Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Más filtros










Intervalo de año de publicación
1.
Stud Health Technol Inform ; 314: 123-124, 2024 May 23.
Artículo en Inglés | MEDLINE | ID: mdl-38785016

RESUMEN

This paper aims to propose an approach leveraging Artificial Intelligence (AI) to diagnose thalassemia through medical imaging. The idea is to employ a U-net neural network architecture for precise erythrocyte morphology detection and classification in thalassemia diagnosis. This accomplishment was realized by developing and assessing a supervised semantic segmentation model of blood smear images, coupled with the deployment of various data engineering techniques. This methodology enables new applications in tailored medical interventions and contributes to the evolution of AI within precision healthcare, establishing new benchmarks in personalized treatment planning and disease management.


Asunto(s)
Inteligencia Artificial , Talasemia , Humanos , Talasemia/diagnóstico , Talasemia/sangre , Redes Neurales de la Computación , Interpretación de Imagen Asistida por Computador/métodos
2.
Stud Health Technol Inform ; 314: 125-126, 2024 May 23.
Artículo en Inglés | MEDLINE | ID: mdl-38785017

RESUMEN

Thrombophilia, a predisposition to thrombosis, poses significant diagnostic challenges due to its multi-factorial nature, encompassing genetic and acquired factors. Current diagnostic paradigms, primarily relying on a combination of clinical assessment and targeted laboratory tests, often fail to capture the complex interplay of factors contributing to thrombophilia risk. This paper proposes an innovative artificial intelligence (AI)-based methodology aimed to enhance the prediction of thrombophilia risk. The designed multidimensional risk assessment model integrates and elaborates through AI a comprehensive collection of patient data types, including genetic markers, clinical parameters, patient history, and lifestyle factors, in order to obtain advanced and personalized explainable diagnoses.


Asunto(s)
Inteligencia Artificial , Trombofilia , Trombofilia/diagnóstico , Humanos , Medición de Riesgo , Factores de Riesgo
3.
Front Health Serv ; 4: 1253905, 2024.
Artículo en Inglés | MEDLINE | ID: mdl-38487373

RESUMEN

Purpose: The coronavirus pandemic (COVID-19) significantly impacted the global economy and health. Italy was one of the first and most affected countries. The objective of our study was to assess the impact of the pandemic and the vaccination campaign on the radiological examinations performed in a radiology department of a tertiary center in Southern Italy. Materials and methods: We analyzed weekly and retrospectively electronic medical records of case volumes performed at the Radiology Department of "Mater Domini" University Hospital of Catanzaro from March 2020 to March 2022, comparing them with the volumes in the same period of the year 2019. We considered the origin of patients (outpatient, inpatient) and the type of examinations carried out (x-ray, mammography, CT, MRI, and ultrasound). A non-parametric test (Wilcoxon Signed Rank test) was applied to evaluate the average volumes. Results: Total flows in the pandemic period from COVID-19 were lower than in the same pre-pandemic period with values of 552 (120) vs. 427 (149) median (IQR) (p < 0.001). The vaccination campaign allowed the resumption of the pre-vaccination pandemic with total flows 563 (113) vs. 427 (149) median (IQR) p < 0.001. In the post-vaccination period, the number of examinations was found to overlap with the pre-COVID period. Conclusion: The pandemic impacted the volume of radiological examinations performed, particularly with the reduction of tests in outpatients. The vaccination allowed the return to the pre-COVID period imaging case volumes.

4.
J. venom. anim. toxins incl. trop. dis ; 26: e20190100, 2020. graf, ilus
Artículo en Inglés | LILACS, VETINDEX | ID: biblio-1135140

RESUMEN

Despite the disrepute spiders have had for centuries, their bite is a rare occurrence. In the Mediterranean area, only two of the numerous known species are considered of medical significance: Latrodectus tredecimguttatus and Loxosceles rufescens. Spider bites have no pathognomonic signs or symptoms, therefore most diagnoses are presumptive; a spider bite can only be diagnosed when a spider (seen at the time of the bite) is collected and identified by an expert, since most physicians and patients are unable to recognize a certain spider species or distinguish spiders from other arthropods. Skin lesions of uncertain etiology are too often attributed to spider bites. In most cases, these are actually skin and soft-tissue infections, allergic reactions, dermatoses etc. Misdiagnosing a wound as a spider bite can lead to delays in appropriate care, cause adverse or even fatal outcomes and have medical-legal implications. Concerningly, misinformation on spider bites also affects the medical literature and it appears there is lack of awareness on current therapeutic indications for verified bites.(AU)


Asunto(s)
Animales , Picaduras de Arañas , Artrópodos , Arañas , Mordeduras y Picaduras , Diagnóstico , Errores Diagnósticos
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA