Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 58
Filtrar
1.
Stud Health Technol Inform ; 273: 104-108, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087598

RESUMO

Prediction of a labor due date is important especially for the pregnancies with high risk of complications where a special treatment is needed. This is especially valid in the countries with multilevel health care institutions like Russia. In Russia medical organizations are distributed into national, regional and municipal levels. Organizations of each level can provide treatment of different types and quality. For example, pregnancies with low risk of complications are routed to the municipal hospitals, moderate risk pregnancies are routed to the reginal and high risk of complications are routed to the hospitals of the national level. In the situation of resource deficiency especially on the national level it is necessary to plan admission date and a treatment team in advance to provide the best possible care. When pregnancy data is not standardized and semantically interoperable, data driven models. We have retrospectively analyzed electronic health records from the perinatal Center of the Almazov perinatal medical center in Saint-Petersburg, Russia. The dataset was exported from the medical information system. It consisted of structured and semi structured data with the total of 73115 lines for 12989 female patients. The proposed due date prediction data-driven model allows a high accuracy prediction to allow proper resource planning. The models are based on the real-world evidence and can be applied with limited amount of predictors.


Assuntos
Aprendizado de Máquina , História Reprodutiva , Registros Eletrônicos de Saúde , Feminino , Humanos , Gravidez , Estudos Retrospectivos , Federação Russa
2.
Stud Health Technol Inform ; 273: 109-114, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087599

RESUMO

Timely identification of risk factors in the early stages of pregnancy, risk management and mitigation, prevention, adherence management can reduce the number of adverse perinatal outcomes and complications for both mother and a child. We have retrospectively analyzed electronic health records from the perinatal Center of the Almazov specialized medical center in Saint-Petersburg, Russia. Correlation analysis was performed using Pearson correlation coefficient to select the most relevant predictors. We used APGAR score as a metrics for the childbirth outcomes. Score of 5 and less was considered as a negative outcome. To analyze the influence of the unstructured anamnesis data on the prediction accuracy we have run two prediction experiments for every classification task: 1. Without unstructured data and 2. With unstructured data. This study presents implementation of predictive models for adverse childbirth events that provides higher precision than state of the art models. This is due to the use of unstructured medical data in addition to the structured dataset that allowed to reach 0.92 precision. Identification of main risk factors using the results of the features importance analysis can support clinicians in early identification of possible complications and planning and execution preventive measures.


Assuntos
Parto Obstétrico , Parto , Criança , Feminino , Humanos , Aprendizado de Máquina , Gravidez , Estudos Retrospectivos , Federação Russa
3.
Stud Health Technol Inform ; 273: 136-141, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087603

RESUMO

Specific predictive models for diabetes polyneuropathy based on screening methods, for example Nerve conduction studies (NCS, can reach up to AUC 65.8 - 84.7 % for the conditional diagnosis of DPN in primary care. Prediction methods that utilize data from personal health records deal with large non-specific datasets with different prediction methods. Li et al. utilized 30 independent variables, which allowed to implement a model with AUC = 0.8863 for a Multilayer perceptron (MLP). Linear regression (LR) based methods produced up to AUC = 0.8 %. This way, modern data mining and computational methods can be effectively adopted in clinical medicine to derive models that use patient-specific information to predict the development of diabetic polyneuropathy, however, there still is a space to improve the efficiency of the predictive models. The goal of this study is the implementation of machine learning methods for early risk identification of diabetes polyneuropathy based on structured electronic medical records. It was demonstrated that the machine learning methods allow to achieve up to 0.7982 precision, 0.8152 recall, 0.8064 f1-score, 0.8261 accuracy, and 0.8988 AUC using the neural network classifier.


Assuntos
Diabetes Mellitus , Aprendizado de Máquina , Humanos , Redes Neurais de Computação , Medição de Risco , Fatores de Risco
4.
Stud Health Technol Inform ; 273: 170-175, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087608

RESUMO

The use of different data formats complicates the standardization and exchange of valuable medical data. Moreover, a big part of medical data is stored as unstructured medical records that are complicated to process. In this work we solve the task of unstructured allergy anamnesis categorization according to categories provided by FHIR. We applied two stage classification model with manually labeled records. On the first stage the model filters records with information about allergies and on the second stage it categorizes each record. The model showed high performance. The development of this approach will ensure secondary use of data and interoperability.


