AI Techniques for Efficient Disease Biomarker Discovery

Non-invasive monitoring of blood analyte levels using electrocardiograms (ECGs) and machine learning. The technique involves training a machine learning model using ECGs and corresponding analyte levels from multiple individuals. The model can then predict analyte levels from new ECGs without needing blood samples. The training data is processed to filter out potentially inaccurate analyte measurements that could negatively impact model accuracy. This involves analyzing the ECGs to identify features that correlate with analyte levels, as some subtle changes in the ECG may indicate analyte fluctuations that are not obvious to the human eye. The model is trained using these identified ECG features rather than just the analyte measurements. By leveraging the relationship between ECGs and analyte levels, the model can accurately predict analyte concentrations without invasive blood draws.

Source

Health monitoring using multimodal sensors and external data to accurately diagnose diseases and track symptoms over time. The method involves continuously monitoring health using sensors like microphones, peak flow meters, pulse oximeters, etc. It also collects non-sensory data like medication, diet, location, etc. The sensory and non-sensory data is fed into neural networks to detect symptoms and diseases. The networks adapt periodically based on user data to improve accuracy and reduce false alarms. The method also generates personalized audio summaries for doctors to help diagnose.

Source

Machine learning method for detecting periodontal disease using oral microbiome analysis. The method involves training a machine learning model to predict periodontal disease risk based on specific bacteria detected in oral samples. The model is trained on oral microbiome data from patients with and without periodontal disease. The trained model can then be used to evaluate periodontal disease risk in new samples by detecting the selected bacterial species and calculating their proportions. Higher proportions of certain bacteria indicate higher disease risk.

Source

Using graph neural networks to predict disease progression, survival, and therapy response for multi-focal diseases like cancer or COPD based on graph representations of the patient's disease lesions. The method involves applying a trained graph machine learning model to a graph representation of the patient's lesions to generate clinical information for predicting disease outcomes. The graph representation can include both local and global features of the lesions. The trained model considers the full distribution of lesions across organs rather than just isolated lesions. This holistic approach improves prediction accuracy compared to using isolated lesion features.

Source

A system for detecting dielectric changes in matter using microwave scattering, machine learning, and big data to detect diseases like stroke. The system involves collecting microwave scattering data from an array, analyzing it with a learning device, comparing results to imaging, and iteratively improving the learning. The learning uses correlations between microwave and imaging to predict disease states. It leverages big data to learn disease signatures from scattering. This provides a cheap, portable, scalable alternative to traditional imaging for rapid, intelligent diagnostics using microwaves.

Source

Automatically detecting and quantifying pathology in medical imaging scans using AI techniques like unsupervised learning to identify and classify irregularities without requiring a human expert. The method involves training a computer system to analyze scanned images and quantify the extent of pathology patterns. It can be used to automatically identify pathologies like usual interstitial pneumonia (UIP) in lung CT scans for diagnosing conditions like idiopathic pulmonary fibrosis. The AI system learns to recognize pathology patterns without human supervision.

Source

Explainable AI models using CNN and attention for early, non-invasive diagnostics of Alzheimer's Disease by analyzing patient's speech patterns. The models can detect Alzheimer's using two types of features: parts-of-speech (PoS) and language embeddings. Attention layers capture the relative importance of features within each class and between classes. This provides explainability by showing which features are most important for the model's decision-making.

Source

Using machine learning algorithms trained on historical insurance claims data and biomarker levels to identify and monitor diseases like multiple sclerosis before symptoms become apparent. The algorithms can predict disease risk and progression based on patterns in insurance claims data like diagnosis codes, treatments, and demographics. Blood biomarkers like long non-coding RNA levels can also be used. This allows early detection, prognosis, and personalized treatment recommendations for diseases like MS.

Source

Method for diagnosing and staging liver diseases using DNA analysis. The method involves analyzing a DNA sample, like circulating cell-free DNA (cfDNA) or blood cell DNA, to determine methylation patterns at specific CpG sites. Methylation levels are calculated from these patterns and used to classify the liver disease. This allows non-invasive diagnosis and staging of conditions like fatty liver, NASH, cirrhosis, and liver cancer without biopsy. The methylation markers are selected based on tissue specificity and can distinguish between liver and non-liver tissue.

Source

Extracting biomarkers from subject response data like video and audio to determine disease severity. The method involves presenting stimuli to a subject and recording their response. Biomarkers are derived from the recorded data by extracting descriptors like facial expressions, speech patterns, and vocal characteristics. These descriptors are used to calculate biomarkers that indicate disease severity.

