Real-Time decision support using data mining to predict blood pressure critical events in intensive medicine patients

Patient blood pressure is an important vital signal to the physicians take a decision and to better understand the patient condition. In Intensive Care Units is possible monitoring the blood pressure due the fact of the patient being in continuous monitoring through bedside monitors and the use of sensors. The intensivist only have access to vital signs values when they look to the monitor or consult the values hourly collected. Most important is the sequence of the values collected, i.e., a set of highest or lowest values can signify a critical event and bring future complications to a patient as is Hypotension or Hypertension. This complications can leverage a set of dangerous diseases and side-effects. The main goal of this work is to predict the probability of a patient has a blood pressure critical event in the next hours by combining a set of patient data collected in real-time and using Data Mining classification techniques. As output the models indicate the probability (%) of a patient has a Blood Pressure Critical Event in the next hour. The achieved results showed to be very promising, presenting sensitivity around of 95%.

The Role of B-Type Natriuretic Peptide in the Diagnosis of Congestive Heart Failure in Patients Presenting to an Emergency Department with Dyspnea

OBJECTIVE: To determine the utility of B-type natriuretic peptide (BNP) in the diagnosis of congestive heart failure (CHF) in patients presenting with dyspnea to an emergency department (ED). METHODS: Seventy patients presenting with dyspnea to an ED from April to July 2001 were included in the study. Mean age was 72±16 years and 33 (47%) were male. BNP was measured in all patients at the moment of admission to the ED. Emergency-care physicians, blinded to BNP values, were required to assign a probable initial diagnosis. A cardiologist retrospectively reviewed the data (blinded to BNP measurements) and assigned a definite diagnosis, which was considered the gold standard for assessing the diagnostic performance of BNP. RESULTS: The mean BNP concentration was higher in patients with CHF (n=36) than in those with other diagnoses (990±550 vs 80±67 pg/mL, p<0.0001). Patients with systolic dysfunction had higher BNP levels than those with preserved systolic function (1,180±641 vs 753±437 pg/mL, p=0.03). At a blood concentration of 200 pg/mL, BNP showed a sensitivity of 100%, specificity of 97.1%, positive predictive value of 97.3%, and negative predictive value of 100%. The application of BNP could have potentially corrected all 16 cases in which the diagnosis was missed by the emergency department physician. CONCLUSION: BNP measurement is a useful tool in the diagnosis of CHF in patients presenting to the ED with dyspnea.

Stress During ACLS Courses: Is it Important for Learning Skills?

OBJECTIVE: To determine the influence of stress on teaching medical emergencies in an Advanced Cardiac Life Support (ACLS) course and to verify this influence on learning, and the efficiency of emergency care training. METHODS: Seventeen physicians signed up for an ACLS course. Their pulses were taken and blood pressure (BP) verified on the first day, before the beginning of the course, and on the second day, during the theoretical and practical test (TPT). Variations in pulse rates and BP were compared with students' test grades. Then, students answered a questionnaire of variables (QV) about the amount of sleep they had during the course, the quantity of study material and the time spent studying for the course, and a stress scale graphic. RESULTS: Seven students had a pulse variation less than 10% between the 2 periods and 10 had a 10% or more variation. Grades on TPT were, respectively, 91.4±2.4 and 87.3±5.2 (p<0.05). Six students had a BP variation less than 20 mmHg, and in 11 it varied more than 21 mmHg. Grades on the TPT were 92.3±3.3 and 86.2± 8.1, respectively (p<0.05). The QV dates did not significantly influence grades. CONCLUSION: Stress, as an isolated variable, had a negative influence on the learning process and on the efficiency of emergency training in this situation.

