Data Mining of Free-Text Responses: An Innovative Approach to Analyzing Patient Perspectives on Treatment for Chronic Rhinosinusitis with Nasal Polyps in a Phase IIa Proof-of-Concept Study for Dupilumab

Figures & data

Table 1 Baseline Demographics and Clinical Characteristics

	Patients Who Completed the SAT		Patients Who Did Not Complete the SAT
	Placebo/MFNS (n = 16)	Dupilumab/MFNS (n = 21)	Placebo/MFNS (n = 14)	Dupilumab/MFNS (n = 9)
Age, mean (SD), years	50.4 (10.5)	46.4 (8.5)	48.0 (7.4)	49.9 (12.4)
Male sex, n (%)	8 (50.0)	13 (61.9)	8 (57.1)	5 (55.6)
NP duration, mean (SD), years	10.2 (8.0)	7.5 (5.6)	12.9 (9.5)	7.8 (7.7)
Bilateral endoscopic NPS, mean (SD), range 0–8^a	5.8 (0.7)	6.0 (0.7)	5.6 (1.1)	5.7 (1.5)
Lund–MacKay total CT score, mean (SD), range 0–24^a	18.4 (4.6)	19.0 (4.5)	19.1 (6.6)	17.8 (6.3)
Smell test (UPSIT) score, mean (SD), range 0–40^b	13.9 (4.5)	11.8 (7.0)	17.6 (10.4)	15.1 (10.8)
Sense of smell loss, mean (SD), range 0–3^a,c	2.9 (0.3)	2.5 (0.9)	2.7 (0.7)	2.2 (1.1)
SNOT-22 total score, mean (SD), range 0–110^a	41.1 (22.2)	43.1 (19.8)	39.9 (17.7)	37.6 (14.1)
CRSwNP disease severity (VAS), mean (SD), range 0–10 cm^a	5.4 (3.1)	6.3 (2.5)	7.7 (1.5)	6.7 (3.4)
Patients with comorbid asthma, n (%)	10 (62.5)	13 (61.9)	9 (64.3)	3 (33.3)
Patients with comorbid NSAID-ERD, n (%)	5 (31.3)	6 (28.6)	5 (35.7)	1 (11.1)

Notes: ^aHigher scores indicate worse status. ^bHigher scores indicate better status. ^c0 = no symptoms, 1 = mild symptoms, 2 = moderate symptoms, 3 = severe symptoms.

Abbreviations: CRSwNP, chronic rhinosinusitis with nasal polyps; CT, computed tomography; MFNS, mometasone furoate nasal spray; NP, nasal polyposis; NPS, nasal polyp score; NSAID-ERD, non-steroidal anti-inflammatory drug-exacerbated respiratory disease; SAT, self-assessment of treatment; SD, standard deviation; SNOT-22, 22-item Sino-Nasal Outcome Test; UPSIT, University of Pennsylvania Smell Identification Test; VAS, Visual Analog Scale.

Figure 1 Word clouds in patients treated with (A) dupilumab or (B) placebo. Word cloud based on frequency (higher frequency = bigger font size). Only words that occur twice or more are shown. Stop words and the words “study” and “treatment” are omitted.

Figure 2 Co-occurrence of words in patients completing a self-assessment tool treated with (A) dupilumab, (B) placebo. Words in the same cluster were more frequently reported together. Colors identify word clusters.

Figure 3 Sentiment analysis of patients completing a self-assessment tool: overall, dupilumab group, and placebo group.