Source

A method to predict diseases using biosignals like EEG, ECG, etc. that involves learning the biosignals using vectorization and deep learning techniques. The method involves expressing the biosignals as multiple symbols based on a condition, converting each symbol to an N-dimensional vector, summing the vectors to get a learnable vector, and using it to predict diseases in new biosignals by comparing against extracted vectors from those biosignals. This allows learning and analyzing biosignals in real time to predict diseases based on what's learned.

Source

Determining biomarkers and health conditions of patients related to cognitive health using multimodal health data and machine learning. The method involves receiving diverse health data like speech, gait, eye movements, etc. from multiple modalities. A neural network extracts latent variables from the health data. These latent variables are provided to another neural network to determine biomarkers and health conditions. The system aims to provide reliable, noninvasive, accurate, and cost-effective determination of cognitive impairment, optimized care, and treatment recommendations.

Source

Improving lung cancer diagnosis by using AI to accurately assess lung nodules based on both lung scans and blood tests. The AI classifier identifies image markers like vascular convergence and air bronchograms in lung scans, as well as blood markers like genomic, epigenomic, and proteomic biomarkers. It also considers factors like discrepancies between scans over time and comorbidities. The AI combines this multimodal data to provide a more accurate lung nodule risk score than using just lung scans.

Source

A method to accurately predict Alzheimer's Disease (AD) from Mild Cognitive Impairment (MCI) patients by using a combination of brain MRI scans and cognitive assessment scores. The method involves training a machine learning model using MRI images containing hippocampus structure and cognitive function scores. The model learns to predict AD based on both structural and functional biomarkers. The hippocampus is segmented into sections and features like volume, surface area, and curvature are extracted. These features are combined with cognitive scores for AD prediction.

Source

Using CT scans to predict molecular biomarkers like PD-L1 and EGFR mutations in lung cancer without invasive biopsies. The method involves processing CT images to estimate molecular data related to biomarkers in the genome, transcriptome, proteome, and metabolome. Nodule patches are identified from the CTs, and nodule-based data is calculated for the biomarkers. This nodule-based data is used as input to trained functions along with CT features to predict molecular data without needing CT images of the entire lung.

Source

A device that uses artificial intelligence to predict if a person who doesn't yet have Alzheimer's disease will develop the condition. The device takes inputs like age, gender, genotype, and brain scan results to train an AI model that can predict beta-amyloid conversion status. This allows identifying individuals who are at higher risk of developing Alzheimer's at an earlier stage compared to waiting for amyloid deposits. The goal is primary prevention by targeting interventions to those at higher risk of progression.

Source

Detecting health issues like heart conditions and brain disorders by analyzing electromagnetic fields (EMF) from the body. A machine learning algorithm trained on EMF data from known conditions is used to identify abnormalities in EMFs from unknown individuals. The algorithm extracts features from the EMFs, associates them with other data, generates a hypothesis function, and determines the presence of abnormalities. This allows diagnosing conditions like heart ischemia or brain disorders without direct imaging or testing.

Source

Automated method for diagnosing and staging non-alcoholic steatohepatitis (NASH) and liver fibrosis using deep learning and image analysis. The method involves developing automated algorithms to recognize and score histological features like ballooning, inflammation, fibrosis, and steatosis from liver biopsy images. This allows fully automated diagnosis and staging of NASH and fibrosis without subjective manual interpretation. The algorithms use deep learning models to predict pathological patterns and morphometric measurements from tissue images. The automated method improves reproducibility and accuracy compared to manual scoring by pathologists.

Source

Method for diagnosing Alzheimer's disease progression using brain network analysis. The method involves extracting features from neuroimaging data like fMRI, converting brain networks to feature vectors using graph embedding, selecting relevant features, and classifying between Alzheimer's, mild cognitive impairment, and normal controls using machine learning techniques like SVM and ELM. The graph embedding technique called node2vec helps transform the brain network graphs into vector representations.

Source

Using interferometric micro-Doppler radar (IMDR) and deep learning to accurately distinguish between cognitively unimpaired individuals and persons with Alzheimer's disease based on gait analysis. The system captures 3D gait signals from both radial and transversal movement using IMDR. Deep learning algorithms process the radar signatures from multiple views to predict Alzheimer's disease risk. The IMDR-based gait data is combined with traditional feature extraction for optimal decision making. The system can quantify Alzheimer's disease risk using interferometric radar gait signatures processed by deep learning.

Source