task-specific variations and is shared across all the labels for a given task. The proposed model is formulated as an iterative optimization problems and solved using a scalable and efficient Block co-ordinate descent (BCD) method. We apply the proposed model on two hospital cohorts - Cancer and Acute Myocardial Infarction (AMI) patients collected over a two year period from a large hospital emergency department. We show that the predictive performance of our proposed models is significantly better than those of several state-of-the-art multi-task and multi-label learning methods.

Cancer cachexia: a molecular nutrition approach to cancer-related muscle loss

The project identified changes in molecular markers of antioxidant status and muscle atrophy during cancer-associated weight-loss, and confirmed omega-3 EPA as an effective treatment for muscle-loss in experimental cancer cachexia. The project also identified the PG-SGA nutrition tool as a powerful predictor of patient outcomes and survival in clinical cachexia.

On the issuing policies for perishable items such as red blood cells and platelets in blood service

Red blood cells (RBCs) and platelets are examples of perishable items with a fixed shelf life. Recent studies show that transfusing fresh RBCs may lead to an improvement of patient outcomes. In addition, to better manage their inventory, hospitals prefer to receive fresh RBCs and platelets. Therefore, as well as minimizing outdates and shortages, reducing the average age of issue is a key performance criterion for blood banks. The issuing policy in a perishable inventory system has a substantial impact on the age of issue and outdate and shortage rates. Although several studies have compared the last in first out (LIFO) and the first in first out (FIFO) policies for perishable products, only a few studies have considered the situation of blood banks where replenishment is not controllable. In this study, we examine various issuing policies for a perishable inventory system with uncontrollable replenishment, and outline a modified FIFO policy. Our proposed modified FIFO policy partitions the inventory into two parts such that the first part holds the items with age less than a threshold. It then applies the FIFO policy in each part and the LIFO policy between the parts. We present two approximation techniques to estimate the average age of issue, the average time between successive outdates and the average time between successive shortages of the modified FIFO policy. Our analysis shows in several cases that where the objective function is a single economic function, or it is formulated as a multiobjective model, the modified FIFO policy outperforms the FIFO and LIFO policies.

Cultural respect encompassing simulation training: being heard about health through broadband

BACKGROUND: Cultural Respect Encompassing Simulation Training (CREST) is a learning program that uses simulation to provide health professional students and practitioners with strategies to communicate sensitively with culturally and linguistically diverse (CALD) patients. It consists of training modules with a cultural competency evaluation framework and CALD simulated patients to interact with trainees in immersive simulation scenarios. The aim of this study was to test the feasibility of expanding the delivery of CREST to rural Australia using live video streaming; and to investigate the fidelity of cultural sensitivity - defined within the process of cultural competency which includes awareness, knowledge, skills, encounters and desire - of the streamed simulations. DESIGN AND METHODS: In this mixed-methods evaluative study, health professional trainees were recruited at three rural academic campuses and one rural hospital to pilot CREST sessions via live video streaming and simulation from the city campus in 2014. Cultural competency, teaching and learning evaluations were conducted. RESULTS: Forty-five participants rated 26 reliable items before and after each session and reported statistically significant improvement in 4 of 5 cultural competency domains, particularly in cultural skills (P<0.05). Qualitative data indicated an overall acknowledgement amongst participants of the importance of communication training and the quality of the simulation training provided remotely by CREST. CONCLUSIONS: Cultural sensitivity education using live video-streaming and simulation can contribute to health professionals' learning and is effective in improving cultural competency. CREST has the potential to be embedded within health professional curricula across Australian universities to address issues of health inequalities arising from a lack of cultural sensitivity training. Significance for public healthThere are significant health inequalities for migrant populations. They commonly have poorer access to health services and poorer health outcomes than the Australian-born population. The factors are multiple, complex and include language and cultural barriers. To address these disparities, culturally competent patient-centred care is increasingly recognised to be critical to improving care quality, patient satisfaction, patient compliance and patient outcomes. Yet there is a lack of quality in the teaching and learning of cultural competence in healthcare education curricula, particularly in rural settings where qualified trainers and resources can be limited. The Cultural Respect Encompassing Simulation Training (CREST) program offers opportunities to health professional students and practitioners to learn and develop communication skills with professionally trained culturally and linguistically diverse simulated patients who contribute their experiences and health perspectives. It has already been shown to contribute to health professionals' learning and is effective in improving cultural competency in urban settings. This study demonstrates that CREST when delivered via live video-streaming and simulation can achieve similar results in rural settings.