Assuntos
Registros Eletrônicos de Saúde , Hipersensibilidade , Humanos , Registros
5.
Stud Health Technol Inform ; 273: 223-227, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087616

RESUMO

The current pandemic can likely have several waves and will require a major effort to save lives and provide optimal treatment. The efficient clinical resource planning and efficient treatment require identification of risk groups and specific clinical features of the patients. In this study we develop analyze mortality for COVID19 patients in Russia. We identify comorbidities and risk factors for different groups of patients including cardiovascular diseases and therapy. In the study we used a Russian national COVID registry, that provides sophisticated information about all the COVID-19 patients in Russia. To analyze Features importance for the mortality we have calculated Shapley values for the "mortality" class and ANN hidden layer coefficients for patient lifetime. We calculated the distribution of days spent in hospital before death to show how many days a patient occupies a bed depending on the age and the severity of the disease to allow optimal resource planning and enable age-based risk assessment. Predictors of the days spent in hospital were calculated using Pearson correlation coefficient. Decisions trees were developed to classify the patients into the groups and reveal the lethality factors.


Assuntos
Infecções por Coronavirus , Aprendizado de Máquina , Pandemias , Pneumonia Viral , Betacoronavirus , Humanos , Federação Russa , Análise de Sobrevida
6.
Stud Health Technol Inform ; 273: 240-245, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087619

RESUMO

Failing to follow up on the abnormal test results can cause serious health problems to patients. We conducted a retrospective medical record review of 3200 randomly selected patients aged 18 to 76 in 14 state clinics and two private laboratory services querying the common regional patient registry. One patient could be included (1 clinical case) in the study only once. We invited patients to take part in the interviews to gain a deeper understanding of the motives to follow up or not after receiving a recommendation and explanation of the role of the automatically generated interpretation in this decision. A qualitative study of the patients' motivation was performed with a group of 689 patients. All the patients who received their interpretations showed a much higher follow-up rate (68% average) than the patients who did not receive interpretations (49 % average). The results of our research demonstrated that there is a significant impact on the patients' decision to follow up on the tests. Patients consider time factor as an important advantage of the computer interpretations and are willing to get automatic interpretations if they can receive it faster than the ones from their doctor (question 4: median =3 out of 7). Discussing the reasons behind the decision to follow up, the patients do trust the computerized clinical decision support systems (question 5: median = 5 out of 7), however, they prefer to receive interpretations and recommendations from doctors (question 3: median = 7).


Assuntos
Sistemas de Apoio a Decisões Clínicas , Médicos , Adolescente , Adulto , Idoso , Seguimentos , Humanos , Pessoa de Meia-Idade , Motivação , Estudos Retrospectivos , Adulto Jovem
7.
Stud Health Technol Inform ; 273: 262-265, 2020 Sep 04.
Artigo em Inglês | MEDLINE | ID: mdl-33087624

RESUMO

The outbreak of COVID-19 has led to a crucial change in ordinary healthcare approaches. In comparison with emergencies re-allocation of resources for a long period of time is required and the peak utilization of the resources is also hard to predict. Furthermore, the epidemic models do not provide reliable information of the development of the pandemic's development, so it creates a high load on the healthcare systems with unforeseen duration. To predict morbidity of the novel COVID-19, we used records covering the time period from 01-03-2020 to 25-05-2020 and include sophisticated information of the morbidity in Russia. Total of 45238 patients were analyzed. The predictive model was developed as a combination of Holt and Holt-Winter models with Gradient boosting Regression. As we can see from the table 2, the models demonstrated a very good performance on the test data set. The forecast is quite reliable, however, due to the many uncertainties, only a real-world data can prove the correctness of the forecast.


