Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry

Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes.

Multichannel biomedical time series clustering via hierarchical probabilistic latent semantic analysis

Biomedical time series clustering that automatically groups a collection of time series according to their internal similarity is of importance for medical record management and inspection such as bio-signals archiving and retrieval. In this paper, a novel framework that automatically groups a set of unlabelled multichannel biomedical time series according to their internal structural similarity is proposed. Specifically, we treat a multichannel biomedical time series as a document and extract local segments from the time series as words. We extend a topic model, i.e., the Hierarchical probabilistic Latent Semantic Analysis (H-pLSA), which was originally developed for visual motion analysis to cluster a set of unlabelled multichannel time series. The H-pLSA models each channel of the multichannel time series using a local pLSA in the first layer. The topics learned in the local pLSA are then fed to a global pLSA in the second layer to discover the categories of multichannel time series. Experiments on a dataset extracted from multichannel Electrocardiography (ECG) signals demonstrate that the proposed method performs better than previous state-of-the-art approaches and is relatively robust to the variations of parameters including length of local segments and dictionary size. Although the experimental evaluation used the multichannel ECG signals in a biometric scenario, the proposed algorithm is a universal framework for multichannel biomedical time series clustering according to their structural similarity, which has many applications in biomedical time series management.

Minimising post-operative risk using a Post-Anaesthetic Care Tool (PACT): protocol for a prospective observational study and cost-effectiveness analysis

Introduction: While the risk of adverse events following surgery has been identified, the impact of nursing care on early detection of these events is not well established. A systematic review of the evidence and an expert consensus study in post-anaesthetic care identified essential criteria for nursing assessment of patient readiness for discharge from the Post-Anaesthetic Care Unit. These criteria were included in a new nursing assessment tool, the Post-Anaesthetic Care Tool (PACT), and incorporated into the post-anaesthetic documentation at a large health service. The aim of this study is to test the clinical reliability of the PACT and evaluate whether use of PACT will i) enhance the recognition and response to patients at risk of deterioration in PACU; ii) improve documentation for handover from PACU nurse to ward nurse; iii) result in improved patient outcomes; and iv) reduce health care costs.

Methods and analysis: A prospective, non-randomised, pre- and post-implementation design comparing: (i) patients (n=750) who have surgery prior to the implementation of the PACT and (ii) patients (n=750) who have surgery after PACT. The study will examine the use of the tool through the observation of patient care and nursing handover. Patient outcomes and cost effectiveness will be determined from health service data and medical record audit. Descriptive statistics will be used to describe the sample and compare the two patient groups (pre- and post-intervention). Differences in patient outcomes between the two groups will be compared using the Cochran-Mantel-Haenszel test and regression analyses and reported as odds ratios with the corresponding 95% confidence intervals.

Conclusion: This study will test the clinical reliability and cost-effectiveness of the PACT. It is hypothesised that the PACT will enable nurses to recognise and respond to patients at risk of deterioration, improve handover to ward nurses, improve patient outcomes, and reduce health care costs.

Using clinical trial data and linked administrative health data to reduce the risk of adverse events associated with the uptake of newly released drugs by older Australians: a model process

BACKGROUND: The study was undertaken to evaluate the contribution of a process which uses clinical trial data plus linked de-identified administrative health data to forecast potential risk of adverse events associated with the use of newly released drugs by older Australian patients. METHODS: The study uses publicly available data from the clinical trials of a newly released drug to ascertain which patient age groups, gender, comorbidities and co-medications were excluded in the trials. It then uses linked de-identified hospital morbidity and medications dispensing data to investigate the comorbidities and co-medications of patients who suffer from the target morbidity of the new drug and who are the likely target population for the drug. The clinical trial information and the linked morbidity and medication data are compared to assess which patient groups could potentially be at risk of an adverse event associated with use of the new drug. RESULTS: Applying the model in a retrospective real-world scenario identified that the majority of the sample group of Australian patients aged 65 years and over with the target morbidity of the newly released COX-2-selective NSAID rofecoxib also suffered from a major morbidity excluded in the trials of that drug, indicating a substantial potential risk of adverse events amongst those patients. This risk was borne out in post-release morbidity and mortality associated with use of that drug. CONCLUSIONS: Clinical trial data and linked administrative health data can together support a prospective assessment of patient groups who could be at risk of an adverse event if they are prescribed a newly released drug in the context of their age, gender, comorbidities and/or co-medications. Communication of this independent risk information to prescribers has the potential to reduce adverse events in the period after the release of the new drug, which is when the risk is greatest.Note: The terms 'adverse drug reaction' and 'adverse drug event' have come to be used interchangeably in the current literature. For consistency, the authors have chosen to use the wider term 'adverse drug event' (ADE).

