RESUMO
Dermatology is one of the medical fields outside the radiology service that uses image acquisition and analysis in its daily medical practice, mostly through digital dermoscopy imaging modality. The acquisition, transfer, and storage of dermatology images has become an important issue to resolve. We aimed to describe our experience in integrating dermoscopic images into PACS using DICOM as a guide for the health informatics and dermatology community. During 2022 we integrated the video dermoscopy equipment through a strategic plan with an 8-step procedure. We used the DICOM standard with Modality Worklist and Storage commitment. Three systems were involved (video dermoscopy software, the EHR, and PACS). We identified critical steps and faced many challenges, such as the lack of a final model of DICOM standard for dermatology images.
Assuntos
Informática Médica , SoftwareRESUMO
In recent years, numerous dermatological image databases have been published to make possible the development and validation of artificial intelligence-based technologies to support healthcare professionals in the diagnosis of skin diseases. However, the generation of these datasets confined to certain countries as well as the lack of demographic information accompanying the images, prevents having a real knowledge of in which populations these models could be used. Consequently, this hinders the translation of the models to the clinical setting. This has led the scientific community to encourage the detailed and transparent reporting of the databases used for artificial intelligence developments, as well as to promote the formation of genuinely international databases that can be representative of the world population. Through this work, we seek to provide details of the processing stages of the first public database of dermoscopy and clinical images created in a hospital in Argentina. The dataset comprises 1,616 images corresponding to 1,246 unique lesions collected from 623 patients.
Assuntos
Melanoma , Dermatopatias , Neoplasias Cutâneas , Humanos , Argentina , Inteligência Artificial , Melanoma/patologia , Sensibilidade e Especificidade , Dermatopatias/diagnóstico por imagem , Neoplasias Cutâneas/patologiaRESUMO
PURPOSE: Colorectal cancer is usually accompanied by liver metastases. The prediction of patient evolution is essential for the choice of the appropriate therapy. The aim of this study is to develop and evaluate machine learning models to predict KRAS gene mutations and 2-year disease-specific mortality from medical images. METHODS: Clinical and follow-up information was collected from patients with metastatic colorectal cancer who had undergone computed tomography prior to liver resection. The dominant liver lesion was segmented in each scan and radiomic features were extracted from the volumes of interest. The 65% of the cases were employed to perform feature selection and to train machine learning algorithms through cross-validation. The best performing models were assembled and evaluated in the remaining cases of the cohort. RESULTS: For the mortality model development, 101 cases were used as training set (64 alive, 37 deceased) and 35 as test set (22 alive, 13 deceased); while for KRAS mutation models, 55 cases were used for training (31 wild-type, 24 mutated) and 30 for testing (17 wild-type, 13 mutated). The ensemble of top performing models resulted in an area under the receiver operating characteristic curve of 0.878 for mortality and 0.905 for KRAS prediction. CONCLUSIONS: Predicting the prognosis of patients with metastatic colorectal cancer is useful for making timely decisions about the best treatment options. This study presents a noninvasive method based on quantitative analysis of baseline images to identify factors influencing patient outcomes, with the aim of incorporating these tools as support systems.
