Clinical diagnosis is a challenging task for which high expertise is required at the doctors’ end. It is recognized that technology integration with the clinical domain would facilitate the diagnostic process. A semantic understanding of the medical domain and clinical context is needed to make intelligent analytics. These analytics need to learn the medical context for different purposes of diagnosing and treating patients. Traditional diagnoses are made through phenotype features from patients’ profiles. It is also a known fact that diabetes mellitus (DM) is widely affecting the population and is a chronic disease that requires timely diagnosis. The motivation for this research comes from the gap found in discovering the common ground for medical context learning in analytics to diagnose DM and its comorbidity diseases. Therefore, a unified medical knowledge base is found significantly important to learning contextual Named Entity Recognition (NER) embedding for semantic intelligence. Our search for possible solutions for medical context learning told us that unified corpora tagged with medical terms were missing to train the analytics for diagnoses of DM and its comorbidities. Hence, we put effort into collecting endocrine diagnostic electronic health records (EHR) corpora for clinical purposes that are labeled with ICD-10-CM international coding scheme. International Codes for Diseases (ICD) by the World Health Organization (WHO) is a known schema to represent medical codes for diagnoses. The complete endocrine EHR corpora make DM-Comorbid-EHR-ICD-10 Corpora. DM-Comorbid-EHR-ICD-10 Corpora is tagged for understanding the medical context with uniformity. We experimented with different NER sequence embedding approaches using advanced ML integrated with NLP techniques. Different experiments used common frameworks like; Spacy, Flair, and TensorFlow, Keras. In our experiments albeit label sets in the form of (instance, label) pair for diagnoses were tagged with the Sequential() model found in TensorFlow.Keras using Bi-LSTM and dense layers. The maximum accuracy achieved was 0.9 for Corpus14407_DM_pts_33185 with a maximum number of diagnostic features taken as input. The sequential DNN NER model diagnostic accuracy increased as the size of the corpus grew from 100 to 14407 DM patients suffering from comorbidity diseases. The significance of clinical notes and practitioner comments available as free text is clearly seen in the diagnostic accuracy.