A prescription for resistance: management of Staphylococcal skin abscesses by general practitioners in Australia

Objectives: We investigated the management of staphylococcal abscesses (boils) by general practitioners (GPs) in the context of rising antibiotic resistance in community strains of Staphylococcus aureus.
Design, Setting, Participants: We analyzed patient-reported management of 66 cases of uncomplicated skin abscesses from the frequency matched methicillinresistant S. aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) Community- Onset Staphylococcus aureus Household Cohort (COSAHC) study (Melbourne, Australia, 2008–2012). Susceptibilities in all cases were known: 50/66 abscesses were caused by MRSA. In order to investigate GP-reported management of staphylococcal abscesses, we surveyed a random subset of GPs, from the COSAHC study (41), and of GPs (39) who used the same community-based pathology service (December 2011– May 2012). Main outcome measures: Patient outcomes, antibiotics prescribed, antibiotic resistance profiles of infecting strains, rates of incision and drainage (I&D), and attitudes to ordering microbiological cultures.
Results: MRSA was three times more likely to be cultured from an abscess than MSSA. Patient-reported management revealed 100% were prescribed antibiotics and only 60.6% had I&D. Of those 85% who remembered their prescription(s), 81% of MRSA cases and 23% of MSSA cases initially received inactive antibiotics. Repeat GP visits where antibiotics were changed occurred in 45 MRSA and 7 MSSA cases, although at least 33% of subsequent prescriptions were inactive for the MRSA infections. Patients treated with I&D and antibiotics did no better than those treated with only I&D, regardless of the antibiotic activity. In the GP surveys, 89% reported I&D, with or without antibiotics, to be their preferred management. Only 29.9% of GPs would routinely swab abscesses.

The role of IT governance in generating business value from IT investments in healthcare: lessons from an Australian experience

Digitizing the core processes of healthcare delivery is looked at as a solution to control the escalating costs without compromising quality or patient outcomes. However, to date the business value of such IT solutions remains elusive, especially in view of the high failure rate of many solutions coupled with the high user resistance. The uniqueness of the healthcare industry makes measuring the business value of IT a complex missions, yet it is the thesis of this research that such an activity is an essential first step if we are to realise the full potential of IT in healthcare. The role IT governance can play is of high importance to generate business value from IT investments in healthcare. This is investigated using an integrative model that is proffered to conceptualise the business value of IT in healthcare. This conceptual model is then used to guide an exploratory case study based at a leading private healthcare provider in Melbourne-Australia.

Compliance to exercise-oncology guidelines in prostate cancer survivors and associations with psychological distress, unmet supportive care needs, and quality of life

Objective The purpose of this study was to determine prevalence of Australian prostate cancer survivors meeting contemporary exercise-oncology guidelines and identify associations with distress, unmet supportive care needs, and quality of life. Methods A population-based cohort of 463 prostate cancer survivors who were on 10.8 months post-curative therapy was assessed for compliance with current exercise guidelines for cancer survivors, motivational readiness for physical activity, psychological distress, unmet supportive care needs, and quality of life. Results Only 57 men (12.3%) reported sufficient exercise levels (150 min of moderate intensity or 75 min of strenuous exercise per week and twice weekly resistance exercise), 186 (40.2%) were insufficiently active, and 220 (47.5%) were inactive. Among inactive men, 99 (45.0%) were in the contemplation or preparation stage of motivation readiness. Inactive men had higher global distress (p=0.01) and Brief Symptom Inventory-Anxiety (p<0.05) than those who were insufficiently active. Total Supportive Care Needs and International Prostate Cancer Symptom scores were higher in inactive than insufficiently and sufficiently active men (p<0.05). Lack of physical activity contributed to poorer quality of life. Conclusions Only a small proportion of Australian prostate cancer survivors met contemporary exercise-oncology recommendations despite increasing recognition of exercise to improve patient outcomes. Strategies are urgently required to increase prostate cancer survivors' participation in aerobic and resistance exercise training.