Assuntos
Infecções por Coronavirus , Pandemias , Pneumonia Viral , Betacoronavirus , Humanos , Morbidade , Federação Russa/epidemiologia
8.
Physiol Meas ; 41(10): 10TR01, 2020 11 10.
Artigo em Inglês | MEDLINE | ID: mdl-32947271

RESUMO

Coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is rapidly spreading across the globe. The clinical spectrum of SARS-CoV-2 pneumonia requires early detection and monitoring, within a clinical environment for critical cases and remotely for mild cases, with a large spectrum of symptoms. The fear of contamination in clinical environments has led to a dramatic reduction in on-site referrals for routine care. There has also been a perceived need to continuously monitor non-severe COVID-19 patients, either from their quarantine site at home, or dedicated quarantine locations (e.g. hotels). In particular, facilitating contact tracing with proximity and location tracing apps was adopted in many countries very rapidly. Thus, the pandemic has driven incentives to innovate and enhance or create new routes for providing healthcare services at distance. In particular, this has created a dramatic impetus to find innovative ways to remotely and effectively monitor patient health status. In this paper, we present a review of remote health monitoring initiatives taken in 20 states during the time of the pandemic. We emphasize in the discussion particular aspects that are common ground for the reviewed states, in particular the future impact of the pandemic on remote health monitoring and consideration on data privacy.


Assuntos
Infecções por Coronavirus/diagnóstico , Infecções por Coronavirus/fisiopatologia , Monitorização Fisiológica/métodos , Pneumonia Viral/diagnóstico , Pneumonia Viral/fisiopatologia , Telemedicina/métodos , Infecções por Coronavirus/epidemiologia , Humanos , Pandemias , Pneumonia Viral/epidemiologia
9.
BMC Med Inform Decis Mak ; 20(1): 201, 2020 08 24.
Artigo em Inglês | MEDLINE | ID: mdl-32831065

RESUMO

BACKGROUND: Methods of data mining and analytics can be efficiently applied in medicine to develop models that use patient-specific data to predict the development of diabetic polyneuropathy. However, there is room for improvement in the accuracy of predictive models. Existing studies of diabetes polyneuropathy considered a limited number of predictors in one study to enable a comparison of efficiency of different machine learning methods with different predictors to find the most efficient one. The purpose of this study is the implementation of machine learning methods for identifying the risk of diabetes polyneuropathy based on structured electronic medical records collected in databases of medical information systems. METHODS: For the purposes of our study, we developed a structured procedure for predictive modelling, which includes data extraction and preprocessing, model adjustment and performance assessment, selection of the best models and interpretation of results. The dataset contained a total number of 238,590 laboratory records. Each record 27 laboratory tests, age, gender and presence of retinopathy or nephropathy). The records included information about 5846 patients with diabetes. Diagnosis served as a source of information about the target class values for classification. RESULTS: It was discovered that inclusion of two expressions, namely "nephropathy" and "retinopathy" allows to increase the performance, achieving up to 79.82% precision, 81.52% recall, 80.64% F1 score, 82.61% accuracy, and 89.88% AUC using the neural network classifier. Additionally, different models showed different results in terms of interpretation significance: random forest confirmed that the most important risk factor for polyneuropathy is the increased neutrophil level, meaning the presence of inflammation in the body. Linear models showed linear dependencies of the presence of polyneuropathy on blood glucose levels, which is confirmed by the clinical interpretation of the importance of blood glucose control. CONCLUSION: Depending on whether one needs to identify pathophysiological mechanisms for one's prospective study or identify early or late predictors, the choice of model will vary. In comparison with the previous studies, our research makes a comprehensive comparison of different decisions using a large and well-structured dataset applied to different decision support tasks.

10.
Stud Health Technol Inform ; 270: 916-920, 2020 Jun 16.
Artigo em Inglês | MEDLINE | ID: mdl-32570515

RESUMO

Failing to follow up on the abnormal test results can cause serious health problems to patients. We conducted a retrospective medical record review of 3200 randomly selected patients aged 18 to 76 in 14 state clinics and two private laboratory services querying the common regional patient registry. One patient could be included (1 clinical case) in the study only once. We invited patients to take part in the interviews to gain a deeper understanding of the motives to follow up or not after receiving a recommendation and explanation of the role of the automatically generated interpretation in this decision. A qualitative study of the patients' motivation was performed with a group of 689 patients. All the patients who received their interpretations showed a much higher follow-up rate (68% average) than the patients who did not receive interpretations (49 % average). The results of our research demonstrated that there is a significant impact on the patients' decision to follow up on the tests. Patients consider time factor as an important advantage of the computer interpretations and are willing to get automatic interpretations if they can receive it faster than the ones from their doctor (question 4: median =3 out of 7). Discussing the reasons behind the decision to follow up, the patients do trust the computerized clinical decision support systems (question 5: median = 5 out of 7), however, they prefer to receive interpretations and recommendations from doctors (question 3: median = 7).


