Oxygen delivery to patients after cardiac surgery : a medical record audit

OBJECTIVE: To describe how intensive care nurses manage the administration of supplemental oxygen to patients during the first 24 hours after cardiac surgery.
METHODS: A retrospective audit was conducted of the medical records of 245 adult patients who underwent cardiac surgery between 1 January 2005 and 31 May 2008 in an Australian metropolitan hospital. Physiological data (oxygen saturation measured by pulse oximetry and respiratory rate) and intensive care unit management data (oxygen delivery device, oxygen flow rate and duration of mechanical ventilation) were collected at hourly intervals over the first 24 hours of ICU care.
RESULTS: Of the 245 patients whose records were audited, 185 were male; mean age was 70 years (SD, 10), and mean APACHE II score was 17.5 (SD, 5.14). Almost half the patients (122, 49.8%) were extubated within 8 hours of ICU admission. The most common oxygen delivery device used immediately after extubation was the simple face mask (214 patients, 87%). Following extubation, patients received supplemental oxygen via, on average, two different delivery devices (range, 1-3), and had the delivery device changed an average of 1.38 times (range, 0-6) during the 24 hours studied. Twenty-two patients (9%) received non-invasive ventilation or high-flow oxygen therapy, and 16 (7%) experienced one or more episode of hypoxaemia during mechanical ventilation. A total of 148 patients (60%) experienced one or more episodes of low oxygenation or abnormal respiratory rate during the first 24 hours of ICU care despite receiving supplemental oxygen.
CONCLUSION: These findings suggest that the ICU environment does not protect cardiac surgical patients from suboptimal oxygen delivery, and highlights the need for strategies to prompt the early initiation of interventions aimed at optimising blood oxygen levels in cardiac surgical patients in the ICU.

Implementing scanned medical record systems in Australia : a structured case study on envisioned changes to elective admissions process in a Victorian hospital

In recent years, influenced by the pervasive power of technology, standards and mandates, Australian hospitals have begun exploring digital forms of keeping this record. The main rationale is the ease of accessing different data sources at the same time by varied staff members. The initial step in this transition was implementation of scanned medical record systems, which converts the paper based records to digitised form, which required process flow redesign and changes to existing modes of work. For maximising the benefits of scanning implementation and to better prepare for the changes, Austin Hospital in the State of Victoria commissioned this research focused on elective admissions area. This structured case study redesigned existing processes that constituted the flow of external patient forms and recommended a set of best practices at the same time highlighting the significance of user participation in maximising the potential benefits anticipated. In the absence of published academic studies focused on Victorian hospitals, this study has become a conduit for other departments in the hospital as well as other hospitals in the incursion.

Determining clinical pharmacy workload by patient disease classification in medical and surgical patients

Aim: To determine the time needed to provide clinical pharmacy services to individual patient episodes for medical and surgical patients and the effect of patient presentation and complexity on the clinical pharmacy workload. Method: During a 5-month period in 2006 at two general hospitals, pharmacists recorded a defined range of activities that they provided for patients, including the actual times required for these tasks. A customised database linked to the two hospitals' patient administration systems stored the data according to the specific patient episode number. The influence of patient presentation and complexity on the clinical pharmacy activities provided was also examined. Results: The average time required by pharmacists to undertake a medication history interview and medication reconciliation was 9.6 (SD 4.9) minutes. Interventions required 5.7 (SD 4.6) minutes, clinical review of the medical record 5.5 (SD 4.0) minutes and medication order review 3.5 (SD 2.0) minutes. For all of these activities, the time required for medical patients was greater than for surgical patients and greater for 'complicated' patients. The average time required to perform all clinical pharmacy activities for 1071 completed patient episodes was 14.4 (SD 10.9) minutes and was greater for medical and 'complicated' patients. Conclusion: The time needed to provide clinical pharmacy services was affected by whether the patients were medical or surgical. The existence of comorbidities or complications affected these times. The times required to perform clinical pharmacy activities may not be consistent with recently proposed staff ratios for the provision of a basic clinical pharmacy service.

