Resumen
| Idioma original | English |
|---|---|
| DOI | |
| Estado | Published - 5 jun 2013 |
| Publicado de forma externa | Sí |
| Evento | Proceedings of SPIE - The International Society for Optical Engineering - Duración: 5 jun 2013 → … |
Conference
| Conference | Proceedings of SPIE - The International Society for Optical Engineering |
|---|---|
| Período | 5/6/13 → … |
Huella dactilar
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering
Citar esto
}
Improved multimodal biomarkers for Alzheimer's disease and mild cognitive impairment diagnosis - Data from ADNI. / Martinez-Torteya, Antonio; Treviño-Alvarado, Víctor; Tamez-Peña, José.
2013. Papel presentado en Proceedings of SPIE - The International Society for Optical Engineering, .Resultado de la investigación
TY - CONF
T1 - Improved multimodal biomarkers for Alzheimer's disease and mild cognitive impairment diagnosis - Data from ADNI
AU - Martinez-Torteya, Antonio
AU - Treviño-Alvarado, Víctor
AU - Tamez-Peña, José
PY - 2013/6/5
Y1 - 2013/6/5
N2 - The accurate diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) confers many clinical research and patient care benefits. Studies have shown that multimodal biomarkers provide better diagnosis accuracy of AD and MCI than unimodal biomarkers, but their construction has been based on traditional statistical approaches. The objective of this work was the creation of accurate AD and MCI diagnostic multimodal biomarkers using advanced bioinformatics tools. The biomarkers were created by exploring multimodal combinations of features using machine learning techniques. Data was obtained from the ADNI database. The baseline information (e.g. MRI analyses, PET analyses and laboratory essays) from AD, MCI and healthy control (HC) subjects with available diagnosis up to June2012 was mined for case/controls candidates. The data mining yielded 47 HC, 83 MCI and 43 AD subjects for biomarker creation. Each subject was characterized by at least 980 ADNI features. A genetic algorithm feature selection strategy was used to obtain compact and accurate cross-validated nearest centroid biomarkers. The biomarkers achieved training classification accuracies of 0.983, 0.871 and 0.917 for HC vs. AD, HC vs. MCI and MCI vs. AD respectively. The constructed biomarkers were relatively compact: from 5 to 11 features. Those multimodal biomarkers included several widely accepted univariate biomarkers and novel image and biochemical features. Multimodal biomarkers constructed from previously and non-previously AD associated features showed improved diagnostic performance when compared to those based solely on previously AD associated features. © 2013 SPIE.
AB - The accurate diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) confers many clinical research and patient care benefits. Studies have shown that multimodal biomarkers provide better diagnosis accuracy of AD and MCI than unimodal biomarkers, but their construction has been based on traditional statistical approaches. The objective of this work was the creation of accurate AD and MCI diagnostic multimodal biomarkers using advanced bioinformatics tools. The biomarkers were created by exploring multimodal combinations of features using machine learning techniques. Data was obtained from the ADNI database. The baseline information (e.g. MRI analyses, PET analyses and laboratory essays) from AD, MCI and healthy control (HC) subjects with available diagnosis up to June2012 was mined for case/controls candidates. The data mining yielded 47 HC, 83 MCI and 43 AD subjects for biomarker creation. Each subject was characterized by at least 980 ADNI features. A genetic algorithm feature selection strategy was used to obtain compact and accurate cross-validated nearest centroid biomarkers. The biomarkers achieved training classification accuracies of 0.983, 0.871 and 0.917 for HC vs. AD, HC vs. MCI and MCI vs. AD respectively. The constructed biomarkers were relatively compact: from 5 to 11 features. Those multimodal biomarkers included several widely accepted univariate biomarkers and novel image and biochemical features. Multimodal biomarkers constructed from previously and non-previously AD associated features showed improved diagnostic performance when compared to those based solely on previously AD associated features. © 2013 SPIE.
U2 - 10.1117/12.2008100
DO - 10.1117/12.2008100
M3 - Paper
ER -