Machine learning with neuroimaging biomarkers: Application in the diagnosis and prediction of drug addiction

Abstract

Drug abuse is a serious problem worldwide. Owing to intermittent intake of certain substances and the early inconspicuous clinical symptoms, this brings huge challenges for timely diagnosing addiction status and preventing substance use disorders (SUDs). As a non-invasive technique, neuroimaging can capture neurobiological signatures of abnormality in multiple brain regions caused by drug consumption in each clinical stage, like parenchymal morphology alteration as well as aberrant functional activity and connectivity of cerebral areas, making it realizable to diagnosis, prediction and even preemptive therapy of addiction. Machine learning (ML) algorithms primarily used for classification have been extensively applied in analysing medical imaging datasets. Significant neurobiological characteristics employed and revealed by classifiers were used to diagnose addictive states and predict initiation and vulnerability to drug usage, treatment abstinence, relapse and resilience of addicts and the risk of SUD. In this review, we summarize application of ML methods in neuroimaging focusing on addicts' diagnosis of clinical status and risk prediction and elucidate the discriminative neurobiological features from brain electrophysiological, morphological and functional perspectives that contribute most to the classifier, finally highlighting the auxiliary role of ML in addiction treatment.

Connectome-based predictive modeling of Internet addiction symptomatology

“…Notably, our research is in part representative of progress in neuroscience and advances the application of machine-learning methods that use functional brain connections as feature values to build neuroimaging-based behavior prediction. The CPM is designed to uncover critical brain features that can be applied to improve the accuracy of diagnosis and the success of treatment for IAS in clinical practice ( Yang et al ., 2023 ). Within this framework, a growing number of studies have developed predictive models based on brain imaging features to distinguish those with IAD from healthy controls or to predict symptom severity.…”

Exploring the potential of the metaverse medical paradigm in drug addiction treatment: a preliminary discussion and future prospects

“…MMP could synergise with other paradigms, potentially involving neural mechanisms in plasticity recovery in the reward-punishment circuit, executive function and contextual memory, including the thalamus, hippocampus and frontal regions. 1 So far, the therapeutic effectiveness of MPP remains unclear, requiring further exploration through comparisons with other routine paradigms and placebo groups. Proposing an optimised approach (eg, MMP, rTMS, TAU, CBT, etc) is essential for maximising the use of medical resources.…”

“…Drug addiction is a chronic and recurrent encephalopathy characterised by impulsive behaviour, spiritual cravings, psychological distortion and physical damage. 1 According to the role of molecular biology mechanisms on the central nervous system, addictive substances can be classified as inhibitors (eg, opioids, etc), stimulants (eg, methamphetamine (MA), nicotine, cocaine, etc) and hallucinogens (eg, cannabis, etc). 1 As published by the World Drug Report 2022, over 284 million individuals aged 15–64 worldwide have reportedly abused drugs in the past 12 months, emphasising the international challenge of effective detox treatment.…”

“… 1 According to the role of molecular biology mechanisms on the central nervous system, addictive substances can be classified as inhibitors (eg, opioids, etc), stimulants (eg, methamphetamine (MA), nicotine, cocaine, etc) and hallucinogens (eg, cannabis, etc). 1 As published by the World Drug Report 2022, over 284 million individuals aged 15–64 worldwide have reportedly abused drugs in the past 12 months, emphasising the international challenge of effective detox treatment. The detoxification process consists of three phases: physiological recovery for the remission of withdrawal symptoms, psychological rehabilitation for the elimination of mental dependence, and social function restoration for the return to life, with the second phase being the most significant challenge.…”

A generalizable functional connectivity signature characterizes brain dysfunction and links to rTMS treatment response in cocaine use disorder

“…Furthermore, we aimed to investigat the link between the FC signature and treatment outcome, which was typically missed in previous phenotyping studies 20,27,28 . By examining the discriminative FC signature as a predictor of treatment response to rTMS in 45 CUD patients who were randomly assigned to receive either 5 Hz active or sham rTMS on the left dorsolateral prefrontal cortex, we demonstrated the utility of this diagnostic FC signature for prognostic purpose of predicting treatment response.…”