Welcome to WordPress. This is your first post. Edit or delete it, then start writing!
As per WHO one in four people in the world will be affected by a mental or neurological disorder at some point in their lives. Around 450 million people currently suffer from such conditions, placing mental disorders among the leading causes of ill health and disability worldwide.
Mood Disorders – These disorders are also called affective disorders which involve the persistent feeling of sadness or period of feeling overly happy, or fluctuations from extreme happiness to extreme sadness. The most common mood disorders are depression, bipolar disorder, and cyclothymic disorder.
Another type of disorder is Psychotic disorder – Which involves distorted awareness and thinking. Two of the main common symptoms of psychotic disorders are hallucinations, where the patient experiences images or sounds that are not real.
Delusions- These are false fixed beliefs that the patient accepts as true, despite the evidence to the contrary. Schizophrenia is an example of a psychotic disorder. These disorders cause detachment from reality.
The question today is how technological advancement in the field of Artificial Intelligence can help in the diagnosis of mental disorders. Therefore it is important to understand what Artificial Intelligence is.
Artificial Intelligence is a software program that can think and act like humans. Basically, we are designing programs that act like our brains but with a higher level of computing power. The Artificial Intelligent program has multiple tools and subsets which have different functions, but they combine together to create an Artificial Intelligent program.
One of the important subsets of AI is Machine Learning – Machine Learning are algorithms that learn complex patterns from data and make predictions from it. Machine learning programs have the following steps:-
It takes data to train the system. This data can be in the form of structured or unstructured data. The data can be extracted from the database. It can be in the form of text, it can be in the form of images. After processing this data, the algorithm understands and learns the pattern shown by this vast data. It can classify the data that it has not seen before. Machine learning is trained by the features or traits of the subjects. In the case of patients who suffer from a mental health issue, this data can be in the form of text data that a patient may write on social media sites, the spoken data, language, and data captured through spoken media and then converted to text through the use of Natural Language processing.
An artificial intelligence program can be used to detect Depression, we take an example of a research paper where the researchers accessed the Facebook status which was posted by 683 patients who visited a large urban academic emergency department, 114 of whom had a diagnosis of depression in their medical record. The research was undertaken to detect and predict the diagnosis of the depression problem from the language used in the Facebook posts.
Prediction performances of a future diagnosis of depression in the EMR based on demographics and Facebook posting activity reported as cross-validated out-of-sample AUCs.
With the Facebook data in hand and using the ML model, researchers could identify depressed patients with a fair degree of accuracy at AUC=0.69, approximately matching the accuracy of screening surveys benchmarked against medical records. They found that the language predictor of depression includes emotional(sadness), interpersonal(loneliness, hostility), and cognitive(preoccupation with self, rumination) processes. From the result, it was also observed that the user who ultimately had a diagnosis of depression used more first-person singular pronouns( I, My, me)suggesting a preoccupation with self. The results show that the Facebook language-based prediction model performs similarly to screening surveys in identifying patients with depression when using diagnostic codes in the EMR to identify a diagnosis of depression. The growth of social media and the continuous improvement of machine learning algorithms suggest that social media-based screening methods for depression may become increasingly feasible and more accurate. The present analysis therefore also suggests that the social media-based prediction of future depression status may be possible as early as 3 months before the first documentation of depression in the medical record. Novel avenues are also becoming available to detect depression. These methods also include algorithmic analysis of phone sensors, GPS position on the phone, and facial expression in images, and videos shared on social platforms. The predictive model of Logistic regression was used
Some of the companies are also involved in building healthcare applications.
Ginger is a chat application that is used by employers that provide direct counseling to their employees. The algorithm analyses the words someone uses and then relies on the training from more than 2 billion behavioral data samples, 45 million chat messages, and 2 million clinical assessments to provide a recommendation.
