Research: How LKCMedicine Is Advancing Early Detection of Psychosis in Asian Youth
By Retna Devi D/O Shanmuga Retnam
A study by researchers from LKCMedicine and NHG Health’s Institute of Mental Health (IMH) is changing the conversation on how clinicians and psychiatrists assess mental health conditions, particularly psychosis, among Asian youth.
 |  |
| L-R: Co-Principal Investigators, Assistant Professor Wilson Goh from LKCMedicine and NTU Centre of AI in Medicine and Associate Professor Jimmy Lee from IMH and LKCMedicine | |
Recently published in Translational Psychiatry, a highly reputed peer-reviewed journal focused on bridging neuroscience research with novel treatments for psychiatric disorders, the team identified blood-based proteomic biomarkers that may help predict which individuals within an at-risk group are most likely to develop psychosis, a serious mental health condition that is characterised by symptoms such as hallucinations, delusions and disorganised thinking. It typically emerges between adolescence to early adulthood.
In Singapore, one in 43 individuals aged 18 and up has had a diagnosis of psychosis, which includes schizophrenia, in their lifetime. Given its early onset and long-term impact, there is a critical need for more reliable tools to identify individuals at risk and enable earlier intervention.
To understand how these findings signal a shift away from the traditional methods of diagnosing psychosis as well as its far-reaching implications, we spoke to LKCMedicine’s Assistant Professor Wilson Goh, who co-led the study.
Here are his takeaways:
- The first large-scale proteomics study of psychosis risk in an Asian population
“Diagnosing psychosis is not always straightforward and it often relies on symptomological and behavioural assessments which take time. Since early intervention is essential to good management and even recovery, the team set out to understand if there were molecular markers unique to Asian populations, especially youth, that would help us objectively and accurately predict who would be at the highest risk of having their first psychotic episode,” shared Asst Prof Goh.
To answer their question, the researchers developed three protein-based models, utilising data from IMH’s “Longitudinal Youth at Risk Study” (LYRIKS), which was designed to comprehensively assess the social, clinical and biological risk factors associated with youths at ultra-high risk of developing psychosis.
For comparison, they also examined two models based on protein signatures identified by a different five-year multi-center research project, the European Network of National Schizophrenia Networks Studying Gene-Environment Interactions (EU-GEI).
The research team found that models based on the European protein patterns achieved accuracy levels of 75% to 81% on the LYRIKS dataset.
In comparison, models developed using the LYRIKS dataset reached accuracy levels of up to 96%, making it the first predictive signature for an Asian cohort.
Additionally, the results showed that while the specific proteins identified differed between the LYRIKS and Caucasian groups, similar biological processes, such as immune function, were observed in both.
“These findings are encouraging as they showed that protein signatures identified in Caucasian populations could be applied more broadly, reinforcing a strong biological basis for mental health progression. It also offers insights into how an Asian-specific signature behaves and performs. This moves the field closer to molecular-based profiling that can support existing clinical approaches, bringing us a step closer to more personalised, biology-based care,” noted Asst Prof Goh.
- Proteomics is a gamechanger that has made blood-based prediction possible
Proteomics—the large-scale study of proteins, which are found in our cells and tissues and carry out nearly all biological functions—was the cornerstone of this research.
“Our genes provide the blueprint for our bodies, but proteins are what bring that blueprint to life. By studying proteins, we can better understand how genetic instructions are used and interpreted to shape biological function in the body and mind,” explained Asst Prof Goh.
Despite being a relatively new discipline that can be traced back to the 1970s, proteomics has made significant strides in understanding the biological underpinnings of diseases. The EU-GEI project that identified key protein signatures related to psychotic disorders is one such example.
However, Asst Prof Goh noted that the EU-GEI study concluded in 2015, and proteomics has since evolved rapidly due to advances in mass spectrometry and automation, which make it easier to analyse complex biological samples.
The LKCMedicine and IMH research team benefitted from these developments, allowing them to utilise an Orbitrap Astral mass spectrometer, a cutting-edge, high-performing analyser, and advanced machine learning methods to examine 1,757 different proteins and understand their characteristics.
Fun fact: Although there are about 20,000 genes, the human body contains over 100,000 different proteins, each performing specialised functions. The proteins analysed in this study represent only a small fraction of this vast biological landscape.
The team is keen to leverage Artificial Intelligence technology to identify more significant protein signatures.
- A step towards preventive and personalised mental healthcare
Although the study successfully developed an Asian signature for psychosis, these findings will need to be validated in larger, independent studies across different populations before clinical implementation.
Beyond psychosis, Asst Prof Goh is cognisant that about one in three young people aged 15 to 35 in Singapore display symptoms of depression, anxiety or stress. He hopes to ascertain if there are proteomic biomarkers related to anxiety and depression and how these in turn can support early interventions to benefit a wider swath of youth.
“A lot of serious mental health disorders and issues emerge adolescence. If we cannot tackle this early on in life, the knock-on effects can be tremendous on the individual and our healthcare system,” he remarked.