Validation of de-identified record linkage to ascertain hospital admissions in a cohort study

Background Cohort studies can provide valuable evidence of cause and effect relationships but are subject to loss of participants over time, limiting the validity of findings. Computerised record linkage offers a passive and ongoing method of obtaining health outcomes from existing routinely collected data sources. However, the quality of record linkage is reliant upon the availability and accuracy of common identifying variables. We sought to develop and validate a method for linking a cohort study to a state-wide hospital admissions dataset with limited availability of unique identifying variables.

Methods A sample of 2000 participants from a cohort study (n = 41 514) was linked to a state-wide hospitalisations dataset in Victoria, Australia using the national health insurance (Medicare) number and demographic data as identifying variables. Availability of the health insurance number was limited in both datasets; therefore linkage was undertaken both with and without use of this number and agreement tested between both algorithms. Sensitivity was calculated for a sub-sample of 101 participants with a hospital admission confirmed by medical record review.

Results Of the 2000 study participants, 85% were found to have a record in the hospitalisations dataset when the national health insurance number and sex were used as linkage variables and 92% when demographic details only were used. When agreement between the two methods was tested the disagreement fraction was 9%, mainly due to "false positive" links when demographic details only were used. A final algorithm that used multiple combinations of identifying variables resulted in a match proportion of 87%. Sensitivity of this final linkage was 95%.

Conclusions High quality record linkage of cohort data with a hospitalisations dataset that has limited identifiers can be achieved using combinations of a national health insurance number and demographic data as identifying variables.

Stabilized sparse ordinal regression for medical risk stratification

The recent wide adoption of electronic medical records (EMRs) presents great opportunities and challenges for data mining. The EMR data are largely temporal, often noisy, irregular and high dimensional. This paper constructs a novel ordinal regression framework for predicting medical risk stratification from EMR. First, a conceptual view of EMR as a temporal image is constructed to extract a diverse set of features. Second, ordinal modeling is applied for predicting cumulative or progressive risk. The challenges are building a transparent predictive model that works with a large number of weakly predictive features, and at the same time, is stable against resampling variations. Our solution employs sparsity methods that are stabilized through domain-specific feature interaction networks. We introduces two indices that measure the model stability against data resampling. Feature networks are used to generate two multivariate Gaussian priors with sparse precision matrices (the Laplacian and Random Walk). We apply the framework on a large short-term suicide risk prediction problem and demonstrate that our methods outperform clinicians to a large margin, discover suicide risk factors that conform with mental health knowledge, and produce models with enhanced stability. © 2014 Springer-Verlag London.

Clinical review criteria and medical emergency teams: evaluating a two-tier rapid response system

OBJECTIVES: To assess the prevalence of patients fulfilling clinical review criteria (CRC), to determine activation rates for CRC assessments, to compare baseline characteristics and outcomes of patients who fulfilled CRC with patients who did not, and to identify the documented nursing actions in response to CRC values. DESIGN, SETTING AND PARTICIPANTS: A cross-sectional study using a retrospective medical record audit, in a universityaffiliated, tertiary referral hospital with a two-tier rapid response system in Melbourne, Australia. We used a convenience sample of hospital inpatients on general medical, surgical and specialist service wards admitted during a 24-hour period in 2013. MAIN OUTCOME MEASURES: Medical emergency team (MET) or code blue activation, unplanned intensive care unit admissions, hospital length of stay and inhospital mortality. For patients who fulfilled CRC or MET criteria during the 24- hour period, the specific criteria fulfilled, escalation treatments and outcomes were collected. RESULTS: Of the sample (N = 422), 81 patients (19%) fulfilled CRC on 109 occasions. From 109 CRC events, 66 patients (81%) had at least one observation fulfilling CRC, and 15 patients (18%) met CRC on multiple occasions. The documented escalation rate was 58 of 109 events (53%). The number of patients who fulfilled CRC and subsequent MET call activation criteria within 24 hours was significantly greater than the number who did not meet CRC (P < 0.001). CONCLUSIONS: About one in five patients reached CRC during the study period; these patients were about four times more likely to also fulfil MET call criteria. Contrary to hospital policy, escalation was not documented for about half the patients meeting CRC values. Despite the clarity of escalation procedures on the graphic observation chart, escalation remains an ongoing problem. Further research is needed on the impact on patient outcomes over time and to understand factors influencing staff response.

