Limits...
Investigating the use of support vector machine classification on structural brain images of preterm-born teenagers as a biological marker.

Chu C, Lagercrantz H, Forssberg H, Nagy Z - PLoS ONE (2015)

Bottom Line: Separately, a random half of the available data were used for training twice and each time the other, unseen, half of the data was classified, resulting 86% and 91% accurate classifications.Statistically significant correlations were also found between IQ (R = -0.30, p < 0.001) and the distance to decision boundary.The long-term goal is to automatically and non-invasively predict the outcome of preterm-born individuals on an individual basis using as early a scan as possible.

View Article: PubMed Central - PubMed

Affiliation: DeepMind Technologies Ltd., London, United Kingdom; Wellcome Trust Centre for Neuroimaging, UCL Institute of Neurology, London, United Kingdom.

ABSTRACT
Preterm birth has been shown to induce an altered developmental trajectory of brain structure and function. With the aid support vector machine (SVM) classification methods we aimed to investigate whether MRI data, collected in adolescence, could be used to predict whether an individual had been born preterm or at term. To this end we collected T1-weighted anatomical MRI data from 143 individuals (69 controls, mean age 14.6y). The inclusion criteria for those born preterm were birth weight ≤ 1500g and gestational age < 37w. A linear SVM was trained on the grey matter segment of MR images in two different ways. First, all the individuals were used for training and classification was performed by the leave-one-out method, yielding 93% correct classification (sensitivity = 0.905, specificity = 0.942). Separately, a random half of the available data were used for training twice and each time the other, unseen, half of the data was classified, resulting 86% and 91% accurate classifications. Both gestational age (R = -0.24, p<0.04) and birth weight (R = -0.51, p < 0.001) correlated with the distance to decision boundary within the group of individuals born preterm. Statistically significant correlations were also found between IQ (R = -0.30, p < 0.001) and the distance to decision boundary. Those born small for gestational age did not form a separate subgroup in these analyses. The high rate of correct classification by the SVM motivates further investigation. The long-term goal is to automatically and non-invasively predict the outcome of preterm-born individuals on an individual basis using as early a scan as possible.

No MeSH data available.


Related in: MedlinePlus

Distance to decision boundary in relation to BW and IQ.In parts A & B the distance to decision boundary (i.e. vertical distance relative to horizontal yellow line) is displayed for both groups. In part A, all 143 subjects are shown while in part B only those with IQ data are represented. The color code in part A indicates birth weight of the individual while on the bottom it represents the full IQ scores (see respective color bars in middle). In part C the distance to decision boundary (horizontal axis) and the full IQ score (vertical axis) are plotted against each other for the group of subjects born preterm. The red dashed line indicates the linear fit to the data (R = –0.34, p < 0.0103).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4383582&req=5

pone.0123108.g005: Distance to decision boundary in relation to BW and IQ.In parts A & B the distance to decision boundary (i.e. vertical distance relative to horizontal yellow line) is displayed for both groups. In part A, all 143 subjects are shown while in part B only those with IQ data are represented. The color code in part A indicates birth weight of the individual while on the bottom it represents the full IQ scores (see respective color bars in middle). In part C the distance to decision boundary (horizontal axis) and the full IQ score (vertical axis) are plotted against each other for the group of subjects born preterm. The red dashed line indicates the linear fit to the data (R = –0.34, p < 0.0103).

Mentions: All measures of IQ were significantly correlated with the distance to decision boundary when both groups were considered: full IQ (R = –0.30, p < 0.001), performance IQ (R = –0.23, p < 0.0133) and verbal IQ (R = –0.29, p = 0.0012). Within only the group of individuals born preterm the correlation with Full IQ was also statistically significant (R = –0.34, p < 0.0103). Fig 5 depicts the prediction scores for both groups. Note that, while the mean predictive scores are clearly distinct for the two groups some individuals of each group possess scores, which could be representative of the other group. The color of the circles in Fig 5A represents the birth weight. For the subset of the group for which it was available, the IQ scores were used to color code the scatter plot in Fig 5B. While there is variability, the tendency of the high IQ scores of the control group and the low IQ scores of the case group were farther from the decision boundary. Fig 5C plots the distance to decision boundary on the x–axis against IQ on the y–axis. The 7 preterm–born individuals who fall below the horizontal decision boundary (horizontal yellow line) in Fig 5A and 5B are shown to the left of the vertical line in Fig 5C.


