Real-world insights of patient voices with age-related macular degeneration in the Republic of Korea and Taiwan: an AI-based Digital Listening study by Semantic-Natural Language Processing

Abstract

Background: In this era of active online communication, patients increasingly share their healthcare experiences, concerns, and needs across digital platforms. Leveraging these vast repositories of real-world information, Digital Listening enables the systematic collection and analysis of patient voices through advanced technologies. Semantic-NLP artificial intelligence, with its ability to process and extract meaningful insights from large volumes of unstructured online data, represents a novel approach for understanding patient perspectives. This study aimed to demonstrate the utility of Semantic-NLP technology in presenting the needs and concerns of patients with age-related macular degeneration (AMD) in Korea and Taiwan.

Methods: Data were collected and analysed over three months from January 2023 using an ontology-based information extraction system (Semantic Hub). The system identified patient "stories" and extracted themes from online posts from January 2013 to March 2023, focusing on Korea and Taiwan by filtering the geographic location of users, the language used, and the local online platforms. Extracted texts were structured into knowledge graphs and analysed descriptively.

Results: The patient voice was identified in 133,857 messages (9,620 patients) from the Naver online platform in Korea and included internet chat forums focused on macular degeneration. The most important factors for AMD treatments were effectiveness (1,632/3,401 mentions; 48%), price and access to insurance (33%), tolerability (10%) and doctor and clinic recommendations (9%). Treatment burden associated with intravitreal injection of vascular endothelial growth factor inhibitors related to tolerability (254/942 mentions; 27%), financial burden (20%), hospital selection (18%) and emotional burden (14%). In Taiwan, 444 messages were identified from Facebook, YouTube and Instagram. The success of treatment was judged by improvements in visual acuity (20/121 mentions; 16.5%), effect on oedema (10.7%), less distortion (9.1%) and inhibition of angiogenesis (5.8%). Tolerability concerns were rarely mentioned (26/440 mentions; 5.9%).

Conclusions: Digital Listening using Semantic-NLP can provide real-world insights from large amounts of internet data quickly and with low human labour cost. This allows healthcare companies to respond to the unmet needs of patients for effective and safe treatment and improved patient quality of life throughout the product lifecycle.

Keywords: Digital; Macular degeneration; Natural language processing; Patient voice; Real-world data; Semantics/semantic analysis; Social media; Tolerability; Unmet needs.

Fig. 1

Process of identifying, extracting and presenting data. Note: Within the knowledge graph, the nodes are objects and the lines are relations between them (facts)

Fig. 2

Selection of messages in the study. Note: A much higher proportion of messages collected in Taiwan (85%) than in Korea (33%) were excluded for having non-meaningful content. This may be explained by the availability of relevant online support groups for patients and carers in Korea, while in Taiwan there were general groups for the discussion of eye health and with a significant number of advertisements

Fig. 3

Criteria for selection of A clinician and treatment centre and B treatment in Korea

Fig. 4

A Criteria patients use to determine the success of their treatment and B patients’ concerns about treatment outcomes expressed by patients in Korea

Fig. 5

Treatment burden in Korea

Fig. 6

A Criteria patients use to determine the success of their treatment and B patients’ concerns about treatment outcomes expressed by patients in Taiwan