Search results for "diagnostiikka"
showing 10 items of 32 documents
Silmitön ja väkivaltainen : erään mielisairaalapotilaan ura 1900-luvulla
2018
Artikkelissa tarkastellaan yhden pitkäaikaisen potilaan, ”Katrin”, potilaskertomuksen kautta mielisairauteen liitettyjen kriteerien muuttumista, diagnostiikan ja sairastuneiden lääketieteellisen hallinnan kehitystä sekä mielisairaanhoidon muuttumista psykiatriaksi. Artikkelissa kysytään, millä perusteella mielisairaalapotilas lähetettiin hoitolaitokseen, millaisia hoitokäytänteitä häneen sovellettiin ja miksi ja auttoivatko ne. Kysymyksiin vastaamiseen tarvitaan kontekstin, suomalaisen psykiatrian, tuntemista. Katrin yhteenlaskettu hoitoaika piirimielisairaalassa kesti yli 40 vuotta, ja tuo ajanjakso sisältää miltei kaikki 1900-luvulla käytetyt hoitomuodot. Sairauskertomuksen lääketieteelli…
H&E Multi-Laboratory Staining Variance Exploration with Machine Learning
2022
In diagnostic histopathology, hematoxylin and eosin (H&E) staining is a critical process that highlights salient histological features. Staining results vary between laboratories regardless of the histopathological task, although the method does not change. This variance can impair the accuracy of algorithms and histopathologists’ time-to-insight. Investigating this variance can help calibrate stain normalization tasks to reverse this negative potential. With machine learning, this study evaluated the staining variance between different laboratories on three tissue types. We received H&E-stained slides from 66 different laboratories. Each slide contained kidney, skin, and colon tissue sampl…
Hyperspectral imaging reveals spectral differences and can distinguish malignant melanoma from pigmented basal cell carcinomas : A pilot study
2021
Pigmented basal cell carcinomas can be difficult to distinguish from melanocytic tumours. Hyperspectral imaging is a non-invasive imaging technique that measures the reflectance spectra of skin in vivo. The aim of this prospective pilot study was to use a convolutional neural network classifier in hyperspectral images for differential diagnosis between pigmented basal cell carcinomas and melanoma. A total of 26 pigmented lesions (10 pigmented basal cell carcinomas, 12 melanomas in situ, 4 invasive melanomas) were imaged with hyperspectral imaging and excised for histopathological diagnosis. For 2-class classifier (melanocytic tumours vs pigmented basal cell carcinomas) using the majority of…
Discriminating Basal Cell Carcinoma and Bowen’s Disease with Novel Hyperspectral Imaging System and Convolutional Neural Networks
2022
The Value of Liquid Biopsies for Guiding Therapy Decisions in Non-small Cell Lung Cancer
2019
Targeted therapies have allowed for an individualized treatment approach in non-small-cell lung cancer (NSCLC). The initial therapeutic decisions and success of targeted therapy depend on genetic identification of personal tumor profiles. Tissue biopsy is the gold standard for molecular analysis, but non-invasive or minimally invasive liquid biopsy methods are also now used in clinical practice, allowing for later monitoring and optimization of the cancer treatment. The inclusion of liquid biopsy in the management of NSCLC provides strong evidence on early treatment response, which becomes a basis for determining disease progression and the need for changes in treatment. Liquid biopsies can…
Classification of Heart Sounds Using Convolutional Neural Network
2020
Heart sounds play an important role in the diagnosis of cardiac conditions. Due to the low signal-to-noise ratio (SNR), it is problematic and time-consuming for experts to discriminate different kinds of heart sounds. Thus, objective classification of heart sounds is essential. In this study, we combined a conventional feature engineering method with deep learning algorithms to automatically classify normal and abnormal heart sounds. First, 497 features were extracted from eight domains. Then, we fed these features into the designed convolutional neural network (CNN), in which the fully connected layers that are usually used before the classification layer were replaced with a global averag…
Dyslektikon prosessitasoinen arviointi
2000
Kuormituskoe modernin kuvantamisen aikakaudella
2019
Kuormituskoetta käytetään sepelvaltimotaudin ja muidenkin sydänsairauksien diagnosoinnissa, ennusteen arvioinnissa, hoidon suunnittelussa ja seurannassa. Kuormituskokeen keskeisin etu on sen helppo saatavuus sekä avoterveydenhuollossa että erikoissairaanhoidossa. Rasitukseen liittyvien oireiden tai suorituskyvyn heikkenemisen yhteydessä kuormituskoe on edelleen arvokas perustutkimus. Sen käytön keskeisin rajoite liittyy sen diagnostiseen osuvuuteen, ja sepelvaltimotaudin ali- ja ylidiagnostiikan välttämiseksi kuormituskokeen käyttö tulisikin rajata liikuntakykyisiin potilaisiin, joilla taudin todennäköisyys ennen testiä on keskisuuri tai suuri. Kuormituskoe sopii potilaille, joiden lepo-EKG…
Laboratory-Based Gait Variability and Habitual Gait Entropy Do Not Differentiate Community-Dwelling Older Adults from Those with Subjective Memory Co…
2020
Background Age-related cognitive decline may be delayed with appropriate interventions if those at high risk can be identified prior to clinical symptoms arising. Gait variability assessment has emerged as a promising candidate prognostic indicator, however, it remains unclear how sensitive gait variability is to early changes in cognitive abilities. Research question Do community-dwelling adults over 65 years of age with subjective memory complaints differ from those with no subjective memory concerns in terms of laboratory-measured or free-living gait variability? Methods This cross-sectional study recruited 24 (age = 73.5(SD 6.4) years) community-dwelling people with subjective memory co…
Orderly display of limb lead ECGs raises Chinese intern’s diagnostic accuracy when determining frontal plane QRS axis
2019
Background: There is limited information on whether the orderly display of limb lead ECGs (electrocardiograms) can facilitate students to determine frontal plane QRS complex wave electrical axis. Objectives: The study investigated whether the orderly display of limb lead ECGs can raise Chinese undergraduate intern’s diagnostic accuracy when determining frontal plane axis. Design: A total of 147 fifth-year undergraduate interns aged between 21 and 25 years were randomly arranged into 2 groups: one group was given classically displayed ECGs of limb leads while the other group was given orderly displayed ECGs of limb leads. They were then taught to determine frontal plane axis with one of the …