Investigating the use of support vector machine classification on structural brain images of preterm-born teenagers as a biological marker.

Chu C, Lagercrantz H, Forssberg H, Nagy Z - PLoS ONE (2015)

Distance to decision boundary in relation to BW and IQ.In parts A & B the distance to decision boundary (i.e. vertical distance relative to horizontal yellow line) is displayed for both groups. In part A, all 143 subjects are shown while in part B only those with IQ data are represented. The color code in part A indicates birth weight of the individual while on the bottom it represents the full IQ scores (see respective color bars in middle). In part C the distance to decision boundary (horizontal axis) and the full IQ score (vertical axis) are plotted against each other for the group of subjects born preterm. The red dashed line indicates the linear fit to the data (R = –0.34, p < 0.0103).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4383582&req=5

pone.0123108.g005: Distance to decision boundary in relation to BW and IQ.In parts A & B the distance to decision boundary (i.e. vertical distance relative to horizontal yellow line) is displayed for both groups. In part A, all 143 subjects are shown while in part B only those with IQ data are represented. The color code in part A indicates birth weight of the individual while on the bottom it represents the full IQ scores (see respective color bars in middle). In part C the distance to decision boundary (horizontal axis) and the full IQ score (vertical axis) are plotted against each other for the group of subjects born preterm. The red dashed line indicates the linear fit to the data (R = –0.34, p < 0.0103).
Mentions: All measures of IQ were significantly correlated with the distance to decision boundary when both groups were considered: full IQ (R = –0.30, p < 0.001), performance IQ (R = –0.23, p < 0.0133) and verbal IQ (R = –0.29, p = 0.0012). Within only the group of individuals born preterm the correlation with Full IQ was also statistically significant (R = –0.34, p < 0.0103). Fig 5 depicts the prediction scores for both groups. Note that, while the mean predictive scores are clearly distinct for the two groups some individuals of each group possess scores, which could be representative of the other group. The color of the circles in Fig 5A represents the birth weight. For the subset of the group for which it was available, the IQ scores were used to color code the scatter plot in Fig 5B. While there is variability, the tendency of the high IQ scores of the control group and the low IQ scores of the case group were farther from the decision boundary. Fig 5C plots the distance to decision boundary on the x–axis against IQ on the y–axis. The 7 preterm–born individuals who fall below the horizontal decision boundary (horizontal yellow line) in Fig 5A and 5B are shown to the left of the vertical line in Fig 5C.

Bottom Line: Separately, a random half of the available data were used for training twice and each time the other, unseen, half of the data was classified, resulting 86% and 91% accurate classifications.Statistically significant correlations were also found between IQ (R = -0.30, p < 0.001) and the distance to decision boundary.The long-term goal is to automatically and non-invasively predict the outcome of preterm-born individuals on an individual basis using as early a scan as possible.

View Article: PubMed Central - PubMed

Affiliation: DeepMind Technologies Ltd., London, United Kingdom; Wellcome Trust Centre for Neuroimaging, UCL Institute of Neurology, London, United Kingdom.

ABSTRACT
Preterm birth has been shown to induce an altered developmental trajectory of brain structure and function. With the aid support vector machine (SVM) classification methods we aimed to investigate whether MRI data, collected in adolescence, could be used to predict whether an individual had been born preterm or at term. To this end we collected T1-weighted anatomical MRI data from 143 individuals (69 controls, mean age 14.6y). The inclusion criteria for those born preterm were birth weight ≤ 1500g and gestational age < 37w. A linear SVM was trained on the grey matter segment of MR images in two different ways. First, all the individuals were used for training and classification was performed by the leave-one-out method, yielding 93% correct classification (sensitivity = 0.905, specificity = 0.942). Separately, a random half of the available data were used for training twice and each time the other, unseen, half of the data was classified, resulting 86% and 91% accurate classifications. Both gestational age (R = -0.24, p<0.04) and birth weight (R = -0.51, p < 0.001) correlated with the distance to decision boundary within the group of individuals born preterm. Statistically significant correlations were also found between IQ (R = -0.30, p < 0.001) and the distance to decision boundary. Those born small for gestational age did not form a separate subgroup in these analyses. The high rate of correct classification by the SVM motivates further investigation. The long-term goal is to automatically and non-invasively predict the outcome of preterm-born individuals on an individual basis using as early a scan as possible.

No MeSH data available.


Related in: MedlinePlus