IET 2019 Healthcare Lecture - Notes and Thoughts
On the 15th October annual, IET 2019 healthcare lecture took place. This short post will give an overview of the topics that were presented and thought of how they might benefit eHealth in general and ongoing standardisation work. The talks include image recognition for medical diagnosis, cfNAs and cfDNA detection using hydrogels, machine learning for medical data and the SPHERE Project.
Advances in Diagnostics
Mostly the interpretations of medical data are being done by a medical expert. In terms of image interpretation by a human expert, it is quite limited due to its subjectivity, the complexity of the image, extensive variations exist across different interpreters and fatigue. After the success of deep learning in other real-world application, it is also providing exciting solutions with good accuracy for medical imaging and is seen as a key method for future applications in the health sector. The aim is to reduce the time taken to diagnosis problems and to prevent signs being missed.
Atrial fibrillation (AF) is a common cardiac arrhythmia that affects 1% of the population and is associated with high levels of morbidity and all-cause mortality. Catheter ablation (CA) has become one of the first-line treatments for AF, but the success rates of CA and other clinical treatments remain suboptimal. The need to improve clinical outcomes warrants the optimisation of CA therapy. They developed a novel deep learning method to identify specific ablation patterns that terminate AF efficiently. To achieve this, they simulated typical AF ablation scenarios using computational models of 2D atrial tissue, and use the simulation outcomes as inputs for a deep neural network. The network is trained, validated and then applied to classify the scenarios and predict the optimal CA pattern in each scenario. For the validation dataset, the overall accuracy in identifying the best CA strategy is recorded at 79%. The study provides proof of concept that deep neural networks can learn from computational models of AF and help optimise CA therapy.
Circulating cell-free nucleic acids (cfNAs) in liquid biopsies have been reported as predictive, diagnostic and prognostic biomarkers for a broad range of conditions and technologies that can facilitate their detection in a point-of-care setting will impact the very broad population affected by these pathologies. However, they are particularly challenging to detect accurately due to their low concentration and high sequence homology. In our lab, they are developing and validating new sensing platforms for the automated and quantitative detection of cfNAs from whole blood. These technologies have great potential for (i) early diagnosis and improved prognosis of prostate cancer; (ii) improved diagnosis of Hepatitis B in developing countries; (iii) non-invasive early prediction of preterm birth. All these applications are currently being pursued through well-established collaborations with clinicians.
Minimally invasive technologies that can sample and detect cell-free nucleic acid biomarkers from liquid biopsies have recently emerged as clinically useful for early diagnosis of a broad range of pathologies, including cancer. Although blood has so far been the most commonly interrogated bodily fluid, skin interstitial fluid has been mostly overlooked despite containing the same broad variety of molecular biomarkers originating from cells and surrounding blood capillaries. Emerging technologies to sample this fluid in a pain-free and minimally-invasive manner often take the form of micro-needle patches. Herein, they developed micro-needles that are coated with an alginate–peptide nucleic acid hybrid material for sequence-specific sampling, isolation, and detection of nucleic acid biomarkers from skin interstitial fluid. Characterised by fast sampling kinetics and large sampling capacity (∼6.5 μL in 2 min), this platform technology also enables the detection of specific nucleic acid biomarkers either on the patch itself or in solution after light-triggered release from the hydrogel. Considering the emergence of cell-free nucleic acids in bodily fluids as clinically informative biomarkers, platform technologies that can detect them in an automated and minimally invasive fashion have great potential for personalised diagnosis and longitudinal monitoring of patient-specific disease progression.
Research involving the development of machine learning methodologies for understanding complex patient data, via Bayesian inference, deep learning and applications involving the developing world. She focuses on creating clinical artificial intelligent (AI) systems for tackling multimorbidities in resource-constrained settings, with the emphasis on phenotyping patients for risk stratification, polypharmacy and treatment strategies.
A research project on the management of patient well-being demonstrated it can be performed by monitoring continuous time-series vital-sign data via low-cost wearable devices. Automated algorithms may then be used with the resulting data to provide early warning of deterioration of the health of an individual.
SPHERE Project (Professor Ian Craddock)
The 'Sensor Platform for Healthcare in a Residential Environment' (SPHERE Project). The UK, like many other nations, is faced with an explosion of long term health conditions - these are conditions that require continuous management, often for many years, outside of a hospital setting. Obesity, depression, diabetes, stroke, falls, respiratory conditions, cardiovascular and musculoskeletal disease are some of the biggest health issues and fastest-rising categories of healthcare costs. The associated expenditure is widely regarded as unsustainable and the impact on the quality of life is felt by millions of people each day. SPHERE is a community of nearly 100 researchers, designed to tell us to what extent new technology can be the answer to some of these problems.
SPHERE has developed a number of different IoT sensors that will combine to build a picture of how we live in our homes. This information can then be used to spot issues that might indicate a medical or well-being problem.
The technology could help in the following ways:
- Characterise the sedentary behaviour that links' many health conditions.
- Detect correlations between factors such as diet and sleep.
- Measure changes in movement, posture and patterns of movement over months.
- Analyse eating behaviour - including whether people are taking prescribed medication.
- Detect periods of depression or anxiety and intervene using a computer-based therapy.
- Predict falls and detect strokes so that help may be summoned.
- They want to make sure the technology is: Acceptable in peoples' homes.
- Solves real healthcare problems in a cost-effective way
- The project generates knowledge that will change clinical practice (this will be achieved by focusing on real-world technologies that can be shown working in a large number of local homes during the life of the project).
SPHERE is working with clinicians, engineers, designers and social care professionals as well as members of the public to develop these sensor technologies.
These advances in data and pattern recognition of medical data for diagnosis important to reduce time in detecting disease and health problems thus minimising time to treatment to start. When eHealth standardisation while these individual methods themselves will not be included some the experience gained would be useful in laying good universals practices. For example, the SPHERE project spent a fair bit of time creating data protection and privacy policies which could be applied to general IoT eHealth devices if/when manufactories begin producing them. Allowing standards to be ahead instead of playing catch-up when comes to ensuring companies roll out new devices and services. Finally, I hope some this information from the IET Healthcare lecture is interesting and leads to further reading about these topics.