Deep learning and feature based medication classifications from EEG in a large clinical data set

Spectral changes in electroencephalography linked to neuroactive medications: A computational pipeline for data mining and analysis

BACKGROUND AND OBJECTIVES

The increasing amount of open-access medical data provides new opportunities to gain clinically relevant information without recruiting new patients. We developed an open-source computational pipeline, that utilizes the publicly available electroencephalographic (EEG) data of the Temple University Hospital to identify EEG profiles associated with the usage of neuroactive medications. It facilitates access to the data and ensures consistency in data processing and analysis, thus reducing the risk of errors and creating comparable and reproducible results. Using this pipeline, we analyze the influence of common neuroactive medications on brain activity.

METHODS

The pipeline is constructed using easily controlled modules. The user defines the medications of interest and comparison groups. The data is downloaded and preprocessed, spectral features are extracted, and statistical group comparison with visualization through a topographic EEG map is performed. The pipeline is adjustable to answer a variety of research questions. Here, the effects of carbamazepine and risperidone were statistically compared with control data and with other medications from the same classes (anticonvulsants and antipsychotics).

RESULTS

The comparison between carbamazepine and the control group showed an increase in absolute and relative power for delta and theta, and a decrease in relative power for alpha, beta, and gamma. Compared to antiseizure medications, carbamazepine showed an increase in alpha and theta for absolute powers, and for relative powers an increase in alpha and theta, and a decrease in gamma and delta. Risperidone compared with the control group showed a decrease in absolute and relative power for alpha and beta and an increase in theta for relative power. Compared to antipsychotic medications, risperidone showed a decrease in delta for absolute powers. These results show good agreement with state-of-the-art research. The database allows to create large groups for many different medications. Additionally, it provides a collection of records labeled as "normal" after expert assessment, which is convenient for the creation of control groups.

CONCLUSIONS

The pipeline allows fast testing of different hypotheses regarding links between medications and EEG spectrum through ecological usage of readily available data. It can be utilized to make informed decisions about the design of new clinical studies.

Exploring patient medication adherence and data mining methods in clinical big data: A contemporary review

BACKGROUND

Increasingly, patient medication adherence data are being consolidated from claims databases and electronic health records (EHRs). Such databases offer an indirect avenue to gauge medication adherence in our data-rich healthcare milieu. The surge in data accessibility, coupled with the pressing need for its conversion to actionable insights, has spotlighted data mining, with machine learning (ML) emerging as a pivotal technique. Nonadherence poses heightened health risks and escalates medical costs. This paper elucidates the synergistic interaction between medical database mining for medication adherence and the role of ML in fostering knowledge discovery.

METHODS

We conducted a comprehensive review of EHR applications in the realm of medication adherence, leveraging ML techniques. We expounded on the evolution and structure of medical databases pertinent to medication adherence and harnessed both supervised and unsupervised ML paradigms to delve into adherence and its ramifications.

RESULTS

Our study underscores the applications of medical databases and ML, encompassing both supervised and unsupervised learning, for medication adherence in clinical big data. Databases like SEER and NHANES, often underutilized due to their intricacies, have gained prominence. Employing ML to excavate patient medication logs from these databases facilitates adherence analysis. Such findings are pivotal for clinical decision-making, risk stratification, and scholarly pursuits, aiming to elevate healthcare quality.

CONCLUSION

Advanced data mining in the era of big data has revolutionized medication adherence research, thereby enhancing patient care. Emphasizing bespoke interventions and research could herald transformative shifts in therapeutic modalities.

EEG classification of traumatic brain injury and stroke from a nonspecific population using neural networks

Traumatic Brain Injury (TBI) and stroke are devastating neurological conditions that affect hundreds of people daily. Unfortunately, detecting TBI and stroke without specific imaging techniques or access to a hospital often proves difficult. Our prior research used machine learning on electroencephalograms (EEGs) to select important features and to classify between normal, TBI, and stroke on an independent dataset from a public repository with an accuracy of 0.71. In this study, we expanded to explore whether featureless and deep learning models can provide better performance in distinguishing between TBI, stroke and normal EEGs by including more comprehensive data extraction tools to drastically increase the size of the training dataset. We compared the performance of models built upon selected features with Linear Discriminative Analysis and ReliefF with several featureless deep learning models. We achieved 0.85 area under the curve (AUC) of the receiver operating characteristic curve (ROC) using feature-based models, and 0.84 AUC with featureless models. In addition, we demonstrated that Gradient-weighted Class Activation Mapping (Grad-CAM) can provide insight into patient-specific EEG classification by highlighting problematic EEG segments during clinical review. Overall, our study suggests that machine learning and deep learning of EEG or its precomputed features can be a useful tool for TBI and stroke detection and classification. Although not surpassing the performance of feature-based models, featureless models reached similar levels without prior computation of a large feature set allowing for faster and cost-efficient deployment, analysis, and classification.

Predicting medication adherence using ensemble learning and deep learning models with large scale healthcare data

Clinical studies from WHO have demonstrated that only 50–70% of patients adhere properly to prescribed drug therapy. Such adherence failure can impact therapeutic efficacy for the patients in question and compromises data quality around the population-level efficacy of the drug for the indications targeted. In this study, we applied various ensemble learning and deep learning models to predict medication adherence among patients. Our contribution to this endeavour involves targeting the problem of adherence prediction for a particularly challenging class of patients who self-administer injectable medication at home. Our prediction pipeline, based on event history, comprises a connected sharps bin which aims to help patients better manage their condition and improve outcomes. In other words, the efficiency of interventions can be significantly improved by prioritizing the patients who are most likely to be non-adherent. The collected data comprising a rich event feature set may be exploited for the purposes of predicting the status of the next adherence state for individual patients. This paper reports on how this concept can be realized through an investigation using a wide range of ensemble learning and deep learning models on a real-world dataset collected from such a system. The dataset investigated comprises 342,174 historic injection disposal records collected over the course of more than 5 years. A comprehensive comparison of different models is given in this paper. Moreover, we demonstrate that the selected best performer, long short-term memory (LSTM), generalizes well by deploying it in a true future testing dataset. The proposed end-to-end pipeline is capable of predicting patient failure in adhering to their therapeutic regimen with 77.35 % accuracy (Specificity: 78.28 %, Sensitivity: 76.42%, Precision: 77.87%,F1 score: 0.7714, ROC AUC: 0.8390).