The extra resource burden of in-hospital falls: a cost of falls study

OBJECTIVE: To quantify the additional hospital length of stay (LOS) and costs associated with in-hospital falls and fall injuries in acute hospitals in Australia. DESIGN, SETTING AND PARTICIPANTS: A multisite prospective cohort study conducted during 2011-2013 in the control wards of a falls prevention trial (6-PACK). The trial included all admissions to 12 acute medical and surgical wards of six Australian hospitals. In-hospital falls data were collected from medical record reviews, daily verbal reports by ward nurse unit managers, and hospital incident reporting and administrative databases. Clinical costing data were linked for three of the six participating hospitals to calculate patient-level costs. OUTCOME MEASURES: Hospital LOS and costs associated with in-hospital falls and fall injuries for each patient admission. RESULTS: We found that 966 of a total of 27 026 hospital admissions (3.6%) involved at least one fall, and 313 (1.2%) at least one fall injury, a total of 1330 falls and 418 fall injuries. After adjustment for age, sex, cognitive impairment, admission type, comorbidity and clustering by hospital, patients who had an in-hospital fall had a mean increase in LOS of 8 days (95% CI, 5.8-10.4; P < 0.001) compared with non-fallers, and incurred mean additional hospital costs of $6669 (95% CI, $3888-$9450; P < 0.001). Patients with a fall-related injury had a mean increase in LOS of 4 days (95% CI, 1.8-6.6; P = 0.001) compared with those who fell without injury, and there was also a tendency to additional hospital costs (mean, $4727; 95% CI, -$568 to $10 022; P = 0.080). CONCLUSION: Patients who experience an in-hospital fall have significantly longer hospital stays and higher costs. Programs need to target the prevention of all falls, not just the reduction of fall-related injuries.

Implementing guidelines to routinely prevent chronic vascular disease in primary care: the preventive evidence into practice cluster randomised controlled trial

Objective: To evaluate an intervention to improve implementation of guidelines for the prevention of chronic vascular disease. Setting: 32 urban general practices in 4 Australian states. Randomisation: Stratified randomisation of practices. Participants: 122 general practitioners (GPS) and practice nurses (PNs) were recruited at baseline and 97 continued to 12 months. 21 848 patient records were audited for those aged 40-69 years who attended the practice in the previous 12 months without heart disease, stroke, diabetes, chronic renal disease, cognitive impairment or severe mental illness. Intervention: The practice level intervention over 6 months included small group training of practice staff, feedback on audited performance, practice facilitation visits and provision of patient education and referral information. Outcome measures: Primary: 1. Change in proportion of patients aged 40-69 years with smoking status, alcohol intake, body mass index (BMI), waist circumference (WC), blood pressure (BP) recorded and for those aged 45-69 years with lipids, fasting blood glucose and cardiovascular risk in the medical record. 2. Change in the level of risk for each factor. Secondary: change in self-reported frequency and confidence of GPS and PNs in assessment. Results: Risk recording improved in the intervention but not the control group for WC (OR 2.52 (95% CI 1.30 to 4.91)), alcohol consumption (OR 2.19 (CI 1.04 to 4.64)), smoking status (OR 2.24 (1.17 to 4.29)) and cardiovascular risk (OR 1.50 (1.04 to 2.18)). There was no change in recording of BP, lipids, glucose or BMI and no significant change in the level of risk factors based on audit data. The confidence but not reported practices of GPS and PNs in the intervention group improved in the assessment of some risk factors. Conclusions: This intervention was associated with improved recording of some risk factors but no change in the level of risk at the follow-up audit. Trial registration number: Australian and New Zealand Clinical Trials Register (ANZCTR): ACTRN12612000578808, results.

