Collaborating Authors


Council Post: What Machine Learning Can Teach Us About Glucose Metabolism And Predicting Future Disease


Amir Hayeri, CEO of Bio Conscious Tech, works with chronically ill patients to help them predict and ideally avoid disease complications. When you hear the word "glucose," what do you think of? For most people, the next word they think of is "diabetes." More than 10% of the U.S. population is diagnosed with diabetes; so is more than 8% of the Canadian population. An even larger population is pre-diabetic.

Unique AI method for generating proteins to speed up drug development


"What we are now able to demonstrate offers fantastic potential for a number of future applications, such as faster and more cost-efficient development of protein-based drugs," says Aleksej Zelezniak, Associate Professor at the Department of Biology and Biological Engineering at Chalmers. Proteins are large, complex molecules that play a crucial role in all living cells, building, modifying, and breaking down other molecules naturally inside our cells. They are also widely used in industrial processes and products, and in our daily lives. Protein-based drugs are very common--the diabetes drug insulin is one of the most prescribed. Some of the most expensive and effective cancer medicines are also protein-based, as well as the antibody formulas currently being used to treat COVID-19.

Analysing Posterior Predictive Distributions with PyMC3


Note that the mean of 31.949 was slightly higher than the prior estimation, while the standard deviation was significantly higher at 7.823. Having taken the data into account, it would make sense in hindsight that the standard deviation is higher than originally expected. After all, numerous patients in the dataset are not diabetic. Moreover, while one might expect a positive correlation between BMI and diabetes, this is based on a prior belief -- we do not have hard evidence that this is the case without looking at the data.

An ecosystem to overhaul China's health care

MIT Technology Review

Like many countries, China has a health care problem. Changing demographics and lifestyles mean demand for health care is outstripping growth in medical resources and its cost is rising faster than the insurance premium. With 250 million people over the age of 60, the world's most populous country is ageing. Diseases associated with more affluent societies, such as cardiovascular conditions and diabetes, are on the rise. China has 400 million chronic disease patients whose treatment costs 70% of total health care resources.

Artificial intelligence helps spot diabetes risk - Sanford Health News


Artificial intelligence won't tell you not to eat that second cookie. But it could help your doctor know if there's a good chance you may develop diabetes in the next year, which could make dessert less appealing. Robert Menzie, lead data scientist on Sanford Health's advanced analytics group, came up with an AI algorithm that can show the probability someone has or might develop type 2 diabetes in the near future. It looks at the past five years of a patient's medical history and compares them to similar patients who were diagnosed with type 2 diabetes. The AI provides a risk score that the person's personal care physician can then use to dig deeper.

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges Machine Learning

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees; (2) Optimization of scoring systems; (3) Placing constraints into generalized additive models to encourage sparsity and better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints; (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning. This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.

Health: Overweight people in their 20s and 30s TWICE as likely to have memory issues later in life

Daily Mail - Science & tech

You may be twice as likely to develop late-life memory and cognitive issues if you are overweight or have high blood pressure or high glucose levels in your 20s/30s. They found that high BMI and blood pressure in early adulthood can double the rate of cognitive decline -- while high blood glucose levels increased in five-fold. The researchers cautioned, however, that they only established an association between these health issues and late-life cognitive problems, not a causal link. 'These results are striking and suggest that early adulthood may be a critical time for the relationship between these health issues and late-life cognitive skills,' said paper author and neurologist Kristine Yaffe of the University of California, San Francisco. 'It's possible that treating or modifying these health issues in early adulthood could prevent or reduce problems with thinking skills in later life.'

Evaluation of a Bi-Directional Methodology for Automated Assessment of Compliance to Continuous Application of Clinical Guidelines, in the Type 2 Diabetes-Management Domain Artificial Intelligence

Evidence-based recommendations are often published in the form of clinical guidelines and protocols, as documents intended to be used by clinicians to provide the state of the art care. However, as demonstrated repeatedly in multiple clinical domains, clinicians often do not sufficiently adhere to the guidelines in a manner sensitive to the context of each patient. Such gaps are important to detect; fast, large-scale detection might lead to specific adjustments, usually of the clinicians' management patterns, but possibly of the guidelines themselves. In this study, we evaluated the DiscovErr system, in which we had implemented a new methodology for assessment of compliance to continuous implementation of clinical guidelines. This new methodology is based on a bi-directional search from the objective of the guideline to the longitudinal multivariate patient data, and vice versa. The evaluation of DiscovErr was performed in the type 2 Diabetes management domain, by comparing its performance to a panel of three clinicians, two experts in diabetes-patient management and a senior family practitioner highly experienced in diabetes treatment. The system and the three experts commented on the management of 10 patients who were randomly selected before the evaluation from a database containing longitudinal records of 2,000 type 2 diabetes patients. On average, each patient record spanned 5.23 years; the overall data of the selected patients included 1,584 time-oriented medical transactions (laboratory tests or medication administrations). We assessed the correctness (i.e.

Using a Personal Health Library-Enabled mHealth Recommender System for Self-Management of Diabetes Among Underserved Populations: Use Case for Knowledge Graphs and Linked Data Artificial Intelligence

Personal health libraries (PHLs) provide a single point of secure access to patients digital health data and enable the integration of knowledge stored in their digital health profiles with other sources of global knowledge. PHLs can help empower caregivers and health care providers to make informed decisions about patients health by understanding medical events in the context of their lives. This paper reports the implementation of a mobile health digital intervention that incorporates both digital health data stored in patients PHLs and other sources of contextual knowledge to deliver tailored recommendations for improving self-care behaviors in diabetic adults. We conducted a thematic assessment of patient functional and nonfunctional requirements that are missing from current EHRs based on evidence from the literature. We used the results to identify the technologies needed to address those requirements. We describe the technological infrastructures used to construct, manage, and integrate the types of knowledge stored in the PHL. We leverage the Social Linked Data (Solid) platform to design a fully decentralized and privacy-aware platform that supports interoperability and care integration. We provided an initial prototype design of a PHL and drafted a use case scenario that involves four actors to demonstrate how the proposed prototype can be used to address user requirements, including the construction and management of the PHL and its utilization for developing a mobile app that queries the knowledge stored and integrated into the PHL in a private and fully decentralized manner to provide better recommendations. The proposed PHL helps patients and their caregivers take a central role in making decisions regarding their health and equips their health care providers with informatics tools that support the collection and interpretation of the collected knowledge.

Feature selection for medical diagnosis: Evaluation for using a hybrid Stacked-Genetic approach in the diagnosis of heart disease Artificial Intelligence

Background and purpose: Heart disease has been one of the most important causes of death in the last 10 years, so the use of classification methods to diagnose and predict heart disease is very important. If this disease is predicted before menstruation, it is possible to prevent high mortality of the disease and provide more accurate and efficient treatment methods. Materials and Methods: Due to the selection of input features, the use of basic algorithms can be very time-consuming. Reducing dimensions or choosing a good subset of features, without risking accuracy, has great importance for basic algorithms for successful use in the region. In this paper, we propose an ensemble-genetic learning method using wrapper feature reduction to select features in disease classification. Findings: The development of a medical diagnosis system based on ensemble learning to predict heart disease provides a more accurate diagnosis than the traditional method and reduces the cost of treatment. Conclusion: The results showed that Thallium Scan and vascular occlusion were the most important features in the diagnosis of heart disease and can distinguish between sick and healthy people with 97.57% accuracy.