Learning vector representation of medical objects via EMR-driven nonnegative restricted Boltzmann machines (eNRBM)

Electronic medical record (EMR) offers promises for novel analytics. However, manual feature engineering from EMR is labor intensive because EMR is complex - it contains temporal, mixed-type and multimodal data packed in irregular episodes. We present a computational framework to harness EMR with minimal human supervision via restricted Boltzmann machine (RBM). The framework derives a new representation of medical objects by embedding them in a low-dimensional vector space. This new representation facilitates algebraic and statistical manipulations such as projection onto 2D plane (thereby offering intuitive visualization), object grouping (hence enabling automated phenotyping), and risk stratification. To enhance model interpretability, we introduced two constraints into model parameters: (a) nonnegative coefficients, and (b) structural smoothness. These result in a novel model called eNRBM (EMR-driven nonnegative RBM). We demonstrate the capability of the eNRBM on a cohort of 7578 mental health patients under suicide risk assessment. The derived representation not only shows clinically meaningful feature grouping but also facilitates short-term risk stratification. The F-scores, 0.21 for moderate-risk and 0.36 for high-risk, are significantly higher than those obtained by clinicians and competitive with the results obtained by support vector machines.

Hierarchical Bayesian nonparametric models for knowledge discovery from electronic medical records

Electronic Medical Record (EMR) has established itself as a valuable resource for large scale analysis of health data. A hospital EMR dataset typically consists of medical records of hospitalized patients. A medical record contains diagnostic information (diagnosis codes), procedures performed (procedure codes) and admission details. Traditional topic models, such as latent Dirichlet allocation (LDA) and hierarchical Dirichlet process (HDP), can be employed to discover disease topics from EMR data by treating patients as documents and diagnosis codes as words. This topic modeling helps to understand the constitution of patient diseases and offers a tool for better planning of treatment. In this paper, we propose a novel and flexible hierarchical Bayesian nonparametric model, the word distance dependent Chinese restaurant franchise (wddCRF), which incorporates word-to-word distances to discover semantically-coherent disease topics. We are motivated by the fact that diagnosis codes are connected in the form of ICD-10 tree structure which presents semantic relationships between codes. We exploit a decay function to incorporate distances between words at the bottom level of wddCRF. Efficient inference is derived for the wddCRF by using MCMC technique. Furthermore, since procedure codes are often correlated with diagnosis codes, we develop the correspondence wddCRF (Corr-wddCRF) to explore conditional relationships of procedure codes for a given disease pattern. Efficient collapsed Gibbs sampling is derived for the Corr-wddCRF. We evaluate the proposed models on two real-world medical datasets - PolyVascular disease and Acute Myocardial Infarction disease. We demonstrate that the Corr-wddCRF model discovers more coherent topics than the Corr-HDP. We also use disease topic proportions as new features and show that using features from the Corr-wddCRF outperforms the baselines on 14-days readmission prediction. Beside these, the prediction for procedure codes based on the Corr-wddCRF also shows considerable accuracy.

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.

Predicting risk of suicide attempt using history of physical illnesses from electronic medical records

BACKGROUND: Although physical illnesses, routinely documented in electronic medical records (EMR), have been found to be a contributing factor to suicides, no automated systems use this information to predict suicide risk.

OBJECTIVE: The aim of this study is to quantify the impact of physical illnesses on suicide risk, and develop a predictive model that captures this relationship using EMR data.