A atuação do psicólogo no contexto das referências ambulatoriais em saúde mental de Aracaju - SE

Psychologists‟ insertion in mental healthcare ambulatory clinics occurred during the decade of 1980, in the context of the claims disseminated by sanitary and psychiatric reforms, of the formation of minimum mental healthcare teams and of the retraction of the private clinic. Historically, this migration had been accompanied by the importation of practices traditionally applied at the clinics. Furthermore, the lack of clear guidelines from the Health Ministery occasioned the opening of ambulatory clinics with diversified structures at each city. The objective of this dissertation was to study the practices of psychologists at mental healthcare ambulatory references at Aracaju-SE. Were interviewed psychologists of these services and managers of the municipal health secretary using a semi-structured interview guideline, in addition to the analysis of management reports. It was observed that the mental healthcare references had experienced substantial changes referred to its structures and operation, leading to a present framework of expansion and readjustment. It was realized that there is an effort by the psychologists to maintain individual and group assistance, using adjustments in the frequency of the sessions and in the focus of the activities. Besides the progresses, the relation with the psychiatrist still works basically through the medical record, blocking advances on joint discussions of the cases. Some advances toward the amplified clinic are notable, like the overcoming of the isolated usage of psychiatric diagnostic and the replacement of the line‟ criterion by the urgency one. Sheltering had become an interesting strategy on flux ordination, however the mismatch between offer and demand seems to be a matter which extrapolates the psychologists‟ sphere at the references. For this reason the narrow of the relation with family healthcare centers seems to be the major challenge to be faced by psychologists at mental healthcare ambulatory references

Clinical and pathological assessment of 82 patients with cardiovascular diseases undergoing autopsy at the Hospital das Clínicas of the Faculdade de Medicina de Botucatu from 1988 to 1993

OBJECTIVE: To evaluated the clinical diagnostic, efficiency for basic death causes in patients dying of circulatory disease and de relative frequency of those diseases. METHODS: Analysis of medical record data of 82 patients, ages from 16 to 84 years old (68 over 40 years old), whose died of circulatory disease and had undergone necropsy in the period from 1988 to 1993 years in the University Hospital of Medicine Faculty of Botucatu-UNESP, Br. RESULTS: The functional class of patients were III or IV, in 78%, and 81.7% needed urgent hospitalization. By the clinical judgment the death were by ischemic heart disease in 32 (21 acute myocardial infarction), Chagas'disease in 12, valvopathy in 11, cardiomyopathy in 7, heart failure with no specification of cardiopathy in 11 and other causes in 9. At the necropsy the death cause was ischemic heart disease in 34 patients, valvopathy in 10, Chagas'disease in 10, cardiomyopathy in 5, and heart failure with no specification of cardiopathy in 2.The concordance taxes were in thhe same order: 94,6%, 90,0%, 83.3%, 71.4% and 28.5%. CONCLUSION: There was a great efficiency of clinical diagnosis for death cause in a general university hospital. The ischemic heart disease were the main causes of death.

Prevenção de conflitos médico-legais no exercício da medicina

Os conflitos médico-legais que ocorrem no exercício da Cirurgia e da Medicina são motivos de preocupação não só no meio médico, mas também na sociedade como um todo, pois se de um lado geram um maior desgaste emocional ao médico, por outro, os pacientes estão sendo rejeitados. As causas desses conflitos são muitas, envolvendo fatores não assistenciais, como o sistema de saúde distorcido e desorganizado, a falta de participação da sociedade e do médico na melhoria desse sistema, o aparelho formador que lança no mercado grande número de jovens médicos despreparados para o exercício dessa nobre profissão, além da falta do ensino continuado. A solução para esses conflitos não poderá ser por meio de simples criação de leis, e nem pela negativa da existência do erro médico, que ocorre numa freqüência até maior do que os próprios conflitos. Todavia, pode-se afirmar que é muito importante melhorar a relação médico-paciente. É necessário, ainda, que o médico conheça a fundo seus deveres de conduta e que, principalmente, se abstenha de praticar abusos do poder. A sociedade deve também entender que a saúde não é uma questão exclusiva dos médicos e que deve lutar pela melhoria das condições dos níveis de vida.