Analysis of the impact of limitation of medical treatment orders during unplanned transfers from sub-acute care to emergency departments

BACKGROUND: The impact of limitation of medical treatment orders (LOMT) on patient outcomes following transfer from sub-acute care to the Emergency Department remains unclear.

METHODS: Retrospective medical record review of 431 adult in-patients who required ambulance transfer following clinical deterioration during a sub-acute care admission during 2010.

RESULTS: Common reasons for transfer were respiratory (18.9%) or neurological (19.0%) conditions; 35.7% (154/431) were transferred within one week of sub-acute care admission. LOMT orders were in place for 37.8% (n=163) patients who were older (p<0.001), with more comorbidities (p<0.005), specifically cardiac, renal and pulmonary disease than patients without LOMT. Patients with LOMT orders had more physiological abnormalities before transfer; tachypnoea (43.7% vs 28.6%), hypoxaemia (63.5% vs 48.4%) and severe hypoxaemia (27.6% vs 14.5%). There were no differences in rates of admission, cardiac arrest, Medical Emergency Team activation or ICU admission. For admitted patients, those with LOMT orders had significantly (p≤0.005) higher mortality: in-hospital (21.9% vs 11.3%); 30 days (23.9% vs 12.3%) and 60 days (28.2% vs 13.4%).

CONCLUSIONS: Patients with LOMT had higher levels of comorbidity and were more acutely ill during their sub-acute care admission. Once transferred those with a LOMT had similar rates of cardiac arrest, MET activation and unplanned ICU admission, but higher mortality.

The transplant team's support of kidney transplant recipients to take their prescribed medications: a collective responsibility.

AIMS AND OBJECTIVES: To obtain an understanding of how health professionals support the kidney transplant patient to take their medications as prescribed long term. BACKGROUND: Kidney transplantation requires stringent adherence to complex medication regimens to prevent graft rejection and to maintain general well-being. Medication nonadherence is common in kidney transplantation, emerging in the first few months post-transplantation, leading to poor patient outcomes. DESIGN: Exploratory qualitative design. METHODS: Five focus groups were conducted with a total of seven renal nurse transplant coordinators, two renal transplant nurse unit managers, seven nephrologists, seven pharmacists, four social workers, and one consumer representative representing all five hospitals offering adult kidney transplantation in Victoria, Australia in 2014. The views of two general practitioners who were unable to attend the focus groups were incorporated into the data set. All data underwent thematic analysis. RESULTS: Analysis revealed that adherence was a collective responsibility involving the whole of the transplant team and the patient via education blitz in hospital, identifying and managing nonadherence, promotion of self-advocacy, and the partnership between the patient and health professional. Patients were directed how to take their complex medications to be self-empowered, yet the partnership between the patient and health professional limited the patient's voice. CONCLUSION: Although medication adherence was a collective responsibility, communication was often one-way chiefly as a result of staffing and time constraints, hindering effective partnerships necessary for medication adherence. Expert skills in communication and adherence counselling are necessary to identify barriers affecting medication adherence. Patients need to be systematically screened, prepared and supported long-term within an accommodating healthcare system for the reality of caring for their transplanted kidney. RELEVANCE TO CLINICAL PRACTICE: Kidney transplant recipients require systematic preparation and quality long-term follow-up to adhere to their prescribed medications.

