Unsupervised machine learning to investigate trajectory patterns of COVID-19 symptoms and physical activity measured via the MyHeart Counts App and smart devices.

Previous studies have associated COVID-19 symptoms severity with levels of physical activity. We therefore investigated longitudinal trajectories of COVID-19 symptoms in a cohort of healthcare workers (HCWs) with non-hospitalised COVID-19 and their real-world physical activity. 121 HCWs with a history of COVID-19 infection who had symptoms monitored through at least two research clinic visits, and via smartphone were examined. HCWs with a compatible smartphone were provided with an Apple Watch Series 4 and were asked to install the MyHeart Counts Study App to collect COVID-19 symptom data and multiple physical activity parameters. Unsupervised classification analysis of symptoms identified two trajectory patterns of long and short symptom duration. The prevalence for longitudinal persistence of any COVID-19 symptom was 36% with fatigue and loss of smell being the two most prevalent individual symptom trajectories (24.8% and 21.5%, respectively). 8 physical activity features obtained via the MyHeart Counts App identified two groups of trajectories for high and low activity. Of these 8 parameters only 'distance moved walking or running' was associated with COVID-19 symptom trajectories. We report a high prevalence of long-term symptoms of COVID-19 in a non-hospitalised cohort of HCWs, a method to identify physical activity trends, and investigate their association. These data highlight the importance of tracking symptoms from onset to recovery even in non-hospitalised COVID-19 individuals. The increasing ease in collecting real-world physical activity data non-invasively from wearable devices provides opportunity to investigate the association of physical activity to symptoms of COVID-19 and other cardio-respiratory diseases.

Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection.

Although a variety of brain lesions may contribute to the pathological assessment of dementia, the relationship of these lesions to dementia, how they interact and how to quantify them remains uncertain. Systematically assessing neuropathological measures by their degree of association with dementia may lead to better diagnostic systems and treatment targets. This study aims to apply machine learning approaches to feature selection in order to identify critical features of Alzheimer-related pathologies associated with dementia. We applied machine learning techniques for feature ranking and classification to objectively compare neuropathological features and their relationship to dementia status during life using a cohort (n=186) from the Cognitive Function and Ageing Study (CFAS). We first tested Alzheimer's Disease and tau markers and then other neuropathologies associated with dementia. Seven feature ranking methods using different information criteria consistently ranked 22 out of the 34 neuropathology features for importance to dementia classification. Although highly correlated, Braak neurofibrillary tangle stage, beta-amyloid and cerebral amyloid angiopathy features were ranked the highest. The best-performing dementia classifier using the top eight neuropathological features achieved 79% sensitivity, 69% specificity and 75% precision. However, when assessing all seven classifiers and the 22 ranked features, a substantial proportion (40.4%) of dementia cases was consistently misclassified. These results highlight the benefits of using machine learning to identify critical indices of plaque, tangle and cerebral amyloid angiopathy burdens that may be useful for classifying dementia.

Biological heterogeneity in idiopathic pulmonary arterial hypertension identified through unsupervised transcriptomic profiling of whole blood.

Idiopathic pulmonary arterial hypertension (IPAH) is a rare but fatal disease diagnosed by right heart catheterisation and the exclusion of other forms of pulmonary arterial hypertension, producing a heterogeneous population with varied treatment response. Here we show unsupervised machine learning identification of three major patient subgroups that account for 92% of the cohort, each with unique whole blood transcriptomic and clinical feature signatures. These subgroups are associated with poor, moderate, and good prognosis. The poor prognosis subgroup is associated with upregulation of the ALAS2 and downregulation of several immunoglobulin genes, while the good prognosis subgroup is defined by upregulation of the bone morphogenetic protein signalling regulator NOG, and the C/C variant of HLA-DPA1/DPB1 (independently associated with survival). These findings independently validated provide evidence for the existence of 3 major subgroups (endophenotypes) within the IPAH classification, could improve risk stratification and provide molecular insights into the pathogenesis of IPAH.

Robust EEG Based Biomarkers to Detect Alzheimer's Disease.

Biomarkers to detect Alzheimer's disease (AD) would enable patients to gain access to appropriate services and may facilitate the development of new therapies. Given the large numbers of people affected by AD, there is a need for a low-cost, easy to use method to detect AD patients. Potentially, the electroencephalogram (EEG) can play a valuable role in this, but at present no single EEG biomarker is robust enough for use in practice. This study aims to provide a methodological framework for the development of robust EEG biomarkers to detect AD with a clinically acceptable performance by exploiting the combined strengths of key biomarkers. A large number of existing and novel EEG biomarkers associated with slowing of EEG, reduction in EEG complexity and decrease in EEG connectivity were investigated. Support vector machine and linear discriminate analysis methods were used to find the best combination of the EEG biomarkers to detect AD with significant performance. A total of 325,567 EEG biomarkers were investigated, and a panel of six biomarkers was identified and used to create a diagnostic model with high performance (≥85% for sensitivity and 100% for specificity).

Early Detection of Alzheimer's Disease with Blood Plasma Proteins Using Support Vector Machines.