The CompanionMX system has an app that allows patients being treated with depression, bipolar disorders, and other conditions to create an audio log where they can talk about how they are feeling. The AI system analyses the recording as well as looks for changes in behavior for proactive mental health monitoring. Bark, a parental control phone tracker app, monitors major messaging and social media platforms to look for signs of cyberbullying, depression, suicidal thoughts, and sexting on a child’s phone
Advantages of Artificial Intelligence in Healthcare
Support Mental Health professionals – AI can act as a support for health professionals in doing their jobs. Algorithms can analyze data much faster than humans can suggest possible treatments, monitor a patient’s progress, and alert the human professional to any concern.
24/7 access- Due to the lack of human mental health professionals, it can take months to take an appointment. AI provides a tool that an individual can access without waiting for an appointment.
Not
expensive – The cost of care prohibits
some individuals from seeking help. This
is more affordable
Comfort talking to a bot- It is easier to disclose information to a bot than to a human
Cognitive computers will analyze a patient’s speech or written words to look for tell-tale indicators found in language, including meaning, syntax, and intonation. Combining the results of these measurements with those from wearable devices and imaging systems (MRIs and EEGs) can paint a more complete picture of the individual for health professionals to better identify, understand, and treat the underlying disease, be it Parkinson’s, Alzheimer’s, Huntington’s disease, PTSD or even underdevelopment conditions such as autism and ADHD.
In a study with Columbia University psychiatrists, were able to predict, with 100 percent accuracy, who among a population of at-risk adolescents would develop their first episode of psychosis within two years. In other research with our Pfizer colleagues, we’re using only about 1 minute of speech from Parkinson’s patients to better track, predict and monitor the disease. We’re already seeing results of nearly 80 percent accuracy. In five years, we hope to advance the study of using words as windows into our mental health.
IBM is building an automated speech analysis application that runs off a mobile device. By taking approximately one minute of speech input, the system uses text-to-speech, advanced analytics, machine learning, natural language processing technologies, and computational biology to provide a real-time, overview of the patient’s mental health.
Artificial Intelligence will play a pivotal role in creating groundbreaking tools to analyze and detect mental health problems and will play a substantially positive role in increasing the treatment coverage by early diagnosis and possibly be able to reduce the death rates due to mental health problems.
REFERENCE
Eichstaedt, Johannes C., et al.
“Facebook Language Predicts Depression in Medical Records.” PNAS,
National Academy of Sciences, 30 Oct. 2018, www.pnas.org/content/115/44/11203.
Marr, Bernard. “The Incredible
Ways Artificial Intelligence Is Now Used In Mental Health.” Forbes,
Forbes Magazine, 22 May 2019, www.forbes.com/sites/bernardmarr/2019/05/03/the-incredible-ways-artificial-intelligence-is-now-used-in-mental-health/#74cf5137d02e.
Cecchi, Guillermo. “With AI,
Our Words Will Be a Window into Our Mental Health.” With AI, Our Words Will
Be a Window into Our Mental Health- IBM Research, www.research.ibm.com/5-in-5/mental-health/.
IBM Research Editorial Staff.
“IBM 5 in 5: With AI, Our Words Will Be a Window into Our Mental Health.” IBM
Research Blog, 5 Jan. 2017,
www.ibm.com/blogs/research/2017/1/ibm-5-in-5-our-words-will-be-the-windows-to-our-mental-health/.
Bedi, Gillinder, et al.
“Automated Analysis of Free Speech Predicts Psychosis Onset in High-Risk
Youths.” Nature News, Nature Publishing Group, 26 Aug. 2015,
www.nature.com/articles/npjschz201530.
WHO. “Mental Disorders Affect
One in Four People.” World Health Organization, World Health
Organization, 4 Oct. 2001, www.who.int/whr/2001/media_centre/press_release/.
Goldberg, Joseph. “Mental Health: Types of Mental Illness.” WebMD, WebMD, 6 Apr. 2019, www.webmd.com/mental-health/mental-health-types-illness#1
