A clinically applicable approach to continuous prediction of future acute kidney injury.

The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2-17 and using acute kidney injury-a common and potentially life-threatening condition18-as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.

Patients' experiences of day surgery: a Parsonian analysis.

AIM: The aim of the study was to explore patients' experiences of day surgery using a sociological framework of analysis. BACKGROUND: Although day surgery has increased globally in the last 20 years, little applied sociological research has been undertaken in this area. METHOD: The Glaserian methodology of Grounded Theory was used. Semi-structured interviews were conducted with 145 patients and 100 carers on three occasions from 2004 to 2006. Analysis of the data involved line-by-line analysis, compilation of key words and phrases (codes) and constant comparison of the codes until core categories were identified. FINDINGS: A major category to emerge from the data was the ambiguity presented to patients in relation to the sick role. Of concern to patients was society's attitudes, which seem to deny to day surgery patients full entitlement to the privileges associated with the sick role. Day surgery patients wanted to feel comfortable in a role that was socially acceptable--the sick role. However, many patients actively resisted this role, and this could have implications for recovery. A large number of patients wished for a limited ascription of the sick role, whilst a minority actively sought to acquire this role. CONCLUSION: The importance of nurses in providing supportive, psychological care, and ensuring patient and carer understanding of what day surgery entails cannot be overstated. Day surgery personnel should teach that day surgery is not minor surgery and that recovery times may be protracted, during which patients will need support.

'They are marvellous with you whilst you are in but the aftercare is rubbish': a grounded theory study of patients' and their carers' experiences after discharge following day surgery.

AIMS AND OBJECTIVES: To explore patients' experiences following discharge from the day surgery unit. BACKGROUND: The shape of twenty-first surgical care is changing. Due to political drivers, the self-care ethos and cost containment as well as technological advances, surgery, which previously required a lengthy hospital stay can now be performed in a day. Care that was previously performed by nurses is now transferred to the patient and their carer. DESIGN: A Glaserian grounded theory methodology was used. METHODOLOGY: A semi-structured interview took place by telephone on two occasions following discharge from 2004-2006. One hundred and forty-five patients and their carers were recruited from two day surgery units in the UK. Analysis took place by constant comparisons of interview data, line by line analysis and referral to field notes and memos until core categories emerged. RESULTS: Three major themes emerged from this study: the difficulties patients encountered in caring for themselves or their loved ones; the desire for obtaining professional support once they were discharged home; and nostalgia for past times. CONCLUSION: This study adds new insights to the discharge experiences of day surgery patients. Discharge planning should be started at the pre-assessment stage of the day surgery process and should be a joint venture between community staff, patients and day surgery nurses. More information should be given concerning community services available to the patients and educational programmes need to be developed to address the changing nature of surgical care. RELEVANCE TO CLINICAL PRACTICE: Raising awareness of the problems patients may experience following discharge from day surgery may encourage a more pro-active attitude towards planning discharge services by a combined approach from day surgery nurses and community (district) nurses.

Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing.

OBJECTIVE: Multitask learning (MTL) using electronic health records allows concurrent prediction of multiple endpoints. MTL has shown promise in improving model performance and training efficiency; however, it often suffers from negative transfer - impaired learning if tasks are not appropriately selected. We introduce a sequential subnetwork routing (SeqSNR) architecture that uses soft parameter sharing to find related tasks and encourage cross-learning between them. MATERIALS AND METHODS: Using the MIMIC-III (Medical Information Mart for Intensive Care-III) dataset, we train deep neural network models to predict the onset of 6 endpoints including specific organ dysfunctions and general clinical outcomes: acute kidney injury, continuous renal replacement therapy, mechanical ventilation, vasoactive medications, mortality, and length of stay. We compare single-task (ST) models with naive multitask and SeqSNR in terms of discriminative performance and label efficiency. RESULTS: SeqSNR showed a modest yet statistically significant performance boost across 4 of 6 tasks compared with ST and naive multitasking. When the size of the training dataset was reduced for a given task (label efficiency), SeqSNR outperformed ST for all cases showing an average area under the precision-recall curve boost of 2.1%, 2.9%, and 2.1% for tasks using 1%, 5%, and 10% of labels, respectively. CONCLUSIONS: The SeqSNR architecture shows superior label efficiency compared with ST and naive multitasking, suggesting utility in scenarios in which endpoint labels are difficult to ascertain.

Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records.

Early prediction of patient outcomes is important for targeting preventive care. This protocol describes a practical workflow for developing deep-learning risk models that can predict various clinical and operational outcomes from structured electronic health record (EHR) data. The protocol comprises five main stages: formal problem definition, data pre-processing, architecture selection, calibration and uncertainty, and generalizability evaluation. We have applied the workflow to four endpoints (acute kidney injury, mortality, length of stay and 30-day hospital readmission). The workflow can enable continuous (e.g., triggered every 6 h) and static (e.g., triggered at 24 h after admission) predictions. We also provide an open-source codebase that illustrates some key principles in EHR modeling. This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks.

Therapeutic relationships in day surgery: a grounded theory study.

AIM: To explore patients' experiences of day surgery. BACKGROUND: Therapeutic relationships are considered to be a core dimension of nursing care. However, in modern health care with short hospital stays the formation of these relationships may be impeded. A major theme to emerge from this study was the development of therapeutic relationships in the day surgery setting. DESIGN: The Glaserian method of Grounded Theory was used. METHODOLOGY: Semi-structured interviews with 145 patients took place from 2004-2006 in two-day surgery units in the UK. Analysis involved transcriptions of interviews and memos. Lists of key words and phrases were made and constantly compared until core categories emerged. RESULTS: Patients spoke highly of the relationships they developed with nurses during their stay in the day surgery unit. Analysis of the data revealed the core category of therapeutic relationships and four sub core categories: 'presence', 'extra special', 'befriending' and 'comfort-giving.' CONCLUSION: This paper adds to the growing body of literature which demonstrates that therapeutic relationships can be developed within the short stay arena of health care: routine interactions which may not be considered to be significant by nurses may be of importance to patients. The patients in this study felt supported, comforted and befriended by day surgery nurses. However a minority of patients were disappointed with the nursing staffs' lack of interpersonal responses to their needs. RELEVANCE TO CLINICAL PRACTICE: Anecdotal evidence suggests that personnel working within day surgery are not always aware of their therapeutic potential. Therefore raising awareness of this through research generated from patients' experiences might encourage nurses to further realise their capabilities in this fundamental area of nursing.

Tweeting does not preclude the ability to communicate.

I share the frustration of your correspondent (letters April 11) who deplores the use of mobile phones and social networking sites such as Twitter and Facebook in the workplace. I also agree that their use should be restricted in the clinical area.

"Like a trip to McDonalds": a grounded theory study of patient experiences of day surgery.

BACKGROUND: The amount and complexity of (ambulatory) day surgery is rapidly expanding internationally. Nurses have a responsibility to provide quality care for day surgery patients. To do this they must understand all aspects of the patient experience. There is dearth of research into day surgery using a sociological frame of reference. OBJECTIVE: The study investigated patients' experiences of day surgery using a sociological frame of reference. DESIGN: A qualitative study using the grounded theory approach was used. SETTING: The study was based in two day surgery units in two urban public hospitals in the United Kingdom. PARTICIPANTS: 145 patients aged 18-70 years and 100 carers were purposely selected from the orthopaedic, ear nose and throat and general surgical lists. They were all English speaking and were of varied socio-economic background. METHODS: The data was collected from 2004 to 2006. Semi-structured interviews were conducted on three occasions: before surgery, 48 h following surgery and one month following discharge. Permission was received from the Local Research Ethics Committee. Analysis of the data involved line-by-line analysis, compilation of key words and phrases (codes) and constant comparison of the codes until categories emerged. FINDINGS: Patients liked day surgery and placed it within the wider societal context of efficiency and speed. Time was a major issue for them. They wished surgery, like all other aspects of their life to be a speedy process. They likened it to a McDonald's experience with its emphasis on speed, predictability and control. CONCLUSION: This study throws new light on patient experiences and offers an understanding of day surgery against a western culture which emphasises the importance of speed and efficiency. It is a popular choice for patients but at times it can be seen to be a mechanistic way of providing care. The implications for nurses to provide education and information to add to the quality of the patient experience are discussed.