"We can ask people a small set of questions and get a good sense of whether they'll become depressed," said lead author Tamar Krishnamurti, an associate professor of general internal medicine at the University of Pittsburgh, US.
"Strikingly, a lot of risk factors for future depression are things that are modifiable -- such as sleep quality, concerns about labour and delivery and, importantly, access to food -- meaning that we can and should do something about them," said Krishnamurti.
Identifying women vulnerable to developing depression in the earlier stages of pregnancy could help tailor preventive care and offer support to address underlying causes, the researchers said.
For the study, the researchers analysed the survey responses of 944
In their first trimester of pregnancy, the women responded to questions about demographics and their medical history, along with those on stress and feelings of sadness.
Some of the 944 women also responded to optional questions on social factors related to their health, such as food insecurity. All women were screened for depression once every trimester.
The researchers developed six machine-learning models using all the data. The best one was found to be 89 per cent accurate in predicting depression in a pregnant woman. A machine learning algorithm is a form of artificial intelligence that learns from past data to make predictions.
The accuracy of the model rose to 93 per cent when the researchers included the responses to optional questions on health-related social factors.
They found that food insecurity, or access to food, emerged as an important risk factor for pregnant women to develop depression in the latter stages of pregnancy.
The researchers are now developing methods to integrate these survey questions into clinical settings and identifying how clinicians could have these conversations with patients about the risk of depression.
SEE ALSO:
Tata Altroz Racer hatchback launched in India starting at ₹9.49 lakh
Nvidia beats Apple, becomes second most valuable company: Top 10 companies by market cap
Indian smartwatch shipments remain flat in Q1 2024, annual shipments expected to end in a decline