Assuntos
Neoplasias do Colo , Neoplasias Retais , Humanos , Proteínas Proto-Oncogênicas p21(ras)/genética , Aprendizado de Máquina , Mutação , Estudos RetrospectivosRESUMO
BACKGROUND AND OBJECTIVES: The multiple chest x-ray datasets released in the last years have ground-truth labels intended for different computer vision tasks, suggesting that performance in automated chest x-ray interpretation might improve by using a method that can exploit diverse types of annotations. This work presents a Deep Learning method based on the late fusion of different convolutional architectures, that allows training with heterogeneous data with a simple implementation, and evaluates its performance on independent test data. We focused on obtaining a clinically useful tool that could be successfully integrated into a hospital workflow. MATERIALS AND METHODS: Based on expert opinion, we selected four target chest x-ray findings, namely lung opacities, fractures, pneumothorax and pleural effusion. For each finding we defined the most suitable type of ground-truth label, and built four training datasets combining images from public chest x-ray datasets and our institutional archive. We trained four different Deep Learning architectures and combined their outputs with a late fusion strategy, obtaining a unified tool. The performance was measured on two test datasets: an external openly-available dataset, and a retrospective institutional dataset, to estimate performance on the local population. RESULTS: The external and local test sets had 4376 and 1064 images, respectively, for which the model showed an area under the Receiver Operating Characteristics curve of 0.75 (95%CI: 0.74-0.76) and 0.87 (95%CI: 0.86-0.89) in the detection of abnormal chest x-rays. For the local population, a sensitivity of 86% (95%CI: 84-90), and a specificity of 88% (95%CI: 86-90) were obtained, with no significant differences between demographic subgroups. We present examples of heatmaps to show the accomplished level of interpretability, examining true and false positives. CONCLUSION: This study presents a new approach for exploiting heterogeneous labels from different chest x-ray datasets, by choosing Deep Learning architectures according to the radiological characteristics of each pathological finding. We estimated the tool's performance on the local population, obtaining results comparable to state-of-the-art metrics. We believe this approach is closer to the actual reading process of chest x-rays by professionals, and therefore more likely to be successful in a real clinical setting.
Assuntos
Aprendizado Profundo , Radiografia , Estudos Retrospectivos , Triagem , Raios XRESUMO
This paper describes the development and implementation of a web based electronic health record for the Homecare Service program in the Hospital Italiano de Buenos Aires. It reviews the process of the integration of the new electronic health record to the hospital information system, allowing physicians to access the clinical data repository from their Pc's at home and with the capability of consulting past and present history of the patient health care, order, tests, and referrals with others professionals trough the new Electronic Health Record. We also discuss how workflow processes were changed and improved for the physicians, nurses, and administrative personnel of the Homecare Services and the educational methods used to improve acceptance and adoption of these new technologies. We also briefly describe the validation of physicians and their field work with electronic signatures.
Assuntos
Prestação Integrada de Cuidados de Saúde/organização & administração , Registros Eletrônicos de Saúde/organização & administração , Serviços de Assistência Domiciliar/organização & administração , Modelos Organizacionais , Argentina , Integração de SistemasRESUMO
CONTEXT: The Unified Model of Information Systems Continuance (UMISC) is a metamodel for the evaluation of clinical information systems (CISs) that integrates constructs from five models that have previously been published in the literature. UMISC was developed at the Georges Pompidou University Hospital (HEGP) in Paris and was partially validated at the Saint Joseph Hospital Group (HPSJ), another acute care institution using the same CIS as HEGP. OBJECTIVE: The aim of this replication study was twofold: (1) to perform an external validation of UMISC in two different hospitals and country contexts: the Italian Hospital of Buenos Aires (HIBA) in Argentina and the Hospital Sirio Libanes in Sao Paulo, Brazil (HSL); (2) to compare, using the same evaluation model, the determinants of satisfaction, use, and continuance intention observed at HIBA and HSL with those previously observed at HEGP and HPSJ. METHODS: The UMISC evaluation questionnaires were translated from their original languages (English and French) to Brazilian Portuguese and Spanish following the translation/back-translation method. These questionnaires were then applied at each target site. The 21 UMISC-associated hypotheses were tested using structural equation modeling (SEM). RESULTS: A total of 3020 users, 1079 at HIBA and 1941 at the HSL, were included in the analysis. The respondents included 1406 medical staff and 1001 nursing staff. The average profession-adjusted use, overall satisfaction and continuance intention were significantly higher at HIBA than at HSL in the medical and nursing groups. In SEM analysis, UMISC explained 23% and 11% of the CIS use dimension, 72% and 85% of health professionals' satisfaction, and 41% and 60% of continuance intention at HIBA and HSL, respectively. Twenty of the 21 UMISC-related hypotheses were validated in at least one of the four evaluation sites, and 16 were validated in two or more sites. CONCLUSION: The UMISC evaluation metamodel appears to be a robust comparison and explanatory model of satisfaction, use and continuance intention for CISs in late post adoption situations.