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

Abstract

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 fMRI and proton MRS (1H-MRS) inputs, we tested whether LITHIA could accurately predict 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 eight weeks and both fMRI and 1H-MRS scans at baseline pre-treatment. We trained LITHIA using 18 1H-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 Results provide proof-of-concept that a novel GFT is capable of providing control to a multidimensional bioinformatics problem – namely prediction of 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.

<p>Challenges and Future Prospects of Precision Medicine in Psychiatry</p>

“…Yet, there have been several attempts, partly successful, to implement predictive models of specific outcomes (for instance treatment response) based purely on clinical data ( Table 2). These studies have mainly focused on: 1) response to lithium, [22][23][24] the mainstay of treatment of bipolar disorder (BD), a recurrent mood disorder characterized by alternating episodes of depression and mania; 2) prediction of resistance to antidepressants in major depressive disorder; 25,26 and 3) stratification of the risk 27 and outcome prediction [28][29][30] in schizophrenia.…”

“…33,34 It should be noted that attempts of predicting lithium response have been made also using neuroimaging data. 24 The proof of concept study of Fleck et al showed that a machine learning system applied to functional magnetic resonance imaging (fMRI) and proton magnetic resonance spectroscopy ( 1 H-MRS) inputs were able to predict post-treatment symptom reductions at 8 weeks of lithium treatment with at least 88% accuracy in training and 80% accuracy in validation. 24 However, the outcome chosen for the analysis (short-term lithium response) was again different from the one typically used in clinical and genetic studies.…”

Machine learning and big data analytics in bipolar disorder: A position paper from the International Society for Bipolar Disorders Big Data Task Force

“…These types of trials will shift the focus from group‐level averages to individuals and will ultimately leverage each person's unique clinical and biological profile to improve selection of treatment. Table S3 shows machine learning studies predicting treatment response and adverse effects …”

“…68 In the field of BD, a pilot study developed a treatment response calculator for lithium. 71 Authors included 20 subjects with first-episode bipolar mania who received lithium over Machine learning guided interventions will not only facilitate the selection of treatment based on efficacy but also aid in the prevention of side effects. 68 In this sense, a study with more than 5700 patients undergoing lithium treatment built a predictive algorithm to renal insufficiency by using logistic regression and electronic medical records.…”

Teaching to See Behaviors—Using Machine Learning?

“…This pattern of learning on its own may be continued in a cyclical manner as long as the program is running and data are supplied. Applying this to psychiatry, Fleck et al [2] trained a machine learning system using baseline, pre-drug scans (obtained with functional magnetic resonance imaging and proton magnetic resonance spectroscopy) from bipolar patients. Twenty patients had a full trial of lithium therapy; some had responded and others had not.…”