AI enables the mHealth to offer solutions for the following use cases:

• early prediction of medical conditions such as heart attacks from data collected 24/7 on person’s heart rate, sleep cycle, breathing rate, activity level and blood pressure
• measuring and monitoring the patient’s heart rate and glucose levels
• connecting healthcare providers with those accessing healthcare solutions.
• managing healthcare operations and resources, administrative procedures, appointments and reminders, dashboard and better payroll solutions 
• more accurate diagnoses, identify at-risk populations, and better understand how patients will respond to medicines and treatment protocols.

Big data, the technology to aggregate and analyse huge amounts of data, has particular relevance to medical and health data. Healthcare Analytics has the potential in disease prevention by significantly reduce the cost of treatment. Advanced data mining and analysis techniques lead to better health outcomes by enabling healthcare professionals to better analyse a patient’s condition and self-care. AI empowers healthcare professionals to make more informed decisions and to treat patients more effectively.

• Identifying high-value use cases to be addressed by AI can be a challenge.
• Lack of standardization framework of algorithms for health. There is no common, vetted framework for assessment / benchmarking of AI-based solutions based on Open source, open data and open standards.
• The AI algorithms lack explainability and interpretability due to complexity of neural networks which makes it impossible to describe how they work. Hence black box nature of machine learning.
• The AI algorithms should be trustworthy with proven robustness to outliers and to adversarial attacks.
• Lack of comparative data on cost effectiveness, or safety evaluations in clinical settings.
• Insufficient training data, a major limiting factor for the predictive performance of models on new data previously unseen.
• Concerns over the privacy and protection of sensitive health data.
• Disparate ethnic groups or residents of different regions may have unique physiologies and environmental factors that will influence the presentation of disease.
• Reconfiguration of outdated business processes for adoption of AI and trusting that disruption will yield big results and will lead to better patient outcomes.

AI-powered digital health assistants integrated in chatbots and delivered through smartphones and other mobile devices can “transform mHealth apps from a simple static source of information into smart platforms for personalized pre-primary care and assisted self-care provision”.

Early adopters of AI and digital technologies will better and more successfully manage future health emergencies. Besides diagnosis and personalized medicine AI should be leveraged to optimize and streamline administrative health workers tasks and workflows.

ML coupled with wearables are opening a wide array of new possibilities for the mHealth systems. These can be further improved and expanded by incorporating new emerging technologies such as personal sensing. Additional use case that can be of interest to the aging population and increase their appetite for consuming AI powered mHealth services and apps are: detecting fall incidents, seizure episodes, emotional arousal (stress level and mood swings), and nutritional intake.