Become a leader in proactive and personalized health management for all.

Let us support you with ethical and trustworthy AI by design.
Omina Technologies > Healthcare and Life Sciences
proactive health

Delivering proactive and personalized health management for all is challenging

Patients now expect:

  • Personal advice on how to prevent health risks and early disease detection: personalized, continuous and dynamic health monitoring and health risk prevention.
  • A health experience that fits their lifestyle; flexibility in time, location and service delivery: telehealth, hospital at home, personalized health experiences
  • To take an active role in their own health decision making and health management: shared decision making, self-health monitoring via wearables, self-diagnosis, self-care
  • To have equal opportunity to attain his or her full health potential, regardless of sex, ethnicity or other protected attributes: health equity.

Consequently, healthcare and life sciences companies should enable proactive, personalized, inclusive and seamless health management in which patients take an active role.

Proactive health management requires a paradigm shift from ‘diagnose & treat’ to ‘monitor and prevent’. This requires patients to take more responsibility for their health and providers to analyze continuous individual-level health status data.

CASE STUDY

But personalizing health management to improve patient experience conflicts with:

  • the increased need to be more cost-efficient due to increased competition
  • the increased expectations for data privacy and data protection

Shared health decision-making clashes with the current practice of short consultation durations and the complexity of explaining alternative diagnoses, treatments and rehabilitation options.

Health equity is also challenging.  Current clinical trials typically primarily recruit average patients (a Caucasian 35-year old man). As a result,  most drugs and vaccines do not work equally well for different patient groups.

Regular AI is not up to the challenge

Enabling proactive and personalized health management for all with AI is complex. Proactive and personalized health services require high levels of personalization and continuous risk monitoring, creating heightened risks to data privacy and data security. Personalization of health management invariably requires analysis of a person’s health data, which may become personal identifiable even after removing sensitive personal data (e.g., a patient with a rare disease living in a small village is easily identifiable). The increased availability of genetic data makes the need for strict data privacy protection even more critical.

To provide more seamless and faster patient experiences at reduced cost, many hospitals have started to automate tasks. Given the high-risk nature of health decisions, the use of AI for automating health decision-making requires allowing for human agency and oversight and explanations of automated decisions that are understandable to auditors, doctors, patients (GDPR). 

doubtful doctor
patient safety

To provide safe patient experiences, AI models must be robust and safe. AI models must be robust enough that prediction accuracy is maintained when there are changes in the data. In February 2022, Statnews published the findings of a research study conducted with the Massachusetts Institute of Technology that found small shifts in data fed into well-known health care algorithms, including the Epic Sepsis Model, can cause their accuracy to degrade over time.

To promote patient safety it is vital that AI models include health domain knowledge and are interpretable. Most AI models identify correlations/associations rather than causations. Given an explainable AI solution, a domain expert should validate which correlations are actual causations. For example, a study by Cooper et al. painfully showed how a black-box neural network indicated that having asthma lowers a patient’s risk of dying from pneumonia. Why the incongruous results? The model learned that asthma patients when they exhibit symptoms of pneumonia are more likely to be admitted to the Emergency Department, thus lowering their mortality risk. Involving domain experts during AI model development and adding interpretability as a selection criterion could have prevented this correlation from being seen by the AI model as a causation.

To enable the patient to take up an active role in health decision-making and health management requires transparent, interpretable and explainable AI solutions. Black-box models are not interpretable. Also, post-hoc explanations are often not authentic, so they cannot be used to enable the patient to make a shared health decision.

