NLP and Conversational AI for Compassionate AI Psychologist with Human-like Memory

NLP and Conversational AI for Compassionate AI Psychologist with Human-like Memory

Build an AI psychologist which will be able to conduct compassionate conversations by using a voice-based conversational AI approach, with the ability to identify the emotions of the users and their underlying mental health state. In this 8-week challenge, you will join a collaborative team of 50 AI engineers.

 

The problem

During the pandemic, we saw a mental health ‘surge’ with a sharp increase in people experiencing anxiety (health anxiety, loneliness, etc.) and stress (including Post Traumatic Stress).

Surveys by such organizations as YouGov and Mental Health America show that, during the pandemic, workers were more stressed than ever. This included anxiety regarding health, finance, and employment, as well as broader issues associated with PTSD, burnout, and moderate depression.

Nearly two-thirds of the UK population (63%) felt anxious at least several times a month during the Spring of 2020. One in five (20%) reported feeling anxious on most days of the week or even more frequently.

Mental Health America’s 2021 study shows the strain on employees, with burnout prevalent and more than half of the respondents actively looking for another job.

There is an increased strain on an already-overstretched mental health service that, in some part, has been accommodated by a growing number of apps as well as telehealth calls (Skype / Zoom calls to human therapists).

 

The project goals

The project goal is to build an AI psychologist which will be able to conduct compassionate conversations by using a voice-based conversational AI approach, with the ability to identify the emotions of the user and their underlying mental health state and the capacity to remember these users’ states by possessing a human-like memory.

 

The data

This project will require the manual collection of data.

 

Why join? The uniqueness of Omdena AI Challenges

A collaborative experience you never had in your working life! For the next eight weeks, you will not only build AI solutions to make a real-world impact but also go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.

And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.

 

Find more information on how an Omdena project works

 

Identifying Mosquito Species Using Computer Vision

Identifying Mosquito Species Using Computer Vision

The team applied instance segmentation to detect body parts of Mosquito species.

 

 

The problem

A vector is a living organism that transmits an infectious agent from an infected animal to a human or another animal. Vectors are frequently arthropods, such as mosquitoes, ticks, flies, fleas, and lice.

  • 700,000 people die each year from vector-borne diseases. 
  • 17% of all infectious disease cases are vector-borne diseases.
  • 80% of the world’s population is at risk for one or more vector-borne diseases.

 

Vectech’s current methods for species classification are based on images gathered with MosID, a custom imaging device designed for consistent, high-quality mosquito imaging, which is fed to a Convolutional Neural Network (CNN) based system. We want Omdena to help us develop a mosquito body part segmentation and identification method, to help us determine what parts of the mosquito are visible and intact in the image. This enables more advanced computer vision methods, serving as highly valuable prior information for the CNN, and may be paired with entomological taxonomic information for species identification. These advanced methods are required for mosquito surveillance products because captured mosquitoes from the wild are often very beaten up, missing scales, wings, legs, etc., which sometimes affects whether that mosquito can be accurately identified to its species.

 

The project outcome 

The team applied various data augmentation techniques and explored different machine learning models for instance segmentation. The solution segments different body parts of the mosquito visible in the image. For example, identifying the specific portions of the image that are the legs, abdomen, wings, and other important body parts of the mosquito. 

 

Identifying Mosquito Species Using Computer Vision

Sample prediction. Source: Omdena

 

 

 

Machine Learning for Risk Prediction of Colon and Lung Cancer

Machine Learning for Risk Prediction of Colon and Lung Cancer

The Omdena team developed and deployed two machine learning enabled applications, one for lung cancer prediction and one for colorectal cancer (CRC) prediction. The user of the apps can enter the input data for a patient and get the likelihood of cancer as an output.

The partner for this project, Radmol AI, is a Dublin-based and Microsoft for Startups supported company on a mission to minimize the risk of delay and errors in medical diagnosis.

