Frederico Molina Cohrs

Artificial intelligence techniques applied to the development of a decision-support system for diagnosing celiac disease.

BACKGROUND Celiac disease (CD) is a difficult-to-diagnose condition because of its multiple clinical presentations and symptoms shared with other diseases. Gold-standard diagnostic confirmation of suspected CD is achieved by biopsying the small intestine. OBJECTIVE To develop a clinical decision-support system (CDSS) integrated with an automated classifier to recognize CD cases, by selecting from experimental models developed using intelligence artificial techniques. METHODS A web-based system was designed for constructing a retrospective database that included 178 clinical cases for training. Tests were run on 270 automated classifiers available in Weka 3.6.1 using five artificial intelligence techniques, namely decision trees, Bayesian inference, k-nearest neighbor algorithm, support vector machines and artificial neural networks. The parameters evaluated were accuracy, sensitivity, specificity and area under the ROC curve (AUC). AUC was used as a criterion for selecting the CDSS algorithm. A testing database was constructed including 38 clinical CD cases for CDSS evaluation. The diagnoses suggested by CDSS were compared with those made by physicians during patient consultations. RESULTS The most accurate method during the training phase was the averaged one-dependence estimator (AODE) algorithm (a Bayesian classifier), which showed accuracy 80.0%, sensitivity 0.78, specificity 0.80 and AUC 0.84. This classifier was integrated into the web-based decision-support system. The gold-standard validation of CDSS achieved accuracy of 84.2% and k=0.68 (p<0.0001) with good agreement. The same accuracy was achieved in the comparison between the physicians diagnostic impression and the gold standard k=0. 64 (p<0.0001). There was moderate agreement between the physicians diagnostic impression and CDSS k=0.46 (p=0.0008). CONCLUSIONS The study results suggest that CDSS could be used to help in diagnosing CD, since the algorithm tested achieved excellent accuracy in differentiating possible positive from negative CD diagnoses. This study may contribute towards developing of a computer-assisted environment to support CD diagnosis.

Comparação dos tempos de geração e digitação de laudos radiológicos entre um sistema eletrônico baseado em voz sobre IP (VoIP) e um sistema tradicional baseado em papel

OBJECTIVE: To compare the time required for generation and typing of radiology reports by means of an electronic system based on the technology of voice over internet protocol (VoIP) and the traditional system, in which the report is handwritten by the radiologist. MATERIALS AND METHODS: It was necessary to model, build and deploy the proposed electronic system, capable of recording the reports in a digital audio format and comparing it with the traditional method. Radiologists and transcriptionists recorded the reports generation and typing times for both systems, using appropriate forms. RESULTS: When the mean times between both systems were compared, those from the electronic system presented a reduction of 20% (p = 0.0410) in the report generation time as compared with the traditional method. On the other hand, the traditional method was more efficient with respect to typing time, as the mean typing time with the electronic system was three times longer (p < 0.0001). CONCLUSION: The results demonstrated a statistically significant difference between the compared systems, with the electronic system being more efficient than the traditional one with respect to report generation time, while the traditional method presented better results with respect to typing time.

Desenvolvimento e Avaliação de um Protocolo Eletrônico para Atendimento e Monitoramento do Paciente com Doença Celíaca

A clinical protocol is a set of guidelines aimed at standardizing the study of a medical case. It may include decision algorithms and therapies to be followed. Celiac disease is a permanent intolerance to gluten, a protein present in wheat, rye and barley. This disease affects genetically susceptible individuals and is characterized by a T-cells-mediated enteropathy. The diversity of signs and symptoms that the disease can present makes its diagnosing difficult. The goal of this study was to develop and evaluate the usability of a web-available electronic medical protocol containing structured information, specific to treating and monitoring patients with celiac disease. The electronic documents created for the current protocol were based on existing clinical forms and medical records, and on the study of a scientific document. A web computational system was modeled and implemented. The protocol usability was assessed through SUS questionnaire, which showed that the protocol met the requirements of its users (average usability score of 83.5% ± 10.0%). The electronic protocol proved to be clinically specific and effective, as the routine of the professionals involved was not disrupted and the expected medical specificity was maintained.

Infecção ou colonização por micro-organismos resistentes: identificação de preditores

OBJETIVO: Identificar os fatores preditores de infeccao ou colonizacao por micro-organismos resistentes. METODOS: Foi realizado estudo quantitativo de coorte prospectivo. Foram realizadas a analise descritiva, para conhecimento da populacao do estudo, e a analise discriminante, para identificacao dos fatores preditores. RESULTADOS: Foram incluidos 85 pacientes com infeccoes por micro-organismos resistentes: Pseudomonas aeruginosas resistente aos carbapenemicos (24,7%), Acinetobacter resistente aos carbapenemicos (21,2%), Staphylococcus aureus resistente a meticilina (25,9%), Enterococcus spp. resistente a vancomicina (17,6%) e Klebsiella pneumoniae resistente aos carbapenemicos (10,6%). A analise discriminante identificou transferencias de outros hospitais e internacao na Unidade de Terapia Intensiva como fatores preditores para ocorrencia de infeccao pelos grupos S. aureus resistente a meticilina, Acinetobacter resistente aos carbapenemicos e K. pneumoniae resistente aos carbapenemicos. Nenhuma das variaveis estudadas foi discriminante para Enterococcus spp. resistente a vancomicina e P. aeruginosas resistente aos carbapenemico. CONCLUSAO: Os fatores preditores encontrados foram: internacao na UTI e a transferencias de outros hospitais.

Artificial Intelligence Techniques: Predicting Necessity for Biopsy in Renal Transplant Recipients Suspected of Acute Cellular Rejection or Nephrotoxicity

The gold standard for nephrotoxicity and acute cellular rejection (ACR) is a biopsy, an invasive and expensive procedure. More efficient strategies to screen patients for biopsy are important from the clinical and financial points of view. The aim of this study was to evaluate various artificial intelligence techniques to screen for the need for a biopsy among patients suspected of nephrotoxicity or ACR during the first year after renal transplantation. We used classifiers like artificial neural networks (ANN), support vector machines (SVM), and Bayesian inference (BI) to indicate if the clinical course of the event suggestive of the need for a biopsy. Each classifier was evaluated by values of sensitivity and area under the ROC curve (AUC) for each of the classifiers. The technique that showed the best sensitivity value as an indicator for biopsy was SVM with an AUC of 0.79 and an accuracy rate of 79.86%. The results were better than those described in previous works. The accuracy for an indication of biopsy screening was efficient enough to become useful in clinical practice.

Avaliação de um sistema de segunda opinião em radiologia

OBJETIVO: A segunda opiniao medica pode auxiliar no processo de investigacao do problema de saude de um paciente e na definicao da conduta terapeutica. Este trabalho tem por objetivo demonstrar um processo de segunda opiniao medica por meio de um sistema web multiespecialidades adaptado para a radiologia. MATERIAIS E METODOS: O sistema foi utilizado por 49 medicos residentes da Universidade Federal de Sao Paulo, os quais responderam a 52 solicitacoes de segunda opiniao. Como instrumentos de avaliacao foram utilizados questionarios. RESULTADOS: Foram avaliadas 1.704 respostas de segunda opiniao. Deste total, 514 (29,1%) foram definidas como satisfatorias. Em 64,4% as respostas dos questionarios indicaram que a qualidade das imagens nao comprometeu o diagnostico. O tempo medio para emitir a segunda opiniao remota foi de 6 minutos e 26 segundos. CONCLUSAO: O processo de segunda opiniao medica realizado por intermedio de um sistema web multiespecialidades ajustado para a radiologia pode ser uma excelente ferramenta para o manejo das condutas medicas.

Quality of nursing records related to cardiopulmonary resuscitation compared to the Utstein model

Objective: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. Methods: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30 th , in 2009. Results: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). Conclusions: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.OBJECTIVE: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. METHODS: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30th, in 2009. RESULTS: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). CONCLUSIONS: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.

Depression in Women with Recurrent Miscarriages - an Exploratory Study

Objective To assess depression, domestic violence and the use of substances in women with recurrent miscarriages. Methods The Abuse Assessment Screen (AAS), the Edinburgh Postnatal Depression Scale (EPDS) and the Alcohol, Smoking and Substance Involvement Screening Test (ASSIST) were used to assess violence, depression and the use of substances among women with recurrent miscarriages. The population corresponded to patients receiving prenatal care from June to August 2014. Multiple logistic regression was used to assess the multivariable relationship between depression and sociodemographic, psychosocial and medical characteristics (p < 0,10). Results The prevalence of depression was of 41.3% (95% confidence interval [CI] = 28.3-55.7%). One third of the pregnant women (32.6%) reported emotional or physical violence, and 13% were classified as abusing or addicted to tobacco according to ASSIST. History of psychiatric diseases was associated with depression (p = 0.005). Violence during life demonstrated a modest association (p = 0.073) with depression, as well as the number of miscarriages (p = 0.071). Conclusion Depression is a frequent disease among pregnant women with recurrent miscarriages. The results of this investigation suggest that a systematic assessment of depression and its associated conditions, such as domestic violence and the use of substances, should be part of the prenatal follow-up visits for women with recurrent miscarriages.

Qualidade das anotações de enfermagem relacionadas à ressuscitação cardiopulmonar comparadas ao modelo Utstein

Objective: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. Methods: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30 th , in 2009. Results: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). Conclusions: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.OBJECTIVE: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. METHODS: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30th, in 2009. RESULTS: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). CONCLUSIONS: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.

Calidad de las anotaciones de enfermería relacionadas a la resucitación cardiopulmonar comparadas con el modelo Utstein

Objective: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. Methods: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30 th , in 2009. Results: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). Conclusions: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.OBJECTIVE: To assess the quality of nursing records related to cardiopulmonary resuscitation, comparing them to the validated Utstein protocol, in a university hospital. METHODS: Retrospective, exploratory and descriptive study, with quantitative approach, performed by means of consultation records of patients that suffered cardiorespiratory arrest (CRA) followed by death. The data collection was carried out in the period of May 1st to June 30th, in 2009. RESULTS: Of the 144 medical records surveyed, 74 were dismissed for not having any recorded information on the items to be studied and, 70 constituted the study sample. In these there were no entries on: the immediate cause of CRA (92%); the interventions seeking to recover the cardiorespiratoy arrest (RCA) (71%); on the initial rate of CRA (59%); on the time of events (16%); on drugs used (50%); and, on the professionals involved in RCA (88%). CONCLUSIONS: The notes were scarce and often not realized. The use of the Utstein model favors the annotation sequence of events, avoiding data loss.