Influência da terapêutica hormonal prévia sobre os indicadores de prognóstico do câncer de mama em mulheres na pós-menopausa

OBJETIVO: avaliar a influência da terapêutica hormonal (TH) prévia sobre alguns indicadores de prognóstico do câncer de mama, em pacientes na pós-menopausa. MÉTODOS: estudo transversal por meio da aplicação de questionários e levantamento de prontuários. Foram entrevistadas 157 pacientes com diagnóstico de câncer de mama na pós-menopausa, registrando-se dados clínicos, antecedentes pessoais e familiares, uso de TH e mamografias. Nos prontuários foram obtidas informações sobre o câncer de mama quanto ao diâmetro do tumor, tipo de cirurgia e estudo imuno-histoquímico. Para a estatística empregou-se ANOVA e teste do chi2. RESULTADOS: 38,2% das pacientes eram ex-usuárias de TH e 61,8% não usuárias. O tempo médio de uso da TH foi de 3,7±3,6 anos. As ex-usuárias eram de menor faixa etária e com menor tempo de menopausa quando comparadas às não usuárias (p<0,05). Constatou-se que 26,8% das pacientes apresentavam antecedentes familiares de câncer de mama, em ambos os grupos. Entre as ex-usuárias de TH, 43,3% foram submetidas a mamografias prévias, ao passo que entre as não usuárias, apenas 11,3% (p<0,001). O diâmetro médio do tumor foi menor entre as ex-usuárias de TH (2,3±1,1 cm), com predomínio de quadrantectomias (60%), quando comparadas as não usuárias (3,3±1,5 cm e 32%, respectivamente) (p<0,001). No estudo imuno-histoquímico, observou-se correlação positiva entre a presença de receptores de estrogênio e progesterona positivos e o uso de TH (p<0,001). Não houve correlação entre TH e c-erbB-2 e p53. CONCLUSÃO: nesta casuística, as mulheres na pós-menopausa que usaram TH prévia ao diagnóstico de câncer de mama apresentaram indicadores de prognóstico mais favoráveis quando comparadas às não usuárias.

Preoperative combined with intraoperative skin-surface warming avoids hypothermia caused by general anesthesia and surgery

Study Objectives: To evaluate the effects of intraoperative skin-surface warming with and without 1 hour of preoperative warming, in preventing intraoperative hypothermia, and postoperative hypothermia, and shivering, and in offering good conditions to early tracheal extubation. Design: Prospective, randomized, blind study. Setting: Teaching hospital. Patients: 30 ASA physical status I and II female patients scheduled for elective abdominal surgery. Interventions: Patients received standard general anesthesia. In 10 patients, no special precautions were taken to avoid hypothermia. Ten patients were submitted to preoperative and intraoperative active warming. Ten patients were only warmed intraoperatively. Measurements and Main Results: Temperatures were recorded at 15-minute intervals. The patients who were warmed preoperatively and intraoperatively had core temperatures significantly more elevated than the other patients during the first two hours of anesthesia. All patients warmed intraoperatively were normothermic only at the end of the surgery. The majority of the patients warmed preoperatively and intraoperatively or intraoperatively only were extubated early, and none had shivering. In contrast, five unwarmed patients shivered. Conclusions: One hour of preoperative warning combined with intraoperative skin-surface warming, not simply intraoperative warming alone, avoided hypothermia caused by general anesthesia during the first two hours of surgery. Both methods prevented postoperative hypothermia and shivering and offered good conditions for early tracheal extubation. © 2003 by Elsevier B.V.