Assessment of the techniques of blood pressure measurement by health professionals

OBJECTIVE: To assess blood pressure measurement by health professionals of a public hospital in São Paulo State. METHODS: Semi-structured interviews and direct observation were performed with a verification list according to the criteria reported by Perloff et al. One hundred and five health professionals took part in the study. After measuring blood pressure, the level of concordance between the way the procedure was performed and the recommended one was assessed. RESULTS: Nurses and nurse's aides abided by 40% of the recommended procedures for adequate blood pressure measurement. The other categories of health professionals (nursing and medicine teachers, physicians, residents, and nursing students) abided by approximately 70%. CONCLUSION: Permanent educational activities aiming at standardizing blood pressure measurement should be implemented among the different categories of health professionals.

The influence of patient's consciousness regarding high blood pressure and patient's attitude in face of disease controlling medicine intake

OBJECTIVE: To assess the relation between blood pressure control and the following: the Morisky-Green test, the patient's consciousness regarding high blood pressure, the patient's attitude in face of medicine intake, the patient's attendance at medical consultations, and the subjective physician's judgment. METHODS: We studied 130 hypertensive patients with the following characteristics: 73% females, 60±11 years, 58% married, 70% white, 45% retired, 45% with incomplete elementary schooling, 64% had a familial income of 1 to 3 minimum wages, body mass index of 30±7 kg/m², consciousness regarding the disease for a mean period of 11±9.5 years, and mean treatment duration of 8 ±7 years. RESULTS: Only 35% of the hypertensive individuals had blood pressure under control and a longer duration of treatment (10±7 vs 7±6.5 years; P<0.05). The retiree predominated. The result of the Morisky-Green test did not relate to blood pressure control. In evaluating the attitude in face of medicine intake, the controlled patients achieved significantly higher scores than did the noncontrolled patients (8±1.9 vs 7 ±2, P<0.05). The hypertensive patients had higher levels of consciousness regarding their disease and its treatment, and most (70%) patients attended 3 or 4 medical consultations, which did not influence blood pressure control. The physicians attributed significantly higher scores regarding adherence to treatment to controlled patients (6±0.8 vs 5±1.2; P<0.05). CONCLUSION: Consciousness regarding the disease, the Morisky-Green test, and attendance to medical consultations did not influence blood pressure control.

Stroke

Stroke is a preventable and treatable disease. It can present with the sudden onset of any neurological disturbance, including limb weakness or numbness, speech disturbance, visual loss or disturbance of balance. Over the last two decades, a growing body of evidence has overturned the traditional perception that stroke is simply a consequence of aging which inevitably results in death or severe disability. Evidence is accumulating for more effective primary and secondary prevention strategies, better recognition of people at highest risk and thus most in need of active intervention, interventions that are effective so on after the onset of symptoms, and an understanding of the processes of care that contribute to a better outcome. In addition, there is now good evidence to support interventions and care processes in stroke rehabilitation. In the UK, the National Sentinel Stroke Audits 2,3 have documented changes in secondary care provision over the last 10 years, with increasing numbers of patients being treated in stroke units, more evidence-based practice, and reductions in mortality and length of stay. In order for evidence from research studies to improve outcomes for patients, it needs to be put into practice. National guidelines provide clinicians, managers and service users with summaries of evidence and recommendations for clinical practice. Implementation of guidelines in practice, supported by regular audit, improves the processes of care and clinical outcome. This guideline covers interventions in the acute stage of a stroke (‘acute stroke’) or transient ischaemic attack (TIA). Most of the evidence considered relates to interventions in the first 48 hours after onset of symptoms, although some interventions of up to 2 weeks are covered as well. This guideline is a stand-alone document, but is designed to be read alongside the Intercollegiate Stroke Working Party guideline ‘National clinical guideline for stroke’* which considers evidence for interventions from the acute stage into rehabilitation and life after stroke. The Intercollegiate Stroke Working Party guideline is an update of the 2004 2nd edition and includes all the recommendations contained within this guideline. This acute stroke and TIA guideline is also designed to be read alongside the Department of Health’s (DH) ‘National stroke strategy’ (NSS). Where there are differences between the recommendations made within this acute stroke and TIA guideline and the NSS, the Guideline Development Group (GDG) members feel that their recommendations are derived from systematic methodology to identify all of the relevant literature.

