Pricing, Popularity, and Customer Satisfaction in Online Pain-Relief Products: An AI-Powered Analysis

Oranicha Jumreornvong,1,* Piyawat Kantagowit,2,* Runchana Parnicharoende,3,* R Jason Yong,4 Giuliano Lo Bianco,5 Qing Zhao Ruan,6 Jamal Hasoon,7 Matthew Chung,8 Michael E Schatman,9,10 Generoso Rullo,11 Paul J Christo,12 Mohammed Issa,4 Christopher L Robinson12 1Department of Human Performance and Rehabilitation, Icahn School of Medicine at Mount Sinai, New York, NY, USA; 2Department of Surgery, NYU Grossman School of Medicine, New York, NY, USA; 3Department of Rehabilitation Medicine, Faculty of Medicine, Chulalongkorn University, Bangkok, Thailand; 4Department of Anesthesiology, Perioperative, and Pain Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA; 5Anesthesiology and Pain Department, Foundation G. Giglio, Cefalù, Palermo, Italy; 6Warren Alpert Medical School, Brown University, Providence, RI, USA; 7Department of Anesthesia, Critical Care, and Pain Medicine, UTHealth McGovern Medical School, Houston, TX, USA; 8Department of Pain Medicine, Division of Anesthesia, Critical Care and Pain Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; 9Department of Anesthesiology, Perioperative Care, and Pain Medicine, NYU Grossman School of Medicine, New York, NY, USA; 10Department of Population Health, Division of Medical Ethics, NYU Grossman School of Medicine, New York, NY, USA; 11Department of Chemistry and Biochemistry, University of Notre Dame, Notre Dame, IN, USA; 12Division of Pain Medicine, Department of Anesthesiology and Critical Care Medicine, The Johns Hopkins University School of Medicine, Baltimore, MD, USA*These authors contributed equally to this workCorrespondence: Christopher L Robinson, Division of Pain Medicine Department of Anesthesiology and Critical Care Medicine the Johns Hopkins University School of Medicine, Baltimore, MD, USA, Email christopherrobinsonmdphd@outlook.comObjective: To examine how product popularity and pricing are associated with customer satisfaction across pain-relief device types on online e-commerce platforms.Methods: A cross-sectional study was conducted to analyze pain-relief products from Amazon and Best Buy. Data were collected via automated web scraping, verified, and categorized into 10 device types. Key variables including product names, prices, customer ratings, and review volumes were assessed in multivariable regression models.Results: A total of 378 distinct pain-relief products were analyzed. The median customer ratings for pain-relief devices varied significantly by type, ranging from 3.2 to 4.5 (p < 0.001). TENS units and cold/heat therapy packs achieved the highest median ratings of 4.5 (4.3– 4.6). In contrast, hand/arm massagers received the lowest median rating of 3.2 (2.2– 4.2). Pricing differences across device types were significant (p < 0.001), with neck stretchers being the least expensive (median: $29.99) and hand/arm massagers being the most expensive (median: $249.50).Discussion: Although price and the number of reviews were not significant predictors of customer ratings in multivariable regression models, significant interactions were observed between price and device type for hand/arm massagers (p < 0.001) and massage guns (p = 0.006). Additionally, significant interactions between the number of reviews and device type were observed for hand/arm massagers (p = 0.004).Conclusion: Although pricing and review quantity were not significant predictors of satisfaction for most devices, they did interact with specific categories such as hand/arm massagers and massage guns. These findings indicate that customer satisfaction is driven more by device-specific characteristics than by price or review volume.Keywords: artificial intelligence, pain-relief, customer satisfaction