AI in healthcare: A narrative review

Balogun, Oluwafemi Samson; Haataja, Keijo; Vehviläinen‐Julkunen, Katri; Toivanen, Pekka

doi:10.12688/f1000research.26997.2

Cited by 34 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(10) AI has found its place in healthcare as robotic-assisted surgical systems, virtual nurse assistants, medications management, medical diagnostics, and so on. (10) This paper will discuss the potential of a speci c AI model, GPT-3.5 Turbo for ICD code assignment.…”

Section: Ai In Healthcarementioning

confidence: 99%

Fine-Tuning for Accuracy: Evaluation of GPT for Automatic Assignment of ICD Codes to Clinical Documentation

Nawab,

Fernbach,

Atreya

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Assignment of International Classification of Disease (ICD) codes to clinical documentation is a tedious but important task that is mostly done manually. This study evaluated the widely popular OpenAI’s Generative Pretrained Model (GPT) 3.5 Turbo in facilitating the automation of assigning ICD codes to clinical notes. Methods: We identified the 10 most prevalent ICD-10 codes in the Medical Information Mart for Intensive Care (MIMIC-IV) dataset. We selected 200 notes for each code, and then split them equally into two groups of 100 each (randomly selected) for training and testing. We then passed each note to GPT 3.5 Turbo via OpenAI’s API, prompting the model to assign ICD-10 codes to each note. We evaluated the model’s response for the presence of the target ICD-10 code. After fine-tuning the GPT model on the training data, we repeated the process with the test data, comparing the fine-tuned model’s performance against the default model. Results: Initially the target ICD-10 code was present in the assigned codes by the default GPT 3.5 Turbo model in 29.7% of the cases. After fine-tuning with 100 notes for each top code, the accuracy improved to 62.6%. Conclusions: Historically, GPT’s performance for healthcare related tasks is sub-optimal. Fine-tuning as in this study provides great potential for improved performance, highlighting a path forward for integration of Artificial Intelligence (AI) in healthcare for improved efficiency and accuracy of this administrative task. Future research should focus on expanding the training datasets with specialized data and exploring the potential integration of these models into existing healthcare systems to maximize their utility and reliability.

show abstract

Section: Ai In Healthcarementioning

confidence: 99%

Fine-Tuning for Accuracy: Evaluation of GPT for Automatic Assignment of ICD Codes to Clinical Documentation

Nawab,

Fernbach,

Atreya

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Human teaming with intelligent machines has become a fundamental characteristic of a successful CDSS. Acceptance of a CDSS for basic functions is more achievable for systems that provide simple support [ 22 ]. For more complex capabilities, including autonomous ones, adding qualitative human perspectives to machine intelligence will be important.…”

Section: Technical Approachmentioning

confidence: 99%

Providing Care: Intrinsic Human–Machine Teams and Data

Russell

Kumar

2022

Entropy

View full text Add to dashboard Cite

Despite the many successes of artificial intelligence in healthcare applications where human–machine teaming is an intrinsic characteristic of the environment, there is little work that proposes methods for adapting quantitative health data-features with human expertise insights. A method for incorporating qualitative expert perspectives in machine learning training data is proposed. The method implements an entropy-based consensus construct that minimizes the challenges of qualitative-scale data such that they can be combined with quantitative measures in a critical clinical event (CCE) vector. Specifically, the CCE vector minimizes the effects where (a) the sample size is too small, (b) the data may not be normally distributed, or (c) The data are from Likert scales, which are ordinal, so parametric statistics cannot be used. The incorporation of human perspectives in machine learning training data provides encoding of human considerations in the subsequent machine learning model. This encoding provides a basis for increasing explainability, understandability, and ultimately trust in AI-based clinical decision support system (CDSS), thereby improving human–machine teaming concerns. A discussion of applying the CCE vector in a CDSS regime and implications for machine learning are also presented.

show abstract

“…Given that the use of AI in healthcare is still in its early stages, the empirical research in this field is lacking [ 31 , 32 ]. In addition, because the medical field involves human life and health problems, it presents unique characteristics.…”

Section: Background and Previous Researchmentioning

confidence: 99%

Adopting Artificial Intelligence in Public Healthcare: The Effect of Social Power and Learning Algorithms

Sun

2021

IJERPH

View full text Add to dashboard Cite

Although the use of artificial intelligence (AI) in healthcare is still in its early stages, it is important to understand the factors influencing its adoption. Using a qualitative multi-case study of three hospitals in China, we explored the research of factors affecting AI adoption from a social power perspective with consideration of the learning algorithm abilities of AI systems. Data were collected through semi-structured interviews, participative observations, and document analysis, and analyzed using NVivo 11. We classified six social powers into knowledge-based and non-knowledge-based power structures, revealing a social power pattern related to the learning algorithm ability of AI.

show abstract

AI in healthcare: A narrative review

Cited by 34 publications

References 37 publications

Fine-Tuning for Accuracy: Evaluation of GPT for Automatic Assignment of ICD Codes to Clinical Documentation

Fine-Tuning for Accuracy: Evaluation of GPT for Automatic Assignment of ICD Codes to Clinical Documentation

Providing Care: Intrinsic Human–Machine Teams and Data

Adopting Artificial Intelligence in Public Healthcare: The Effect of Social Power and Learning Algorithms

Contact Info

Product

Resources

About