Managed Care in der Schweiz : eine empirische Analyse des Verhaltens von Allgemeinmedizinern

Managed Care, physicians' behavior, primary practice, efficiency, econometric analysis

Applicability of the Appropriate use Criteria for Myocardial Perfusion Scintigraphy

Background: Appropriateness Criteria for nuclear imaging exams were created by American College of Cardiology (ACC) e American Society of Nuclear Cardiology (ASNC) to allow the rational use of tests. Little is known whether these criteria have been followed in clinical practice. Objective: To evaluate whether the medical applications of myocardial perfusion scintigraphy (MPS) in a private nuclear medicine service of a tertiary cardiology hospital were suitable to the criteria of indications proposed by the American medical societies in 2005 and 2009 and compare the level of indication of both. Methods: We included records of 383 patients that underwent MPS, November 2008 up to February 2009. Demographic characteristics, patient's origin, coronary risk factors, time of medical graduation and appropriateness criteria of medical applications were studied. The criteria were evaluated by two independent physicians and, in doubtful cases, defined by a medical expert in MPS. Results: Mean age was 65 ± 12 years. Of the 367 records reviewed, 236 (64.3%) studies were performed in men and 75 (20.4%) were internee. To ACC 2005, 255 (69.5%) were considered appropriate indication and 13 (3.5%) inappropriate. With ACC 2009, 249 (67.8%) were considered appropriate indications and 13 (5.2%) inappropriate. Conclusions: We observed a high rate of adequacy of medical indications for MPS. Compared to the 2005 version, 2009 did not change the results.

Comparison of Cardiovascular Risk Factors in Different Areas of Health Care Over a 20-Year Period

Background:Cardiovascular diseases (CVDs) are the leading cause of death worldwide. Knowledge about cardiovascular risk factors (CVRFs) in young adults and their modification over time are measures that change the risks and prevent CVDs.Objectives:To determine the presence of CVRFs and their changes in different health care professionals over a period of 20 years.Methods:All students of medicine, nursing, nutrition, odontology, and pharmacy departments of Federal University of Goiás who agreed to participate in this study were evaluated when they started their degree courses and 20 years afterward. Questionnaires on CVRFs [systemic arterial hypertension (SAH), diabetes mellitus, dyslipidemia, and family history of early CVD, smoking, alcohol consumption, and sedentarism] were administered. Cholesterol levels, blood sugar levels, blood pressure, weight, height, and body mass index were determined. The Kolmogorov-Smirnov test was used to evaluate distribution, the chi-square test was used to compare different courses and sexes, and the McNemar test was used for comparing CVRFs. The significance level was set at a p value of < 0.05.Results:The first stage of the study included 281 individuals (91% of all the students), of which 62.9% were women; the mean age was 19.7 years. In the second stage, 215 subjects were reassessed (76% of the initial sample), of which 59.07% were women; the mean age was 39.8 years. The sample mostly consisted of medical students (with a predominance of men), followed by nursing, nutrition, and pharmacy students, with a predominance of women (p < 0.05). Excessive weight gain, SAH, and dyslipidemia were observed among physicians and dentists (p < 0.05). Excessive weight gain and SAH and a reduction in sedentarism (p < 0.05) were observed among pharmacists. Among nurses there was an increase in excessive weight and alcohol consumption (p < 0.05). Finally, nutritionists showed an increase in dyslipidemia (p < 0.05).Conclusion:In general, there was an unfavorable progression of CVRFs in the population under study, despite it having adequate specialized knowledge about these risk factors.

