With millions of people living with a disease as restraining as migraines, there are no ways to diagnose them before they occur. In this study, a migraine model using nitroglycerin is used in rats to study the awake brain activity during the migraine state. In an attempt to search for a biomarker for the migraine state, we found multiple deviations in EEG brain activity across different bands. Firstly, there was a clear decrease in power in the delta, beta, alpha, and theta bands. A slight increase in power in the gamma and high frequency bands was also found, which is consistent with other pain-related studies12. Additionally, we searched for a decreased pain threshold in this deviation, in which we concluded that more data analysis is needed to eliminate the multiple potential noise influxes throughout each dataset. However, with this study we did find a clear change in brain activity, but a more detailed analysis will narrow down what this change could mean and how it impacts the migraine state.
In 1953, Raymond Greene and Katharina Dalton, who were doctors in the UK, published The Premenstrual Syndrome in the British Medical Journal. In their article, Dalton and Greene established the term premenstrual syndrome (PMS). The authors defined PMS as a cluster of symptoms that include bloating, breast pain, migraine-headache, fatigue, anxiety, depression, and irritability. The article states that the symptoms begin one to two weeks before menstruation during the luteal phase of the menstrual cycle, and they disappear upon the onset of the menstrual period. Menstruation is the monthly series of changes a woman's body undergoes in preparation for the possibility of pregnancy. Dalton and Greene described how progesterone affected women during different phases of their menstrual cycles. The paper convinced many about the phenomenon of PMS, and docotors and scientists adopted Dalton's and Green's term. The paper furthered research about the role of hormones in physiology and of conditions linked to the reproductive system.
The first topic introduces an integration of machine learning (ML) and a mechanistic model (PI) to develop an SSL model applied to predicting cell density of glioblastoma brain cancer using multi-parametric medical images. The proposed ML-PI hybrid model integrates imaging information from unbiopsied regions of the brain as well as underlying biological knowledge from the mechanistic model to predict spatial tumor density in the brain.
The second topic develops a multi-modality imaging-based diagnostic decision support system (MMI-DDS). MMI-DDS consists of modality-wise principal components analysis to incorporate imaging features at different aggregation levels (e.g., voxel-wise, connectivity-based, etc.), a constrained particle swarm optimization (cPSO) feature selection algorithm, and a clinical utility engine that utilizes inverse operators on chosen principal components for white-box classification models.
The final topic develops a new SSL regression model with integrated feature and instance selection called s2SSL (with “s2” referring to selection in two different ways: feature and instance). s2SSL integrates cPSO feature selection and graph-based instance selection to simultaneously choose the optimal features and instances and build accurate models for continuous prediction. s2SSL was applied to smartphone-based telemonitoring of Parkinson’s Disease patients.