The successful development of amyloid-based biomarkers and tests for Alzheimer's disease (AD) represents an important milestone in AD diagnosis. However, two major limitations remain. Amyloid-based diagnostic biomarkers and tests provide limited information about the disease process and they are unable to identify individuals with the disease before significant amyloid-beta accumulation in the brain develops. The objective in this study is to develop a method to identify potential blood-based non-amyloid biomarkers for early AD detection. The use of blood is attractive because it is accessible and relatively inexpensive. Our method is mainly based on machine learning (ML) techniques (support vector machines in particular) because of their ability to create multivariable models by learning patterns from complex data. Using novel feature selection and evaluation modalities, we identified 5 novel panels of non-amyloid proteins with the potential to serve as biomarkers of early AD. In particular, we found that the combination of A2M, ApoE, BNP, Eot3, RAGE and SGOT may be a key biomarker profile of early disease. Disease detection models based on the identified panels achieved sensitivity (SN) > 80%, specificity (SP) > 70%, and area under receiver operating curve (AUC) of at least 0.80 at prodromal stage (with higher performance at later stages) of the disease. Existing ML models performed poorly in comparison at this stage of the disease, suggesting that the underlying protein panels may not be suitable for early disease detection. Our results demonstrate the feasibility of early detection of AD using non-amyloid based biomarkers.

Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study.

BACKGROUND: Up to half of patients with dementia may not receive a formal diagnosis, limiting access to appropriate services. It is hypothesised that it may be possible to identify undiagnosed dementia from a profile of symptoms recorded in routine clinical practice. AIM: The aim of this study is to develop a machine learning-based model that could be used in general practice to detect dementia from routinely collected NHS data. The model would be a useful tool for identifying people who may be living with dementia but have not been formally diagnosed. DESIGN & SETTING: The study involved a case-control design and analysis of primary care data routinely collected over a 2-year period. Dementia diagnosed during the study period was compared to no diagnosis of dementia during the same period using pseudonymised routinely collected primary care clinical data. METHOD: Routinely collected Read-encoded data were obtained from 18 consenting GP surgeries across Devon, for 26 483 patients aged >65 years. The authors determined Read codes assigned to patients that may contribute to dementia risk. These codes were used as features to train a machine-learning classification model to identify patients that may have underlying dementia. RESULTS: The model obtained sensitivity and specificity values of 84.47% and 86.67%, respectively. CONCLUSION: The results show that routinely collected primary care data may be used to identify undiagnosed dementia. The methodology is promising and, if successfully developed and deployed, may help to increase dementia diagnosis in primary care.

Higuchi fractal dimension of the electroencephalogram as a biomarker for early detection of Alzheimer's disease.

It is widely accepted that early diagnosis of Alzheimer's disease (AD) makes it possible for patients to gain access to appropriate health care services and would facilitate the development of new therapies. AD starts many years before its clinical manifestations and a biomarker that provides a measure of changes in the brain in this period would be useful for early diagnosis of AD. Given the rapid increase in the number of older people suffering from AD, there is a need for an accurate, low-cost and easy to use biomarkers that could be used to detect AD in its early stages. Potentially, the electroencephalogram (EEG) can play a vital role in this but at present, no reliable EEG biomarker exists for early diagnosis of AD. The gradual slowing of brain activity caused by AD starts from the back of the brain and spreads out towards other parts. Consequently, determining the brain regions that are first affected by AD may be useful in its early diagnosis. Higuchi fractal dimension (HFD) has characteristics which make it suited to capturing region-specific neural changes due to AD. The aim of this study is to investigate the potential of HFD of the EEG as a biomarker which is associated with the brain region first affected by AD. Mean HFD value was calculated for all channels of EEG signals recorded from 52 subjects (20-AD and 32-normal). Then, p-values were calculated between the two groups (AD and normal) to detect EEG channels that have a significant association with AD. k-nearest neighbor (KNN) algorithm was used to compute the distance between AD patients and normal subjects in the classification. Our results show that AD patients have significantly lower HFD values in the parietal areas. HFD values for channels in these areas were used to discriminate between AD and normal subjects with a sensitivity and specificity values of 100% and 80%, respectively.

Changes in the EEG amplitude as a biomarker for early detection of Alzheimer's disease.

The rapid increase in the number of older people with Alzheimer's disease (AD) and other forms of dementia represents one of the major challenges to the health and social care systems. Early detection of AD makes it possible for patients to access appropriate services and to benefit from new treatments and therapies, as and when they become available. The onset of AD starts many years before the clinical symptoms become clear. A biomarker that can measure the brain changes in this period would be useful for early diagnosis of AD. Potentially, the electroencephalogram (EEG) can play a valuable role in early detection of AD. Damage in the brain due to AD leads to changes in the information processing activity of the brain and the EEG which can be quantified as a biomarker. The objective of the study reported in this paper is to develop robust EEG-based biomarkers for detecting AD in its early stages. We present a new approach to quantify the slowing of the EEG, one of the most consistent features at different stages of dementia, based on changes in the EEG amplitudes (ΔEEGA). The new approach has sensitivity and specificity values of 100% and 88.88%, respectively, and outperformed the Lempel-Ziv Complexity (LZC) approach in discriminating between AD and normal subjects.

Tsallis entropy as a biomarker for detection of Alzheimer's disease.

Alzheimer's disease (AD) and other forms of dementia are one of the major public health and social challenges of our time because of the large number of people affected. Early diagnosis is important for patients and their families to get maximum benefits from access to health and social care services and to plan for the future. EEG provides useful insight into brain functions and can play a useful role as a first line of decision-support tool for early detection and diagnosis of dementia. It is non-invasive, low-cost and has a high temporal resolution. The functions of brain cells are affected by damage caused by dementia and this in turn causes changes in the features of the EEG. Information theoretic methods have emerged as a potentially useful way to quantify changes in the EEG as biomarkers of dementia. Tsallis entropy has been shown to be one of the most promising information theoretic methods for quantifying changes in the EEG. In this paper, we develop the approach further. This has yielded an enhanced performance compared to existing approaches.