Some things couples always wanted to know about stable matchings (but were afraid to ask)

It is well-known that couples that look jointly for jobs in the same centralized labor market may cause instabilities. We demonstrate that for a natural preference domain for couples, namely the domain of responsive preferences, the existence of stable matchings can easily be established. However, a small deviation from responsiveness in one couple's preference relation that models the wish of a couple to be closer together may already cause instability. This demonstrates that the nonexistence of stable matchings in couples markets is not a singular theoretical irregularity. Our nonexistence result persists even when a weaker stability notion is used that excludes myopic blocking. Moreover, we show that even if preferences are responsive there are problems that do not arise for singles markets. Even though for couples markets with responsive preferences the set of stable matchings is nonempty, the lattice structure that this set has for singles markets does not carry over. Furthermore we demonstrate that the new algorithm adopted by the National Resident Matching Program to fill positions for physicians in the United States may cycle, while in fact a stable matchings does exist, and be prone to strategic manipulation if the members of a couple pretend to be single.

Optimal regulation of specialized medical care in a mixed system

We study the optimal public intervention in setting minimum standards of formation for specialized medical care. The abilities the physicians obtain by means of their training allow them to improve their performance as providers of cure and earn some monopoly rents.. Our aim is to characterize the most efficient regulation in this field taking into account different regulatory frameworks. We find that the existing situation in some countries, in which the amount of specialization is controlled, and the costs of this process of specialization are publicly financed, can be supported as the best possible intervention.

Evaluation de la douleur chez les personnes cérébrolésées non-communicantes aux soins intensifs

