In 2020, OpenAI unveiled their third-generation language generation model, which is known as the generative pretrained transformer 3 (GPT-3) model [1]. This model was the latest in a line of large pretrained models designed for understanding and producing natural language by using the transformer architecture, which was published only 3 years prior and significantly improved natural language understanding task performance over that of models built on prior architectures [2]. However, GPT-3’s development was remarkable because it resulted in a substantial increase in the model’s size; it increased by more than 10-fold in 1 year, reaching 175 billion weights [1-3]. GPT-3’s increased model size makes it substantially more powerful than prior models; propels its language capabilities to near–human-like levels; and, in some cases, makes it the superior option for several language understanding tasks [1].

Ordinarily, deep learning tasks require large amounts of labeled training data. This requirement usually limits the tasks to which deep learning can be effectively applied. However, with its increased model size, GPT-3 has an enhanced capability for so-called few-shot, one-shot, and zero-shot learning when compared to prior models [1,4]. These learning methods involve training a model on significantly smaller amounts of training data. In these methods, the models are given a description of the task and, if applicable, a handful of examples to learn from, with few-shot training on only hundreds to thousands of instances, one-shot training on only 1 example, and zero-shot training on only the task description.

GPT-3 was designed as a language generation model, focusing on producing appropriate text responses to an input. Although it can be adapted to address more traditional machine learning tasks, such as answering yes-no questions, matching pronouns to their nouns, and conducting sentiment analyses [1], GPT-3’s text generation capabilities have attracted much attention as a potential solution for a variety of problems, such as creating enhanced chatbots [5], answering complex questions, generating computer code from a design specification [6], and writing news articles [7]. As such, there is much research on and commercial interest in using GPT-3 for a variety of text generation applications. Textbox 1 illustrates the power of GPT-3 in 3 question and answer examples [8]. In 3 cases, GPT-3 provided human-like logical and intellectual responses. However, applying GPT-3 in health care is still an emerging topic.

A plethora of research articles have outlined the potential opportunities for integrating artificial intelligence (AI) and machine learning models in a variety of hospital and health care settings [9-11]. However, the authors also quickly pointed out the many development and implementation challenges to deploying such solutions, such as the lack of transparency [11], potential model biases [9], and financing [10]. A successful deployment of GPT-3 would need to overcome all of these standard barriers to AI implementation alongside the additional challenges that GPT-3 itself introduces [12]. In this viewpoint, we introduce the use of GPT-3 in the health care setting with a use case and discuss implementation and operational considerations for its use in clinical practice.

The power of meaningful text generation by GPT-3 makes it an ideal tool for human-machine conversations, especially those conducted via chatbots. In our case, we illustrate the use of GPT-3 within a hospital network. In this hypothetical example, the hospital is providing a chatbot triaging mechanism for incoming patients to reduce the overhead at clinics and increase the safety and quality of care during the COVID-19 pandemic. The chatbot has to be connected to the hospital network, combined with a triage text summary service that is to be reviewed, and stored in the electronic health record (EHR; Figure 1). Putting aside the front-end details in this workflow (Figure 1), this use case outlines a typical implementation of GPT-3 as a service within a health system.

In this example, triage could be initiated by a patient or a hospital to conduct a health screening. The front-end application is operationalized through a chatbot mechanism over a front-end application, which could be a patient portal app, voice assistant, phone call, or SMS text messaging. Once a connection is established, the hospital system formulates GPT-3 requests by gathering patient health information and formatting this information to be interpretable with the GPT-3 model. Within the secure hospital network, GPT-3 is located outside of the EHR and provided as the “GPT-3-as-a-Service” platform. The application programming interface enables interoperability and acts as a gatekeeper for the data transfer of requests and responses. Once a request is received, the “GPT-3-as-a-Service” platform preprocesses the data and requests, allocates the tasks to be completed, produces outputs in an interpretable format, and sends the outputs to users. The type of tasks allocated depends on the requests, which, in our case, are question answering, text generation or culturally appropriate language translation, and text summarization. The response is sent back to the EHR system and then to the front-end application. At the end of triage, similar to the after-visit summary, the conversation text is summarized. To reduce the additional clinical burden of reading the whole conversation, GPT-3 summarizes the text (similar to a digital scriber) and stores it in the patient's health records. To avoid or address potential biases [12], correct errors, and increase the control over patient data use and the model, the human-in-the-loop model [13] can be implemented by using a report back mechanism at the front end, or the clinical team can be given oversight of GPT-3 integrated process in the hospital EHR system at the back end. Furthermore, the error corrections and adjustments in the text can be used to fine-tune the GPT-3 model to increase its accuracy and effectiveness.

To be able to execute this use case in a real-world setting, health care practitioners and decision makers should consider and address the following operational and implementation challenges.

In addition to implementation, there are 3 major operational factors driving the adoption of GPT-3 in health care, as follows: (1) GPT-3 needs to work in compliance with the Health Insurance Portability and Accountability Act (HIPAA), (2) technology providers need to earn trust from health care providers, and (3) technology providers should improve access to the tool (Figure 2).

Similar to GPT-3, there was huge enthusiasm to use the Amazon Alexa (Amazon.com Inc) voice assistant in health care delivery when it was released in 2014. However, at the time, Alexa was not yet legally able to store or transmit private health information. It took Amazon 5 years to become HIPAA compliant and to be able to sign business associate agreements with health care providers [22]. A limited number of Alexa skills was released, and there is still a long list of other Alexa skills waiting to become HIPAA compliant. This example shows the slow progress of legislation changes and regulation updates for including new technologies in health care, suggesting that efforts should be put forward as early as possible for GPT-3. Without HIPAA compliance, the adoption of GPT-3 in health care can be a false start [23]. However, although HIPAA compliance may not be immediate, it may be gradually progressing. GPT-3 is a black-box model, which complicates the HIPAA compliance process because unlike with other types of programmatic solutions, it is harder to decipher how data are processed internally by the model itself. However, assuming that GPT-3 will be deployable in the future, operations will start with implementing the limited capabilities of GPT-3 (ie, storing and transmitting data, running behind the firewalls of specific hardware [security rules], and analyzing a specific data set or patient cohort [privacy rules]). In parallel, further practices are needed to optimize the payment models for accommodating GPT-3 and seek opportunities for satisfying the US Food and Drug Administration’s requirements for software as a medical device [24] with regard to using AI in clinical applications.

In addition to legal requirements, trust must be established among patients, health care providers, and technology companies to adopt GPT-3 [25]. It is common for technology companies to claim the right that they can use their customers’ data to further improve their services or achieve additional commercial value. Additionally, the culture of skepticism toward AI among clinicians can place a heavy burden on model interpretability and result in lower trust in clinical care than in other industries [10]. Unlike commercial implementations, GPT-3 needs to be explicitly discussed in terms of what it will and will not do with a patient’s data. Health care providers’ data governance committees need to be aware and comfortable when they sign the service agreement with GPT-3. Given the black-box nature of GPT-3, an operational strategic approach will be necessary for interpreting the evaluation reports and outcomes that are generated through the human-in-the-loop model.

Access also needs to be ensured. Training large language models like GPT-3 can cost tens of millions of dollars. As such, GPT-3 is innovating the business model of access. Currently, GPT-3 is privately controlled by OpenAI, and health care providers can remotely run the program and pay for usage per token (1000 tokens are approximately equivalent to 750 words) [26]. In September 2020, Microsoft bought an exclusive license to GPT-3, with plans to integrate it into its existing products. Similarly, a number of companies are already integrating GPT-3 model predictions into their products. However, this business model also limits open-access research and development and will eventually limit improvements, such as advancements in translation mechanisms and all-inclusive, equity-driven approaches in conversational agent development. In these early stages, open-source alternatives, such as GPT-J [27], may help health care developers and institutions assess operational viability. In future iterations, once the value of using GPT-3 in the health care setting is assured, the responsibility of accessibility could be delegated to health care and government agencies. Such agencies may distribute the “GPT-3-as-a-Service” platform through secure cloud platforms and establish a federated learning mechanism to run decentralized training services while collaboratively contributing to the GPT-3 model [28]. This would also reduce the burden on individual health systems when it comes to building, training, and deploying their own GPT-3 platforms and reduce costs. These advantages are especially beneficial for hospitals in low-resource settings.

In this viewpoint, we briefly introduce GPT-3 and its capabilities and outline considerations for its implementation and operationalization in clinical practice through a use case. Building on top of Korngiebel and Mooney’s [12] remarks toward unrealistic, realistic, feasible, and realistic but challenging use cases, we provide consideration points for implementing and operationalizing GPT-3 in clinical practice. We believe that our work can inform health care practitioners, developers, clinicians, and decision makers toward understanding the use of the powerful AI tools integrated into hospital systems and health care.