Precision medicine does not escape the psychiatric field. Precision medicine is a medical model that proposes the customisation of healthcare, with decisions and practices being tailored to the individual patient by use of genetic or other information. Precision medicine is reshaping disease treatment with the potential to provide superior outcomes in smaller patient populations, increasing patient expectations around efficacy. Precision medicine uses biomarkers, data analytics and AI to provide personalised treatment projections. It is constantly pointed out that each person is unique and unrepeatable, but the clinical guidelines propose standardised doses and treatment times for the majority of the population.

According to the Centres for Disease Control and Prevention (CDC), the percentage of adults aged 18 years and older with regular feelings of depression is 4.8%. A patient with depression may present with comorbid insomnia, agitation and anxiety, but there may be patients with depression who experience hypersomnia, psychomotor retardation and loss of interest and motivation. Therefore, the treatment cannot be the same. Precision medicine opens the door to the personalisation of treatments using more detailed diagnostic systems, since each specific group of symptoms can inform the choice of treatment differently.

Spring Health assures that precision medicine can help to accurately predict mental diseases, since 70% of the first treatments are not effective. With their new Precision Mental Healthcare approach, they aim to reduce trial-and-error treatments, identify the right antidepressant, predict which patient might relapse into depression, and search for different treatment options.

The medical community is quickly adopting AI into its processes. Clinical decision support systems are a powerful tool in the service of health professionals, and must be transparent both in their design and in the machine learning model. For Spring Health, the first step is to collect data on everyone which includes specific symptoms, family and psychiatric history, and socio-demographics among others. These data are then compared with a set of datapoints for machine learning to recommend a tailored navigation plan. Spring Health has used patient-reported data from patients with depression to identify the variables that were most predictive of treatment outcomes, before using these variables to train a machine learning model to predict clinical remission.