La douleur est fréquente en milieu de soins intensifs et sa gestion est l'une des missions des infirmières. Son évaluation est une prémisse indispensable à son soulagement. Cependant lorsque le patient est incapable de signaler sa douleur, les infirmières doivent se baser sur des signes externes pour l'évaluer. Les guides de bonne pratique recommandent chez les personnes non communicantes l'usage d'un instrument validé pour la population donnée et basé sur l'observation des comportements. A l'heure actuelle, les instruments d'évaluation de la douleur disponibles ne sont que partiellement adaptés aux personnes cérébrolésées dans la mesure où ces personnes présentent des comportements qui leur sont spécifiques. C'est pourquoi, cette étude vise à identifier, décrire et valider des indicateurs, et des descripteurs, de la douleur chez les personnes cérébrolésées. Un devis d'étude mixte multiphase avec une dominante quantitative a été choisi pour cette étude. Une première phase consistait à identifier des indicateurs et des descripteurs de la douleur chez les personnes cérébrolésées non communicantes aux soins intensifs en combinant trois sources de données : une revue intégrative des écrits, une démarche consultative utilisant la technique du groupe nominal auprès de 18 cliniciens expérimentés (6 médecins et 12 infirmières) et les résultats d'une étude pilote observationnelle réalisée auprès de 10 traumatisés crâniens. Les résultats ont permis d'identifier 6 indicateurs et 47 descripteurs comportementaux, vocaux et physiologiques susceptibles d'être inclus dans un instrument d'évaluation de la douleur destiné aux personnes cérébrolésées non- communicantes aux soins intensifs. Une deuxième phase séquentielle vérifiait les propriétés psychométriques des indicateurs et des descripteurs préalablement identifiés. La validation de contenu a été testée auprès de 10 experts cliniques et 4 experts scientifiques à l'aide d'un questionnaire structuré qui cherchait à évaluer la pertinence et la clarté/compréhensibilité de chaque descripteur. Cette démarche a permis de sélectionner 33 des 47 descripteurs et valider 6 indicateurs. Dans un deuxième temps, les propriétés psychométriques de ces indicateurs et descripteurs ont été étudiés au repos, lors de stimulation non nociceptive et lors d'une stimulation nociceptive (la latéralisation du patient) auprès de 116 personnes cérébrolésées aux soins intensifs hospitalisées dans deux centres hospitaliers universitaires. Les résultats montrent d'importantes variations dans les descripteurs observés lors de stimulation nociceptive probablement dues à l'hétérogénéité des patients au niveau de leur état de conscience. Dix descripteurs ont été éliminés, car leur fréquence lors de la stimulation nociceptive était inférieure à 5% ou leur fiabilité insuffisante. Les descripteurs physiologiques ont tous été supprimés en raison de leur faible variabilité et d'une fiabilité inter juge problématique. Les résultats montrent que la validité concomitante, c'est-à-dire la corrélation entre l'auto- évaluation du patient et les mesures réalisées avec les descripteurs, est satisfaisante lors de stimulation nociceptive {rs=0,527, p=0,003, n=30). Par contre la validité convergente, qui vérifiait l'association entre l'évaluation de la douleur par l'infirmière en charge du patient et les mesures réalisés avec les descripteurs, ainsi que la validité divergente, qui vérifiait si les indicateurs discriminent entre la stimulation nociceptive et le repos, mettent en évidence des résultats variables en fonction de l'état de conscience des patients. Ces résultats soulignent la nécessité d'étudier les descripteurs de la douleur chez des patients cérébrolésés en fonction du niveau de conscience et de considérer l'hétérogénéité de cette population dans la conception d'un instrument d'évaluation de la douleur pour les personnes cérébrolésées non communicantes aux soins intensifs. - Pain is frequent in the intensive care unit (ICU) and its management is a major issue for nurses. The assessment of pain is a prerequisite for appropriate pain management. However, pain assessment is difficult when patients are unable to communicate about their experience and nurses have to base their evaluation on external signs. Clinical practice guidelines highlight the need to use behavioral scales that have been validated for nonverbal patients. Current behavioral pain tools for ICU patients unable to communicate may not be appropriate for nonverbal brain-injured ICU patients, as they demonstrate specific responses to pain. This study aimed to identify, describe and validate pain indicators and descriptors in brain-injured ICU patients. A mixed multiphase method design with a quantitative dominant was chosen for this study. The first phase aimed to identify indicators and descriptors of pain for nonverbal brain- injured ICU patients using data from three sources: an integrative literature review, a consultation using the nominal group technique with 18 experienced clinicians (12 nurses and 6 physicians) and the results of an observational pilot study with 10 traumatic brain injured patients. The results of this first phase identified 6 indicators and 47 behavioral, vocal and physiological descriptors of pain that could be included in a pain assessment tool for this population. The sequential phase two tested the psychometric properties of the list of previously identified indicators and descriptors. Content validity was tested with 10 clinical and 4 scientific experts for pertinence and comprehensibility using a structured questionnaire. This process resulted in 33 descriptors to be selected out of 47 previously identified, and six validated indicators. Then, the psychometric properties of the descriptors and indicators were tested at rest, during non nociceptive stimulation and nociceptive stimulation (turning) in a sample of 116 brain-injured ICLI patients who were hospitalized in two university centers. Results showed important variations in the descriptors observed during the nociceptive stimulation, probably due to the heterogeneity of patients' level of consciousness. Ten descriptors were excluded, as they were observed less than 5% of the time or their reliability was insufficient. All physiologic descriptors were deleted as they showed little variability and inter observer reliability was lacking. Concomitant validity, testing the association between patients' self report of pain and measures performed using the descriptors, was acceptable during nociceptive stimulation (rs=0,527, p=0,003, n=30). However, convergent validity ( testing for an association between the nurses' pain assessment and measures done with descriptors) and divergent validity (testing for the ability of the indicators to discriminate between rest and a nociceptive stimulation) varied according to the level of consciousness These results highlight the need to study pain descriptors in brain-injured patients with different level of consciousness and to take into account the heterogeneity of this population forthe conception of a pain assessment tool for nonverbal brain-injured ICU patients.

Non-assisted versus neuro-navigated and XperCT-guided external ventricular catheter placement: a comparative cadaver study.