Cerebral oxygenation in mechanically ventilated early cardiac arrest survivors: The impact of hypercapnia

BACKGROUND : Optimal cerebral oxygenation is considered fundamental to cerebral protection in cardiac arrest (CA) patients. Hypercapnia increases cerebral blood flow and may also improve cerebral oxygenation. It is uncertain, however, whether this effect occurs in mechanically ventilated early survivors of CA. METHODS: We enrolled mechanically ventilated resuscitated patients within 36 h of their cardiac arrest. We performed a prospective double cross-over physiological study comparing the impact of normocapnia (PaCO2 35-45 mmHg) vs. mild hypercapnia (PaCO2 45-55 mmHg) on regional cerebral tissue oxygen saturation (SctO2) assessed by near infrared spectroscopy (NIRS).RESULTS: We studied seven adult CA patients with a median time to return of spontaneous circulation of 28 min at a median of 26 h and 30 min after CA. During normocapnia (median EtCO2 of 32 mmHg [30-41 mmHg] and PaCO2 of 37 mmHg [32-45 mmHg]) the median NIRS-derived left frontal SctO2 was 61% [52-65%] and the right frontal SctO2 was 61% [54-68%]. However, during mild hypercapnia (median EtCO2 of 49 mmHg [40-57 mmHg] and PaCO2 of 52 mmHg [43-55 mmHg) the median left frontal SctO2 increased to 69% [59-78%] and the right frontal SctO2 increased to 73% [61-76%])(p = 0.001, for all comparisons). CONCLUSION: During the early post-resuscitation period, in mechanically ventilated CA patients, mild hypercapnia increases cerebral oxygenation as assessed by NIRS. Further investigations of the effect of prolonged mild hypercapnia on cerebral oxygenation and patient outcomes appear justified.

Lateral positioning for critically ill adult patients

BACKGROUND: Critically ill patients require regular body position changes to minimize the adverse effects of bed rest, inactivity and immobilization. However, uncertainty surrounds the effectiveness of lateral positioning for improving pulmonary gas exchange, aiding drainage of tracheobronchial secretions and preventing morbidity. In addition, it is unclear whether the perceived risk levied by respiratory and haemodynamic instability upon turning critically ill patients outweighs the respiratory benefits of side-to-side rotation. Thus, lack of certainty may contribute to variation in positioning practice and equivocal patient outcomes. OBJECTIVES: To evaluate effects of the lateral position compared with other body positions on patient outcomes (mortality, morbidity and clinical adverse events) in critically ill adult patients. (Clinical adverse events include hypoxaemia, hypotension, low oxygen delivery and global indicators of impaired tissue oxygenation.) We examined single use of the lateral position (i.e. on the right or left side) and repeat use of the lateral position (i.e. lateral positioning) within a positioning schedule. SEARCH METHODS: We searched the Cochrane Central Register of Controlled Trials (CENTRAL; 2015, Issue 5), MEDLINE (1950 to 23 May 2015), the Cumulative Index to Nursing and Allied Health Literature (CINAHL) (1937 to 23 May 2015), the Allied and Complementary Medicine Database (AMED) (1984 to 23 May 2015), Latin American Caribbean Health Sciences Literature (LILACS) (1901 to 23 May 2015), Web of Science (1945 to 23 May 2015), Index to Theses in Great Britain and Ireland (1950 to 23 May 2015), Trove (2009 to 23 May 2015; previously Australasian Digital Theses Program (1997 to December 2008)) and Proquest Dissertations and Theses (2009 to 23 May 2015; previously Proquest Digital Dissertations (1980 to 23 May 2015)). We handsearched the reference lists of potentially relevant reports and two nursing journals. SELECTION CRITERIA: We included randomized and quasi-randomized trials examining effects of lateral positioning in critically ill adults. We included manual or automated turns but limited eligibility to studies that included duration of body position of 10 minutes or longer. We examined each lateral position versus at least one comparator (opposite lateral position and/or another body position) for single therapy effects, and the lateral positioning schedule (repeated lateral turning) versus other positioning schedules for repetitive therapy effects. DATA COLLECTION AND ANALYSIS: We pre-specified methods to be used for data collection, risk of bias assessment and analysis. Two independent review authors carried out each stage of selection and data extraction and settled differences in opinion by consensus, or by third party adjudication when disagreements remained unresolved. We planned analysis of pair-wise comparisons under composite time intervals with the aim of considering recommendations based on meta-analyses of studies with low risk of bias. MAIN RESULTS: We included 24 studies of critically ill adults. No study reported mortality as an outcome of interest. Two randomized controlled trials (RCTs) examined lateral positioning for pulmonary morbidity outcomes but provided insufficient information for meta-analysis. A total of 22 randomized trials examined effects of lateral positioning (four parallel-group and 18 cross-over designs) by measuring various continuous data outcomes commonly used to detect adverse cardiopulmonary events within critical care areas. However, parallel-group studies were not comparable, and cross-over studies provided limited data as the result of unit of analysis errors. Eight studies provided some data; most of these were single studies with small effects that were imprecise. We pooled partial pressure of arterial oxygen (PaO2) as a measure to detect hypoxaemia from two small studies of participants with unilateral lung disease (n = 19). The mean difference (MD) between lateral positions (bad lung down versus good lung down) was approximately 50 mmHg (MD -49.26 mmHg, 95% confidence interval (CI) -67.33 to -31.18; P value < 0.00001). Despite a lower mean PaO2 for bad lung down, hypoxaemia (mean PaO2 < 60 mmHg) was not consistently reported. Furthermore, pooled data had methodological shortcomings with unclear risk of bias. We had similar doubts regarding internal validity for other studies included in the review. AUTHORS' CONCLUSIONS: Review authors could provide no clinical practice recommendations based on the findings of included studies. Available research could not eliminate the uncertainty surrounding benefits and/or risks associated with lateral positioning of critically ill adult patients. Research gaps include the effectiveness of lateral positioning compared with semi recumbent positioning for mechanically ventilated patients, lateral positioning compared with prone positioning for acute respiratory distress syndrome (ARDS) and less frequent changes in body position. We recommend that future research be undertaken to address whether the routine practice of repositioning patients on their side benefits all, some or few critically ill patients.

