Predicting Post-Concussion Symptom Recovery in Adolescents Using a Novel Artificial Intelligence.

This pilot study explores the possibility of predicting post-concussion symptom recovery at one week post-injury using only objective diffusion tensor imaging (DTI) data inputs to a novel artificial intelligence (AI) system composed of Genetic Fuzzy Trees (GFT). Forty-three adolescents age 11 to 16 years with either mild traumatic brain injury or traumatic orthopedic injury were enrolled on presentation to the emergency department. Participants received a DTI scan three days post-injury, and their symptoms were assessed by the Post-Concussion Symptom Scale (PCSS) at 6 h and one week post-injury. The GFT system was trained using one-week total PCSS scores, 48 volumetric magnetic resonance imaging inputs, and 192 DTI inputs per participant over 225 training runs. Each training run contained a randomly selected 80% of the total sample followed by a 20% validation run. Over a different randomly selected sample distribution, GFT was also compared with six common classification methods. The cascading GFT structure controlled an effectively infinite solution space that classified participants as recovered or not recovered significantly better than chance. It demonstrated 100% and 62% classification accuracy in training and validation, respectively, better than any of the six comparison methods. Recovery sensitivity and specificity were 59% and 65% in the GFT validation set, respectively. These results provide initial evidence for the effectiveness of a GFT system to make clinical predictions of trauma symptom recovery using objective brain measures. Although clinical and research applications will necessitate additional optimization of the system, these results highlight the future promise of AI in acute care.

Prediction of lithium response in first-episode mania using the LITHium Intelligent Agent (LITHIA): Pilot data and proof-of-concept.

OBJECTIVES: Individualized treatment for bipolar disorder based on neuroimaging treatment targets remains elusive. To address this shortcoming, we developed a linguistic machine learning system based on a cascading genetic fuzzy tree (GFT) design called the LITHium Intelligent Agent (LITHIA). Using multiple objectively defined functional magnetic resonance imaging (fMRI) and proton magnetic resonance spectroscopy (1 H-MRS) inputs, we tested whether LITHIA could accurately predict the lithium response in participants with first-episode bipolar mania. METHODS: We identified 20 subjects with first-episode bipolar mania who received an adequate trial of lithium over 8 weeks and both fMRI and 1 H-MRS scans at baseline pre-treatment. We trained LITHIA using 18 1 H-MRS and 90 fMRI inputs over four training runs to classify treatment response and predict symptom reductions. Each training run contained a randomly selected 80% of the total sample and was followed by a 20% validation run. Over a different randomly selected distribution of the sample, we then compared LITHIA to eight common classification methods. RESULTS: LITHIA demonstrated nearly perfect classification accuracy and was able to predict post-treatment symptom reductions at 8 weeks with at least 88% accuracy in training and 80% accuracy in validation. Moreover, LITHIA exceeded the predictive capacity of the eight comparator methods and showed little tendency towards overfitting. CONCLUSIONS: The results provided proof-of-concept that a novel GFT is capable of providing control to a multidimensional bioinformatics problem-namely, prediction of the lithium response-in a pilot data set. Future work on this, and similar machine learning systems, could help assign psychiatric treatments more efficiently, thereby optimizing outcomes and limiting unnecessary treatment.