METHODS: We used history of physical illnesses (except chapter V: Mental and behavioral disorders) from EMR data over different time-periods to build a lookup table that contains the probability of suicide risk for each chapter of the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) codes. The lookup table was then used to predict the probability of suicide risk for any new assessment. Based on the different lengths of history of physical illnesses, we developed six different models to predict suicide risk. We tested the performance of developed models to predict 90-day risk using historical data over differing time-periods ranging from 3 to 48 months. A total of 16,858 assessments from 7399 mental health patients with at least one risk assessment was used for the validation of the developed model. The performance was measured using area under the receiver operating characteristic curve (AUC).

RESULTS: The best predictive results were derived (AUC=0.71) using combined data across all time-periods, which significantly outperformed the clinical baseline derived from routine risk assessment (AUC=0.56). The proposed approach thus shows potential to be incorporated in the broader risk assessment processes used by clinicians.

CONCLUSIONS: This study provides a novel approach to exploit the history of physical illnesses extracted from EMR (ICD-10 codes without chapter V-mental and behavioral disorders) to predict suicide risk, and this model outperforms existing clinical assessments of suicide risk.

Mixed-initiative decision support for care planning based on clinical practice guidelines

Care Plan On-Line (CPOL) is an intranet based system that supports a “Coordinated Care” model for chronic/complex disease management. CPOL combines provision of solicited and unsolicited advice features based on integration of the electronic medical record (EMR) with its decision support logic. The objective is to support General Practitioners (GPs) in formulating a 12-month care plan of services such that: (a) the plan is proactive and patient-centered; (b) the GP is kept in awareness of project- and diseasespecific clinical practice guidelines; and (c) the support integrates with GP workflow in a natural fashion. A key feature of our approach is to blur the distinction of EMR and decision support by presenting guidelines in layers with the top-most being a problem-oriented presentation of patient status, progressing on through to patient-independent supporting evidence. In conjunction with a degree of automated inclusion of care planning services, the system demonstrates mixed user and software initiative. We describe the CPOL deployment setting, the challenges of guideline-based clinical decision support, our approach to guideline delivery, and the CPOL architecture.

A methodology of health information security evaluation

With the conversion of paper health records to electronic health records, the health care sector is increasingly relying on technology to maintain the integrity of and update patients’ data. This reliance on technology requires an acute level of protection from technological disasters and/or threats of human error or sabotage. Research has shown there are inadequacies in the installation and use of security controls for health information records and that current methods of security analysis lack the techniques to analyse the technical and social aspects of security. This paper reports on progress towards development of a health information security evaluation methodology based on Unified Modelling Language techniques, and discusses an imminent case study that will be used for validation of the methodology.

Continuity of care and general wellbeing of patients with comorbidities requiring joint replacement

Aim. The aim of this paper is to examine the continuity of care and general wellbeing of patients with comorbidities undergoing elective total hip or knee joint replacement.
Background. Advances in medical science and improved lifestyles have reduced mortality rates in most Western countries. As a result, there is an ageing population with a concomitant growth in the number of people who are living with multiple chronic illnesses, commonly referred to as comorbidities. These patients often require acute care services, creating a blend of acute and chronic illness needs. For example, joint replacement surgery is frequently performed to improve impaired mobility associated with osteoarthritis.
Method. A purposive sample of twenty participants with multiple comorbidities who required joint replacement surgery was recruited to obtain survey, interview and medical record audit data. Data were collected during 2004 and 2005.
Findings. Comorbidity care was poorly co-ordinated prior to having surgery, during the acute care stay and following surgery and primarily entailed prescribed medicines. The main focus in acute care was patient throughput following joint replacement surgery according to a prescribed clinical pathway. General wellbeing was less than optimal: participants reported pain, fatigue, insomnia and alterations in urinary elimination as the chief sources of discomfort during the course of the study.
Conclusion. Continuity of care of comorbidities was lacking. Comorbidities affected patient general wellbeing and delayed recovery from surgery. Acute care, clinical pathways and the specialisation of medicine and nursing subordinated the general problem of patients with comorbidities. Systems designed to integrate and co-ordinate chronic illness care had limited application in the acute care setting. A multidisciplinary, holistic approach is required. Recommendations for further research conclude this paper.