BACKGROUND AND PURPOSE: Accurate placement of an external ventricular drain (EVD) for the treatment of hydrocephalus is of paramount importance for its functionality and in order to minimize morbidity and complications. The aim of this study was to compare two different drain insertion assistance tools with the traditional free-hand anatomical landmark method, and to measure efficacy, safety and precision. METHODS: Ten cadaver heads were prepared by opening large bone windows centered on Kocher's points on both sides. Nineteen physicians, divided in two groups (trainees and board certified neurosurgeons) performed EVD insertions. The target for the ventricular drain tip was the ipsilateral foramen of Monro. Each participant inserted the external ventricular catheter in three different ways: 1) free-hand by anatomical landmarks, 2) neuronavigation-assisted (NN), and 3) XperCT-guided (XCT). The number of ventricular hits and dangerous trajectories; time to proceed; radiation exposure of patients and physicians; distance of the catheter tip to target and size of deviations projected in the orthogonal plans were measured and compared. RESULTS: Insertion using XCT increased the probability of ventricular puncture from 69.2 to 90.2 % (p = 0.02). Non-assisted placements were significantly less precise (catheter tip to target distance 14.3 ± 7.4 mm versus 9.6 ± 7.2 mm, p = 0.0003). The insertion time to proceed increased from 3.04 ± 2.06 min. to 7.3 ± 3.6 min. (p < 0.001). The X-ray exposure for XCT was 32.23 mSv, but could be reduced to 13.9 mSv if patients were initially imaged in the hybrid-operating suite. No supplementary radiation exposure is needed for NN if patients are imaged according to a navigation protocol initially. CONCLUSION: This ex vivo study demonstrates a significantly improved accuracy and safety using either NN or XCT-assisted methods. Therefore, efforts should be undertaken to implement these new technologies into daily clinical practice. However, the accuracy versus urgency of an EVD placement has to be balanced, as the image-guided insertion technique will implicate a longer preparation time due to a specific image acquisition and trajectory planning.

Screening primary-care patients forgoing health care for economic reasons.

BACKGROUND: Growing social inequities have made it important for general practitioners to verify if patients can afford treatment and procedures. Incorporating social conditions into clinical decision-making allows general practitioners to address mismatches between patients' health-care needs and financial resources. OBJECTIVES: Identify a screening question to, indirectly, rule out patients' social risk of forgoing health care for economic reasons, and estimate prevalence of forgoing health care and the influence of physicians' attitudes toward deprivation. DESIGN: Multicenter cross-sectional survey. PARTICIPANTS: Forty-seven general practitioners working in the French-speaking part of Switzerland enrolled a random sample of patients attending their private practices. MAIN MEASURES: Patients who had forgone health care were defined as those reporting a household member (including themselves) having forgone treatment for economic reasons during the previous 12 months, through a self-administered questionnaire. Patients were also asked about education and income levels, self-perceived social position, and deprivation levels. KEY RESULTS: Overall, 2,026 patients were included in the analysis; 10.7% (CI95% 9.4-12.1) reported a member of their household to have forgone health care during the 12 previous months. The question "Did you have difficulties paying your household bills during the last 12 months" performed better in identifying patients at risk of forgoing health care than a combination of four objective measures of socio-economic status (gender, age, education level, and income) (R(2) = 0.184 vs. 0.083). This question effectively ruled out that patients had forgone health care, with a negative predictive value of 96%. Furthermore, for physicians who felt powerless in the face of deprivation, we observed an increase in the odds of patients forgoing health care of 1.5 times. CONCLUSION: General practitioners should systematically evaluate the socio-economic status of their patients. Asking patients whether they experience any difficulties in paying their bills is an effective means of identifying patients who might forgo health care.

Prévention des alcoolisations aiguës a l'adolescence: quel rôle pour le médecin de famille [Prevention of binge drinking in adolescents: do family doctors have a role to play?].

Binge drinking has nearly become the norm for young people and is thus worrying. Although alcohol use in males attracts more media attention, females are also frequently affected. A variety of preventive measures can be proposed: at the individual level by parents, peers and family doctors; at the school and community level, particularly to postpone age of first use and first episode of drunkenness; at the structural level through a policy restricting access to alcohol for young people and increasing its price. Family doctors can play an important role in identifying at risk users and individualising preventive messages to which these young people are exposed in other contexts.