To promote health equity is also challenging. Health disparities can be exacerbated through biases in the data used to train an AI algorithm, and in the algorithm’s intent. For AI to be used effectively to promote health equity, existing biases in healthcare services and systems based on race, ethnicity, age, and gender, that are encoded in data used to train algorithms, must be addressed (WHO, Guide on Ethics and Governance of Artificial Intelligence for Health, June, 2021).  Obermeyer et al. (2019) found that a widely used commercial prediction algorithm resulted in significant racial bias in predicting outcomes. A particular challenge in the application of AI to cardiovascular medicine is in the intrinsic and extrinsic biases that affect quality control, and thus clinical outcomes. The bulk of current evidence-based medicine in cardiology might not apply to women and minority groups, because they are historically under-represented (Tat et al., The Lancet, 2020. A systematic review study of COVID-19 prediction models uncovered widespread and serious shortcomings, particularly with respect to potential biases (Wijnants et al., BMJ, 2021). With the push to quickly adopt AI to assist in the fight against COVID-19 frenzy, the risk of producing biased prediction models due to unrepresentative datasets and other limitations in model development is higher than ever (Roosli et al., JAMIA, 2021).

Regular AI has a lack of respect for data privacy, human agency, explainability, transparency, fairness,  which result in lack of trust and no adoption of the AI solution supporting health management decisions.

health equity
WHO AI for Health

Trustworthy AI to enable proactive and personalized health management for all

Trustworthy AI supports hyper-personalized health management decisions that are fair, transparent and explainable by design. Trustworthy AI is ethical (fair, non-discriminating), lawful and robust (see Ethics Guidelines for Trustworthy AI, 2019). It enables fair and consistent decisions that are explainable and justifiable to all stakeholders.

The WHO also published a report on trustworthy AI for Health (2021): ‘’Guide on Ethics and Governance of Artificial Intelligence for Health’’.

Trustworthy AI tools contribute to the United Nations Sustainable Development Goal 3 (WHO, 2021): Achieve universal health coverage, including financial risk protection , access to quality essential health-care services and access to safe, effective, quality and affordable essential medicines and vaccines for all.

Healthcare use cases

Omina Technologies trustworthy AI by design helps you to support healthcare decision-making in an ethical and explainable way.

Omina Technologies focusses on healthcare use cases with a high need for AI-enabled fair, non-discriminatory and explainable decision making:

AI to support health decision-making in patient disease prevention, prognosis, diagnosis, treatment, that is fair, non-discriminatory and explainable by design: patient disease screen out from acute care, segment-based/personalized patient prognosis, adverse health event detection, patient diagnosis of rare diseases, personalized disease diagnosis, geriatric patient diagnosis, personalized treatment recommendations, patient risk profiling for hospital acquired infections, personalized continuous patient well-being therapy.

AI to support resource allocation and patient flow that is fair, non-discriminatory and explainable by design: patient admission risk prediction, diagnostic test prioritization, patient treatment postponement, rehabilitation success prediction and access to specialized rehabilitation centers.

healthcare AI use cases

Life sciences use cases

Omina Technologies trustworthy AI by design helps you to support life sciences decision-making in an ethical and explainable way.

Omina Technologies focusses on life science use cases that require AI-enabled fair, non-discriminatory and explainable decision-making. 

AI to support health management for underserved patient groups via patient segmentation: Currently most drugs are developed for the average patient; a middle-aged white male. AI can support the development of drugs for specific patient groups, including vulnerable and disadvantaged groups, by supporting patient selection for clinical trials and assessing drug efficacy for specified patient segments/strata. 

AI to identify disease biomarkers: The AI-identified disease biomarkers are cross-domain (omics) and require various explainable AI (XAI)  techniques to ensure that both the healthcare professional and patient can understand the prediction and how the AI model came to that prediction.

AI to identify drug targets: A clear explanation of why an AI solution expects specific targets to be suitable targets is critical to enable the R&D department to use the deployed solution as a pre-selector of potential targets for further development.

AI to improve patient disease experiences: AI provides an explanation for why a patient has a negative or positive patient disease experience, sheds light on drug side effects, and recommends the best action to improve a specific patient’s disease experience.

life sciences AI use cases

Why Omina Technologies?

Omina Technologies has been an expert in ethical and trustworthy AI since 2016. We enable you to become a leader in proactive and personalized health management for all by supporting you to build trustworthy AI solutions by design: