Automated quantitative analysis of EEG data is ubiquitous in clinical neurophysiology research. However, these methods have not been fully adopted in medical practice, specifically to inform clinical diagnosis of neurological disorders. In this paper, some of the benefits and challenges of using these techniques as biomarkers for disease indication and progression are discussed. Examples of baseline EEG (resting state) data acquired with the same system and software from patients diagnosed with four types of neurodegenerative diseases are presented and compared with healthy controls. Overall power spectral density analyses showed clear significant differences in EEG for patient sub-types including enhanced theta power in dementia patients (Alzheimer’s and Lewy-body dementia), enhanced beta power in Parkinson’s patients (with or without dementia) and reduced Alpha power in Alzheimer’s dementia. To assess the discriminating power of resting state EEG spectral measures particularly for differential diagnosis at an individual level, a binary classifier was designed to classify EEG data across conditions after feature dimensionality reduction (PCA). The results were evaluated using the area under classifier’s ROC curve (AUC). On average, data acquired during eyes-closed resting state resulted in better classification than eyes-open. The highest classification performance (against healthy control) was obtained for Alzheimer’s dementia (AD) and Lewy-body dementia (LBD) with AUC =0.80 in both cases. The least accurate classification results were obtained for Mild Cognitive Impairments (MCI) group. The challenges of using resting state EEG for characterization of MCI is discussed and other examples of EEG biomarkers for MCI based on event-related-potentials in a cognitive test of visual memory are presented. An argument is made for adequate sensitivity/specificity of the current state-of-the-art in data-driven EEG analytics as secondary end-points in clinical trials. However, routine clinical diagnostic at an individual level may require a paradigm shift incorporating techniques of precision medicine and big data analytics. Multi-modal public datasets (including EEG and other imaging/clinical data) and adopting standards/protocols for sharing anonymized data between researchers could likely facilitate development of more reliable biomarkers in clinical practice.