| 1. |
- Ahmed, Rafsan, et al.
(författare)
-
EasyNER: A Customizable Easy-to-Use Pipeline for Deep Learning- and Dictionary-based Named Entity Recognition from Medical Text
- 2023
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Medical research generates a large number of publications with the PubMed database already containing >35 million research articles. Integration of the knowledge scattered across this large body of literature could provide key insights into physiological mechanisms and disease processes leading to novel medical interventions. However, it is a great challenge for researchers to utilize this information in full since the scale and complexity of the data greatly surpasses human processing abilities. This becomes especially problematic in cases of extreme urgency like the COVID-19 pandemic. Automated text mining can help extract and connect information from the large body of medical research articles. The first step in text mining is typically the identification of specific classes of keywords (e.g., all protein or disease names), so called Named Entity Recognition (NER). Here we present an end-to-end pipeline for NER of typical entities found in medical research articles, including diseases, cells, chemicals, genes/proteins, and species. The pipeline can access and process large medical research article collections (PubMed, CORD-19) or raw text and incorporates a series of deep learning models fine-tuned on the HUNER corpora collection. In addition, the pipeline can perform dictionary-based NER related to COVID-19 and other medical topics. Users can also load their own NER models and dictionaries to include additional entities. The output consists of publication-ready ranked lists and graphs of detected entities and files containing the annotated texts. An associated script allows rapid inspection of the results for specific entities of interest. As model use cases, the pipeline was deployed on two collections of autophagy-related abstracts from PubMed and on the CORD19 dataset, a collection of 764 398 research article abstracts related to COVID-19.
|
|
| 2. |
|
|
| 3. |
- Nordlund, Arto, 1962, et al.
(författare)
-
Episodic memory and speed/attention deficits are associated with Alzheimer-typical CSF abnormalities in MCI
- 2008
-
Ingår i: Journal of the International Neuropsychological Society. - 1355-6177. ; 14:4, s. 582-590
-
Tidskriftsartikel (refereegranskat)abstract
- Mild cognitive impairment (MCI) is regarded as the prodromal stage of dementia disorders, such as Alzheimer's disease (AD). Objective: To compare the neuropsychological profiles of MCI subjects with normal concentrations of total tau (T-τ) and Aβ42 in CSF (MCI-norm) to MCI subjects with deviating concentrations of the biomarkers (MCI-dev). MCI-norm (N = 73) and MCI-dev (N = 73) subjects were compared to normal controls (N = 50) on tests of speed/attention, memory, visuospatial function, language and executive function. Results: MCI-norm performed overall better than MCI-dev, specifically on tests of speed and attention and episodic memory. When MCI-dev subjects were subclassified into those with only high T-tau (MCI-tau), only low Aβ42 (MCI-Aβ) and both high T-tau and low Aβ42 (MCI-tauAβ), MCI-tauAβ tended to perform slightly worse. MCI-tau and MCI-Aβ performed quite similarly. Conclusions: Considering the neuropsychological differences, many MCI-norm probably had more benign forms of MCI, or early non-AD forms of neurodegenerative disorders. Although most MCI-dev performed clearly worse than MCI-norm on the neuropsychological battery, some did not show any deficits when compared to age norms. A combination of CSF analyses and neuropsychology could be a step toward a more exact diagnosis of MCI as prodromal AD.
|
|
| 4. |
- Nordlund, Arto, 1962, et al.
(författare)
-
Two year outcome of MCI subtypes and aetiologies in the Goteborg MCI study.
- 2010
-
Ingår i: Journal of neurology, neurosurgery, and psychiatry. - : BMJ. - 1468-330X .- 0022-3050. ; 81:5, s. 541-6
-
Tidskriftsartikel (refereegranskat)abstract
- The objective was to study the two year outcome of subjects diagnosed with Mild Cognitive Impairment (MCI). Two hundred and nine subjects diagnosed with MCI were examined with a comprehensive neuropsychological test battery and followed up after two years. After two years 34 subjects (16%) were lost for follow-up. Those subjects did not differ significantly in terms of MCI subclassification, MMSE score or age and education. Of the 175 subjects followed up, 8 (4.5%) had improved to normal, two with amnestic MCI, one from multiple domains MCI, three with single domain MCI and two without any significant impairment at baseline. Forty-four subjects (25%) had progressed to dementia. Out of these 35 were from the multidomain amnestic group and 9 from the multidomain non-amnestic group. The combination of Alzheimer-typical biomarkers (total-tau and amyloid beta) and multidomain amnestic MCI was the strongest predictor of progression to Alzheimer's disease, while vascular disease and multidomain amnestic MCI preceded mixed and vascular dementia. The results suggest that memory impairment alone, or impairment in any one cognitive domain alone, are rather benign conditions. Impairment in several cognitive domains is associated with a more severe outcome over two years. Also, 20% of the subjects who progressed to dementia, including Alzheimer's disease, did not show memory impairment at baseline, which suggests that memory impairment is not always the first symptom of even the most common dementia disorders.
|
|
| 5. |
- Rolstad, Sindre, 1976, et al.
(författare)
-
The Swedish National Adult Reading Test (NART-SWE): a test of premorbid IQ.
- 2008
-
Ingår i: Scandinavian journal of psychology. - : Wiley. - 0036-5564 .- 1467-9450. ; 49:6, s. 577-82
-
Tidskriftsartikel (refereegranskat)abstract
- The purpose of this study was to construct a Swedish version of the National Adult Reading Test (NART-SWE), a test for assessment of premorbid IQ, and to investigate its validity and reliability on healthy controls and patients with mild Alzheimer's disease. As Swedish pronunciation rules are fixed, NART-SWE was constructed using loan words. NART-SWE has satisfactory psychometric properties: Inter-rater and retest reliability as well as internal consistency are very high. The NART-SWE demonstrates face validity. In addition, high correlation with IQ was obtained. A significant model emerged when using NART-SWE to predict IQ. Furthermore, no significant differences were observed when comparing performance for healthy controls' with that of patients with Alzheimer's disease on NART-SWE. It does appear that reading of irregular words is intact in mild Alzheimer's disease.
|
|
