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

Effect of extent of preterm birth and SGA birth on results.The group of 74 participants that were born preterm is represented by colored circles. The vertical distance from the horizontal yellow line represents the distance to decision boundary. The further above the line is more like preterm whereas further below the line is more like control. In part A the color code represents the 11 moderately preterm (blue), 36 very preterm (green) and 27 extremely preterm (red) births based on gestational age. In part B the 16 individuals that were born SGA are represented by red circles while the other 58 by blue circles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0123108.g004: Effect of extent of preterm birth and SGA birth on results.The group of 74 participants that were born preterm is represented by colored circles. The vertical distance from the horizontal yellow line represents the distance to decision boundary. The further above the line is more like preterm whereas further below the line is more like control. In part A the color code represents the 11 moderately preterm (blue), 36 very preterm (green) and 27 extremely preterm (red) births based on gestational age. In part B the 16 individuals that were born SGA are represented by red circles while the other 58 by blue circles.

Mentions: When testing the heterogeneity of the group of volunteers born preterm we found that the gestational age was indeed an important factor. Fig 4A depicts the results of the above SVM analysis on the entire group where the group of subjects born preterm is color–coded (blue = moderately preterm, green = very preterm, red = extremely preterm). The mean distances to the decision boundary for these 3 subgroups are 0.43, 0.73 and 1.20 respectively. The additional specific analyses performed between subgroups corroborated these findings. When including only the controls and the 27 individuals born extremely preterm (Group +3) the SVM classification was 100% accurate. This accuracy dropped to 90% when including only the controls and the 36 individuals born very preterm (Group +2). When directly comparing the 27 individuals born extremely preterm and the 36 individuals born very preterm directly the classification rate was 67% correct.


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)

Effect of extent of preterm birth and SGA birth on results.The group of 74 participants that were born preterm is represented by colored circles. The vertical distance from the horizontal yellow line represents the distance to decision boundary. The further above the line is more like preterm whereas further below the line is more like control. In part A the color code represents the 11 moderately preterm (blue), 36 very preterm (green) and 27 extremely preterm (red) births based on gestational age. In part B the 16 individuals that were born SGA are represented by red circles while the other 58 by blue circles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0123108.g004: Effect of extent of preterm birth and SGA birth on results.The group of 74 participants that were born preterm is represented by colored circles. The vertical distance from the horizontal yellow line represents the distance to decision boundary. The further above the line is more like preterm whereas further below the line is more like control. In part A the color code represents the 11 moderately preterm (blue), 36 very preterm (green) and 27 extremely preterm (red) births based on gestational age. In part B the 16 individuals that were born SGA are represented by red circles while the other 58 by blue circles.
Mentions: When testing the heterogeneity of the group of volunteers born preterm we found that the gestational age was indeed an important factor. Fig 4A depicts the results of the above SVM analysis on the entire group where the group of subjects born preterm is color–coded (blue = moderately preterm, green = very preterm, red = extremely preterm). The mean distances to the decision boundary for these 3 subgroups are 0.43, 0.73 and 1.20 respectively. The additional specific analyses performed between subgroups corroborated these findings. When including only the controls and the 27 individuals born extremely preterm (Group +3) the SVM classification was 100% accurate. This accuracy dropped to 90% when including only the controls and the 36 individuals born very preterm (Group +2). When directly comparing the 27 individuals born extremely preterm and the 36 individuals born very preterm directly the classification rate was 67% correct.

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