 

The problem

According to WHO (world health organization), 80% of countries do not have early detection programs/guidelines for childhood cancer while 67% of countries do not have a childhood cancer defined referral system.

As a result, in high-income countries, more than 80 percent of children diagnosed with cancer are cured, but this figure is only 20 percent in many emerging countries. The disparity is mostly the result of a late or inaccurate diagnosis, among others. Many cancer patients could be saved from premature death and suffering if they had timely access to early detection programs and adequate treatment.

Many cancer patients could be saved from premature death and suffering if they had timely access to early detection programs and adequate treatment. Radmol AI´s solution will facilitate early detection and prompt intervention, hence minimizing needless loss of lives and strain on the economic resources of individuals and countries.

 

The project outcomes

Within 10 weeks, the team covered the following steps:

  1. Collecting datasets for cancer patients with previous symptoms, demographics data, and ailments
  2. Labeling datasets appropriately
  3. Training and testing various machine learning models for lung and colorectal cancer (CRC) prediction
  4. Deploying two applications to visualize the predictions (see the screenshot below) 

 

 

Application Screenshot

 

 

Cancer Drugs Survival Analysis to Support Affordability of Immunotherapy Treatments

Cancer Drugs Survival Analysis to Support Affordability of Immunotherapy Treatments

The team explored various models available in the survival analysis literature and identified the best-performing algorithms. The model predicts the survival probability of a patient and the next treatment period for specific, often less costly, drugs. 

The project partner Mango Sciences is a Boston-based leading emerging market data science company connecting millions of underrepresented patients to precision medicine. The company’s Querent™ platform utilizes industry-leading AI analytics to transform deep clinical data into key insights that drive global health improvements.

 

The problem

The vast majority of patients who unfortunately get diagnosed with cancer, can’t afford the life-extending cancer drugs targeted immunotherapies due to high price tags. As a result, most patients use older chemotherapy medications which have significant side effects and poor outcomes.

Survival Analysis is a branch of statistics developed initially to analyze the expected duration of lifespans of individuals. It is also known as duration analysis, time-to-event analysis, reliability analysis, and event history analysis. In the case of cancer treatments, it can be used to predict the survival probability of a patient or the next treatment period for specific drugs. 

 

The project outcomes

Mango Sciences has developed a financing product for immunotherapies that helps patients’ families pay for their drugs over a period of time, but they only pay the full value of the drug if they get the clinical benefit. Mango Sciences is building predictive algorithms to identify which type of drug works best in which patients based on their specific characteristics. Fundamentally, the right drug should go to the right patient at the right time. Patients and their families should only pay the full value for drugs if they receive a clinical benefit that is financed over a period of time.

The team explored the standard set of models available in the survival analysis literature and identified the best-performing model with the highest concordance index. An example visualization and prediction in Tableau can be found below. 

 

Survival Analysis using AI

Survival Analysis in Tableau;  Source: Omdena

 

Sleep Pose Estimation to Improve Sleep Apnea Condition

Sleep Pose Estimation to Improve Sleep Apnea Condition

Globally, more than 1 billion people suffer from sleep apnea which makes the disease a global challenge. In this high-impact 8-week challenge, 50 AI engineers developed an AI algorithm for sleep pose estimation.

 

The problem

Sleep apnea is a disorder characterized by repeated interruptions in breathing during sleep. The most common cause of these pauses in respiration is the relaxation of throat muscles, provoking a blockage of the airways (Obstructive Sleep Apnea; OSA). Sleep position has been shown to influence the frequency and severity of OSA [1], and treatment strategies exist specializing in patients with positional sleep apnea.

Sleepiz AG has developed a contactless medical device to monitor a person’s sleep throughout the night. The sensing technology, based on continuous wave radar, measures the person’s movements with sub-millimeter resolution. 

 

The project outcomes

The team built several machine learning algorithms to detect Periodic Limb Movements from complex Electromyography (EMG) and I/Q radar-based time series data.