Assuntos
Tomada de Decisões , Adolescente , Adulto , Idoso , Sistemas de Apoio a Decisões Clínicas , Seguimentos , Humanos , Registros Médicos , Pessoa de Meia-Idade , Pesquisa Qualitativa , Estudos Retrospectivos , Adulto Jovem
11.
Stud Health Technol Inform ; 270: 1379-1380, 2020 Jun 16.
Artigo em Inglês | MEDLINE | ID: mdl-32570668

RESUMO

Specific predictive models for diabetes polyneuropathy based on screening methods, for example Nerve conduction studies (NCS), can reach up to AUC 65.8-84.7 % for the conditional diagnosis of DPN in primary care. Prediction methods that utilize data from personal health records deal with large non-specific datasets with different prediction methods. It was demonstrated that the machine learning methods allow to achieve up to 0.7982 precision, 0.8152 recall, 0.8064 f1-score, 0.8261 accuracy, and 0.8988 AUC using the neural network classifier.


Assuntos
Neuropatias Diabéticas , Doença Crônica , Humanos , Aprendizado de Máquina , Redes Neurais de Computação , Exame Neurológico , Fatores de Risco
12.
Artigo em Inglês | MEDLINE | ID: mdl-31861851

RESUMO

This paper is an extension of work originally presented to pHealth 2019-16th International Conference on Wearable, Micro and Nano Technologies for Personalized Health. To provide an efficient decision support, it is necessary to integrate clinical decision support systems (CDSSs) in information systems routinely operated by healthcare professionals, such as hospital information systems (HISs), or by patients deploying their personal health records (PHR). CDSSs should be able to use the semantics and the clinical context of the data imported from other systems and data repositories. A CDSS platform was developed as a set of separate microservices. In this context, we implemented the core components of a CDSS platform, namely its communication services and logical inference components. A fast healthcare interoperability resources (FHIR)-based CDSS platform addresses the ease of access to clinical decision support services by providing standard-based interfaces and workflows. This type of CDSS may be able to improve the quality of care for doctors who are using HIS without CDSS features. The HL7 FHIR interoperability standards provide a platform usable by all HISs that are FHIR enabled. The platform has been implemented and is now productive, with a rule-based engine processing around 50,000 transactions a day with more than 400 decision support models and a Bayes Engine processing around 2000 transactions a day with 128 Bayesian diagnostics models.


Assuntos
Gerenciamento de Dados/métodos , Sistemas de Apoio a Decisões Clínicas , Registros Eletrônicos de Saúde , Sistemas de Informação Hospitalar , Teorema de Bayes , Humanos , Registros , Semântica
13.
Artigo em Inglês | MEDLINE | ID: mdl-31717300

RESUMO

This paper is an extension of the work originally presented in the 16th International Conference on Wearable, Micro and Nano Technologies for Personalized Health. Despite using electronic medical records, free narrative text is still widely used for medical records. To make data from texts available for decision support systems, supervised machine learning algorithms might be successfully applied. In this work, we developed and compared a prototype of a medical data extraction system based on different artificial neural network architectures to process free medical texts in the Russian language. Three classifiers were applied to extract entities from snippets of text. Multi-layer perceptron (MLP) and convolutional neural network (CNN) classifiers showed similar results to all three embedding models. MLP exceeded convolutional network on pipelines that used the embedding model trained on medical records with preliminary lemmatization. Nevertheless, the highest F-score was achieved by CNN. CNN slightly exceeded MLP when the biggest word2vec model was applied (F-score 0.9763).


Assuntos
Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Redes Neurais de Computação , Algoritmos , Humanos
14.
Stud Health Technol Inform ; 261: 62-67, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156092

RESUMO

Despite using electronic medical records, free narrative text is still widely used for medical records. Such text cannot be analyzed by statistical tools and be proceed by decision support systems. To make data from texts available for such tasks a supervised machine learning algorithms might be successfully applied. In this work, we develop and compare a prototype of a medical data extraction system based on different artificial neuron networks architectures to process free medical texts in Russian language. The best F-score (0.9763) achieved on a combination of CNN prediction model and large pre-trained word2vec model. The very close result (0.9741) has shown by the MLP model with the same embedding.