Intensive care nurses' knowledge of enteral nutrition: a descriptive questionnaire

BACKGROUND: Nurses have an important role in the delivery and management of enteral nutrition in critically ill patients, to prevent iatrogenic malnutrition. It is not clear how nurses source enteral nutrition information. 

It is not that simple nor compelling! Comment on "Translating evidence into healthcare policy and practice: single versus multi-faceted implementation strategies - is there a simple answer to a complex question?"

Healthcare decisions are often made under pressure, with varying levels of information in a changing clinical context. With limited resources and a focus on improving patient outcomes, healthcare managers and health professionals strive to implement both clinical and cost-effective care. However, the gap between research evidence and health policy/clinical practice persists despite our best efforts. In an attempt to close the gap through behaviour change interventions, there has been a strong held belief that 'more is better,' without understanding the mechanisms and circumstances of knowledge translation (KT). We argue that even a single intervention or strategy in translating evidence into healthcare policy or practice is rarely simple to implement. Nor is the evidence compelling on the best approach. As Harvey and Kitson argued, designing and evaluating KT interventions requires flexibility and responsiveness. If we are to move forward in translation science then we need to use rigorous designs such as randomised controlled trials to test effectiveness of interventions or strategies with embedded process evaluations to understand the reason interventions do or do not work!

What are the implications of changing treatment delivery models for patients with inflammatory bowel disease : a discussion paper

An integrated model of care has been used effectively to manage chronic diseases; however, there is limited, yet encouraging evidence on its introduction in the management of inflammatory bowel disease (IBD), a chronic gastrointestinal condition. Here, the rationale for and implications of introducing an integrated model of care for patients with IBD are discussed, with a particular focus on psychology input, patient-centred care, efficiency as perceived by patients and doctors, financial implications and the possible means of model introduction. This is a discussion paper on the integrated model of care for IBD against a background of what has been learned from an integrated model of care established in other chronic conditions. Although limited, the emerging data on an integrated model of care in IBD are encouraging with respect to patient outcomes and savings in healthcare costs. In other conditions, the model has been well received by both patients and practitioners, although the loss of autonomy by doctors is listed among its drawbacks. The cost-effectiveness data are now sufficiently convincing to recommend the model's acceptance in principle. The model should be promoted at the policy level rather than by individual practitioners to facilitate equal access for patients with IBD on a larger scale than currently.