Integrating PubMed and Google Scholar with ChatGPT To Optimize Cardiovascular Disease Treatment

Authors: Amina Khalpey, PhD, Brynne Rozell, BS, Zain Khalpey, MD, PhD, FACS

Cardiovascular diseases are a major cause of mortality and morbidity globally. Effective treatment and management of these conditions require the use of current and evidence-based medical knowledge. Medical databases such as Pubmed and Google Scholar are the largest sources of biomedical literature and provide access to a vast amount of information on treatment options for cardiovascular disease. However, finding the best treatment options from this vast amount of data can be a challenge for physicians. ChatGPT, an AI language model developed by OpenAI, can be utilized to assist physicians in finding the best treatment options for patients with cardiovascular disease. The API can also be programmed to provide references with every answer so physicians can rely on the program to support accurate medical decision making.

Strategy For ChatGPT Implementation:

ChatGPT can be integrated into Pubmed or Google Scholar to provide NLP-based (Natural Language Processing) searching capabilities. This would allow physicians to ask questions about the best treatment options for patients with cardiovascular disease in a conversational manner and receive relevant information in a prompt and accurate manner generated by AI. The AI system can be trained on medical terminology and concepts to enable it to understand and appropriately respond to medical queries.

Benefits of Using AI To Improve Patient Treatment:

The integration of ChatGPT into medical databases such as Pubmed and Google Scholar provides several benefits:

Improved efficiency: By using NLP searches, physicians can retrieve the information they need quickly and easily, saving time and increasing productivity.

Increased accuracy: The AI system’s ability to understand medical queries and retrieve relevant information can reduce the risk of errors in decision making.

Improved patient care: The availability of the latest and most effective treatment options for cardiovascular disease through the integration of ChatGPT with medical databases can enhance the quality of care provided to patients.

ChatGPT Integration Enables Doctors to Work Better and More Efficiently:

ChatGPT can provide a valuable tool for physicians in finding the best treatment options for patients with cardiovascular disease by integrating into medical databases such as Pubmed and Google Scholar. This would result in a more efficient and accurate way of retrieving information, ultimately improving patient care. However, it’s important to note that ChatGPT is not a replacement for human physicians and should be used as a tool to assist in decision making rather than replace it.

Introducing KAI:

Our lab has taken the initiative to create a program called KAI, the ultimate physician chatbot for patients, clinicians and scientists. This natural language processor, powered by ChatGPT, was designed to search research databases to provide relevant and scientific answers to queries, based on knowledge base.

There are three unique models for every healthcare need:

Kai Patient:

Designed for patients seeking general information about heart surgery, including what to expect, how to prepare, and understanding risks and benefits. Kai Patient provides reliable, personalized information based on your condition and preferences.

Kai Clinician (beta):

Tailored for healthcare professionals seeking clinical information related to medical and surgical diseases, such as diagnosis, treatment, guidelines, and best practices. Access the latest evidence and expert opinions from reputable sources and peers with Kai Clinician.

Kai Scientist (beta):

Crafted for researchers inquiring about scientific or translational questions in health sciences, such as literature reviews, data analysis, grant writing, and collaboration. Kai Scientist assists in finding relevant, high-quality information and resources for your research projects.

Try KAI out now!


Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., Blum, A., … & Winkler, J. (2018). Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 157 dermatologists. Annals of Oncology, 29(8), 1836-1842. doi: 10.1093/annonc/mdy166

Sallam M. ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns. Healthcare (Basel). 2023;11(6):887. Published 2023 Mar 19. doi:10.3390/healthcare11060887

Srivastava SK, Singh SK, Suri JS. State-of-the-art methods in healthcare text classification system: AI paradigm. Front Biosci (Landmark Ed). 2020;25(4):646-672. Published 2020 Jan 1. doi:10.2741/4826