Assuntos
Mineração de Dados , Registros Eletrônicos de Saúde , Processamento de Linguagem Natural , Algoritmos , Idioma
15.
Stud Health Technol Inform ; 261: 162-167, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156109

RESUMO

Clusterization is a promising group of methods in the context of patient similarity. However, results of clustering are not often clear for physicians as well as different clustering methods can produce different results. We have examined a well-known dataset and implemented 3 clustering methods (k-means, Agglomerative and Spectral). We have compared and evaluated clusters and their correlation with data attributes. In contrast to original dataset's target value, the clusters correlated with only a few attributes. Finally, we train 2 predictive models based on k-nearest neighbors (KNN) algorithm and Artificial Neural Network (ANN). Models evaluation demonstrates that using the results of clustering algorithms as predictive attribute give a higher F-score than the original target attribute.


Assuntos
Algoritmos , Análise de Dados , Cardiopatias , Análise por Conglomerados , Humanos , Redes Neurais de Computação
16.
Stud Health Technol Inform ; 261: 174-178, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156111

RESUMO

The paper deals with using a machine-learning algorithm for patient adherence level determination. For this purpose, we developed a neural network using the Python language, Keras library, and PyCharm platform. We analyzed different medical data collected from medical staff, patient interviews, and measurements preprocessed using a fuzzy Mamdani algorithm. After analysing 369 records we received 79.4% of accuracy.


Assuntos
Lógica Fuzzy , Aprendizado de Máquina , Cooperação do Paciente , Algoritmos , Humanos , Redes Neurais de Computação
17.
Stud Health Technol Inform ; 261: 199-204, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156116

RESUMO

Clinical decision support is very important especially in such a wide-spread disease as a coronary artery disease. A large variety of prediction methods can potentially solve the classification problem to support clinical decisions. However, not all of them provide similar efficiency for the classification of patients with coronary artery disease. We have analyzed prediction the efficiency of classifiers (Ridge Classifier, XGB Classifier and Logistic Regression) depending on the number and combination of features. We have tested 24 sets of features on 4 classifiers to proof the hypothesis that using optimized features sets with a higher Pearson ratio results in more efficient classifiers than using all available data.


Assuntos
Doença da Artéria Coronariana , Sistemas de Apoio a Decisões Clínicas , Modelos Logísticos , Algoritmos , Doença da Artéria Coronariana/diagnóstico , Doença da Artéria Coronariana/terapia , Humanos
18.
Stud Health Technol Inform ; 261: 211-216, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156118

RESUMO

The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9%. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64%. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.


Assuntos
Dermatite Seborreica , Diagnóstico por Computador , Líquen Plano , Redes Neurais de Computação , Psoríase , Dermatite Seborreica/diagnóstico , Dermatologia , Diagnóstico Diferencial , Humanos , Líquen Plano/diagnóstico , Psoríase/diagnóstico
19.
Stud Health Technol Inform ; 261: 230-235, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31156121

RESUMO

Efficient Interaction between Hospital information (HIS) and laboratory information systems (LIS) provide a smooth laboratory testing process and data consistency. The current software ecosystem can be characterized by its rapid changes that can lead to breaks in HIS-LIS interaction and problems with semantic interoperability of the systems. To avoid such problems developers can clusterize software applications into small, easily supportable functional units that can be changed on demand without effecting other pieces of software. This approach commonly referred to as microservice architecture. The goal the research is to develop a FHIR based microservice platform that connects HIS, LIS and a Clinical decision support system (CDSS) into unified information space. A microservice platform has been implemented and now is in the production operation processing around 15000 orders a day.


Assuntos
Sistemas de Informação em Laboratório Clínico , Sistemas de Apoio a Decisões Clínicas , Software , Hospitais
20.
Stud Health Technol Inform ; 258: 41-45, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-30942710

RESUMO

To manage medical information semantic interoperability is essential. Mapping of concepts and mapping of terminologies are two objectives to reach semantic interoperability. Russian proprietary health information system and FHIR overlaps (60%) were calculated to estimate possibility of standardization. Russian terminology directories and FHIR overlaps were calculated to estimate possibility of use Russian terminologies and codifications in FHIR-based information system. The result is promising, however, requires more wide investigation using automatic tools.


Assuntos
Sistemas de Informação em Saúde , Terminologia como Assunto , Idioma , Federação Russa , Semântica
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA