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.

PURPOSE: Patient perspective is an important and increasingly sought-after complement to clinical assessment. The aim of this study was to transcribe individual patients' experience of treatment in a dupilumab clinical trial through free-text responses with analysis using natural language processing (NLP) to obtain the unique perspective of patients on disease impact and unmet needs with existing treatment to inform future trial design. PATIENTS AND METHODS: Patients with chronic rhinosinusitis with nasal polyps (CRSwNP) who were enrolled in a Phase IIa randomized controlled trial comparing dupilumab with placebo (NCT01920893) were invited to complete a self-assessment of treatment (SAT) tool at the end of treatment, asking, "What is your opinion on the treatment you had during the trial? What did you like or dislike about the treatment?" Free-text responses were analyzed for the overall cohort and according to treatment assignment using natural language processing including sentiment scoring. In a mixed-methods approach, quantitative patient-reported outcome (PRO) results were utilized to complement the qualitative analysis of free-text responses. RESULTS: Of 60 patients enrolled in the study, 43 (71.6%) completed the SAT and responses from 37 patients were analyzed (placebo, n = 16; dupilumab, n = 21). Word analyses showed that the most common words were "smell," "improve," "staff," "great," "time," and "good." Across the whole cohort, "smell" was the most common symptom-related word. The words "smell" and "experience" were more likely to occur in patients treated with dupilumab. Patients treated with dupilumab also had more positive sentiment in their SAT responses than those who received placebo. The results from this qualitative analysis were reflected in quantitative PRO results. CONCLUSION: "Smell" was important to patients with CRSwNP, highlighting its importance as a patient-centric efficacy outcome measure in the context of clinical trials in CRSwNP. TRIAL REGISTRATION: ClinicalTrials.gov, NCT01920893. Registered 12 August 2013, https://www.clinicaltrials.gov/ct2/show/NCT01920893.

Correction to: Qualitative Assessment of Adult Patients' Perception of Atopic Dermatitis Using Natural Language Processing Analysis in a Cross-Sectional Study.

The authors would like to correct the images in figures which are in wrong order and require swapping.

Qualitative Assessment of Adult Patients' Perception of Atopic Dermatitis Using Natural Language Processing Analysis in a Cross-Sectional Study.

INTRODUCTION: Atopic dermatitis (AD) is an incurable, inflammatory skin disease characterized by skin barrier disruption and immune dysregulation. Although AD is considered a childhood disease, adult onset is possible, presenting with daily sleep disturbance and functional impairment associated with itch, neuropsychiatric issues (anxiety and depression), and reduced health-related quality of life. Although such aspects of adult AD disease burden have been measured through standardized assessments and based on population-level data, the understanding of the disease experienced at the patient level remains poor. This text-mining study assessed the impact of AD on the lives of adult patients as described from an experiential perspective. METHODS: Natural language processing (NLP) was applied to qualitative patient response data from two large-scale international cross-sectional surveys conducted in the USA and countries outside of the USA (non-USA; Canada, France, Germany, Italy, Spain, and the UK). Descriptive analysis was conducted on patient responses to an open-ended question on how they felt about their AD and how the disease affected their life. Character length, word count, and stop word (common words) count were evaluated; centrality analysis identified concepts that were most strongly interlinked. RESULTS: Patients with AD in all countries were most frequently impacted by itch, pain, and embarrassment across all levels of disease severity. Patients with moderate-to-severe AD were more likely than patients with mild AD to describe sleep disturbances, fatigue, and feelings of depression, anxiety, and a lack of hope that were directly associated with AD. Centrality analysis revealed sleep disturbance was strongly linked with itch. Collectively, these concepts revealed that patients with AD are impacted by both physical and emotional burdens that are intricately connected. CONCLUSIONS: Qualitative data from NLP, being more patient-centric than data from clinical standardized measures, provide a more comprehensive view of the burden of AD to inform disease management.

Dupilumab improves health-related quality of life in patients with chronic rhinosinusitis with nasal polyposis.

BACKGROUND: Chronic rhinosinusitis with nasal polyposis (CRSwNP) negatively affects health-related quality of life (HRQoL). In a previously reported randomized clinical trial (NCT01920893), addition of dupilumab to mometasone furoate in patients with CRSwNP refractory to intranasal corticosteroids (INCS) significantly improved endoscopic, radiographic, and clinical endpoints and patient-reported outcomes. The objective of this analysis was to examine the impact of dupilumab treatment on HRQoL and productivity using secondary outcome data from this trial. METHODS: Following a 4-week mometasone furoate nasal spray run-in, patients were randomized to commence subcutaneous dupilumab (600 mg loading dose, then 300 mg once weekly for 15 weeks [n = 30], or matched placebo [n = 30]). Outcomes included scores on the CRS disease severity visual analog scale (VAS), 22-item Sino-Nasal Outcome Test (SNOT-22), 5-dimension EuroQoL (EQ-5D) general health status VAS, and 36-item Short-Form Health Survey (SF-36) for HRQoL and nasal polyp-related healthcare resource use questionnaires. RESULTS: Following 16 weeks of treatment, the proportion of patients with moderate-to-severe CRSwNP (VAS > 3-10) decreased from 86.2% to 21.4% with dupilumab and 88.0% to 84.2% with placebo. Dupilumab (vs placebo) resulted in significantly greater improvement in HRQoL, based on SNOT-22, SF-36, and EQ-5D VAS scores. The dupilumab group had a significantly lower adjusted annualized mean number of sick leave days (0.09, vs 4.18 with placebo, P = .015) and significantly greater improvement (vs placebo) in the SNOT-22 item "reduced productivity." CONCLUSIONS: In adults with CRSwNP refractory to treatment with INCS alone, the addition of dupilumab reduced disease severity, significantly improved HRQoL, and improved productivity.

Dupilumab improves symptoms, quality of life, and productivity in uncontrolled persistent asthma.

BACKGROUND: In a pivotal, phase 2b study (NCT01854047) in patients with uncontrolled persistent asthma, despite using medium-to-high-dose inhaled corticosteroids plus long-acting ß2 agonists, dupilumab improved lung function, reduced severe exacerbations, and showed an acceptable safety profile. OBJECTIVE: To assess the impact of dupilumab on asthma control, symptoms, quality of life (QoL), and productivity. METHODS: Data are shown for the intention-to-treat population receiving dupilumab 200/300 mg every 2 weeks (doses being assessed in phase 3; NCT02414854), or placebo. Predefined analyses of total scores were conducted at week 24 for the 5-item Asthma Control Questionnaire (ACQ-5), patient-reported morning/evening (AM/PM) asthma symptoms, Asthma Quality of Life Questionnaire (AQLQ), and asthma-related productivity loss. Responder rate analyses for these measures, subgroup analyses by baseline characteristics, and asthma-related productivity loss analyses were conducted post hoc. RESULTS: Data from 465 patients were analyzed (158 placebo; 307 dupilumab). Both dupilumab doses significantly improved scores through week 24 (all outcomes, overall population). The proportion of patients meeting or exceeding the minimal clinically important difference for the overall population were significantly greater vs placebo (P < .05) for ACQ-5 (range, 72.6%-76.7% vs 61.4%), for AM/PM asthma symptoms score (48.7%-54.1% vs 34.2% and 52.7%-53.5% vs 34.2%, respectively) and for AQLQ (64.0%-65.0% vs 51.3%). The effect of dupilumab was consistent across most subgroups. Productivity loss was significantly higher in placebo- vs dupilumab-treated patients (P < .0001). CONCLUSION: Dupilumab produced significant, clinically meaningful improvements in asthma control, symptoms, QoL, and productivity. REGISTRATION: ClinicalTrials.gov Identifier: NCT01854047.

Stopping Antidepressants and Anxiolytics as Major Concerns Reported in Online Health Communities: A Text Mining Approach.

BACKGROUND: Internet is a particularly dynamic way to quickly capture the perceptions of a population in real time. Complementary to traditional face-to-face communication, online social networks help patients to improve self-esteem and self-help. OBJECTIVE: The aim of this study was to use text mining on material from an online forum exploring patients' concerns about treatment (antidepressants and anxiolytics). METHODS: Concerns about treatment were collected from discussion titles in patients' online community related to antidepressants and anxiolytics. To examine the content of these titles automatically, we used text mining methods, such as word frequency in a document-term matrix and co-occurrence of words using a network analysis. It was thus possible to identify topics discussed on the forum. RESULTS: The forum included 2415 discussions on antidepressants and anxiolytics over a period of 3 years. After a preprocessing step, the text mining algorithm identified the 99 most frequently occurring words in titles, among which were escitalopram, withdrawal, antidepressant, venlafaxine, paroxetine, and effect. Patients' concerns were related to antidepressant withdrawal, the need to share experience about symptoms, effects, and questions on weight gain with some drugs. CONCLUSIONS: Patients' expression on the Internet is a potential additional resource in addressing patients' concerns about treatment. Patient profiles are close to that of patients treated in psychiatry.

The "Efficacy-Effectiveness Gap": Historical Background and Current Conceptualization.

BACKGROUND: The concept of the "efficacy-effectiveness gap" (EEG) has started to challenge confidence in decisions made for drugs when based on randomized controlled trials alone. Launched by the Innovative Medicines Initiative, the GetReal project aims to improve understanding of how to reconcile evidence to support efficacy and effectiveness and at proposing operational solutions. OBJECTIVES: The objectives of the present narrative review were 1) to understand the historical background in which the concept of the EEG has emerged and 2) to describe the conceptualization of EEG. METHODS: A focused literature review was conducted across the gray literature and articles published in English reporting insights on the EEG concept. The identification of different "paradigms" was performed by simple inductive analysis of the documents' content. RESULTS: The literature on the EEG falls into three major paradigms, in which EEG is related to 1) real-life characteristics of the health care system; 2) the method used to measure the drug's effect; and 3) a complex interaction between the drug's biological effect and contextual factors. CONCLUSIONS: The third paradigm provides an opportunity to look beyond any dichotomy between "standardized" versus "real-life" characteristics of the health care system and study designs. Namely, future research will determine whether the identification of these contextual factors can help to best design randomized controlled trials that provide better estimates of drugs' effectiveness.

Randomized controlled trials in relapsed/refractory follicular lymphoma: a systematic review and meta-analysis.

This systematic literature review evaluated the clinical efficacy and safety of interventions used in relapsed/refractory follicular lymphoma. Primary efficacy outcomes were objective response rate, progression-free survival and overall survival. Safety endpoints were grade 3/4 toxicities, serious adverse events and withdrawals or deaths due to toxicity. Studies were selected if they were randomized controlled trials reporting on the efficacy or safety of treatments for relapsed or refractory follicular lymphoma, and if outcomes were reported separately from trials that included other lymphoid neoplasms. We used the Bucher method for conducting adjusted indirect comparisons within a meta-analysis. We identified 10 randomized controlled trials of treatments for relapsed/refractory follicular lymphoma. The most prominent drug investigated (alone or in combination) was rituximab. Most trials did not report median overall survival. Two trials reported median event-free survival (range, 1.2-23.2 months). Six of ten trials reported objective response rate (range, 9-93%). Meta-analysis showed only one statistically significant result: rituximab + bortezomib yielded a significantly higher objective response rate than rituximab monotherapy (relative risk, 1.28; 95% confidence interval, 1.11-1.47). Otherwise, there were no discernable differences in overall survival or progression-free survival, partly due to insufficient reporting of results in the clinical trials. The relatively small number of randomized controlled trials, few overlapping treatment arms, and variability in the randomized controlled trial features and in the endpoints studied complicate the formal comparison of therapies for relapsed/refractory follicular lymphoma. Additional well-designed randomized controlled trials are needed to fully understand the relative outcomes of older and more recently developed therapies.

Text mining applications in psychiatry: a systematic literature review.

The expansion of biomedical literature is creating the need for efficient tools to keep pace with increasing volumes of information. Text mining (TM) approaches are becoming essential to facilitate the automated extraction of useful biomedical information from unstructured text. We reviewed the applications of TM in psychiatry, and explored its advantages and limitations. A systematic review of the literature was carried out using the CINAHL, Medline, EMBASE, PsycINFO and Cochrane databases. In this review, 1103 papers were screened, and 38 were included as applications of TM in psychiatric research. Using TM and content analysis, we identified four major areas of application: (1) Psychopathology (i.e. observational studies focusing on mental illnesses) (2) the Patient perspective (i.e. patients' thoughts and opinions), (3) Medical records (i.e. safety issues, quality of care and description of treatments), and (4) Medical literature (i.e. identification of new scientific information in the literature). The information sources were qualitative studies, Internet postings, medical records and biomedical literature. Our work demonstrates that TM can contribute to complex research tasks in psychiatry. We discuss the benefits, limits, and further applications of this tool in the future. Copyright © 2015 John Wiley & Sons, Ltd.

Randomized controlled trials in relapsed/refractory chronic lymphocytic leukemia: a systematic review and meta-analysis.

This systematic literature review with meta-analysis was conducted on the clinical efficacy and safety of interventions used in the treatment of chronic lymphocytic leukemia (CLL). We systematically searched databases (PubMed, Cochrane Library, and Embase; 1997 to August 2, 2012), conference abstracts, bibliographic reference lists, recent reviews, and Clinicaltrials.gov. Primary efficacy outcomes were objective response rate, progression-free survival, and overall survival. Safety end points were Grade 3/4 toxicities, serious adverse events, withdrawals because of toxicity, and deaths due to toxicity. Studies were selected if they were randomized controlled trials (RCTs) reporting on the efficacy or safety of relapsed or refractory CLL and if outcomes for CLL were reported separately from trials that included other lymphoid neoplasms. We used the Bucher method for conducting adjusted indirect comparisons within a meta-analysis. We identified 6 RCTs of pharmacologic treatment for relapsed/refractory CLL. The most common drugs investigated (alone or in combination) were fludarabine and cyclophosphamide. When reported, median overall survival ranged from 27.3 to 52.9 months, and overall response rate from 58% to 82%. Although meta-analysis of efficacy results was considered, details are not presented because only 3 studies qualified and the common comparator treatment was not clinically relevant. The relatively small number of RCTs, few overlapping treatment arms, and variability in end points studied make it difficult to formally compare therapies for relapsed/refractory CLL. Significant variability in RCT features presents a further challenge to meaningful comparisons. Additional well-designed RCTs are needed to fully understand the relative efficacy and safety of older and more recently developed therapies.

Clinical efficacy and safety in relapsed/refractory mantle cell lymphoma: a systematic literature review.

A systematic literature review was performed to collect and review information on the clinical efficacy and safety of treatments for relapsed/refractory (R/R) mantle cell lymphoma (MCL), with a meta-analysis, if possible. PubMed, Embase, and the Cochrane Library were searched for studies published in English from January 1, 1997, to August 2, 2012. Conference proceedings, bibliographic reference lists of included articles, recent reviews, and ClinicalTrials.gov were searched for phase II to IV studies displaying results. Studies were included if they reported on patients with R/R MCL who were ineligible to receive high-dose chemotherapy with stem cell transplant. Studies of patients with several non-Hodgkin lymphoma subtypes were only included if they reported MCL outcomes separately. We identified 59 studies in R/R MCL. Forty distinct treatment regimens were evaluated. Thirty studies included more than 15 patients with R/R MCL. Six studies were comparative (including 5 randomized controlled trials [RCTs]); 53 were single-arm. There were no common treatments among the RCTs; therefore, a meta-analysis was not feasible. Thirty-one of 59 studies reported baseline data for patients with R/R MCL. Of the 30 studies with > 15 patients with R/R MCL, 30 reported overall response rate data, 14 reported progression-free survival (PFS), and 12 reported overall survival (OS). The small number of RCTs in R/R MCL precludes identifying an optimal treatment. Small sample sizes, infrequent reporting of OS and PFS, and limited information on patient characteristics made a comparison of results difficult. High-quality comparative studies of novel therapies that have the potential to demonstrate OS advantages in R/R MCL are needed.

Clinical efficacy and safety in relapsed/refractory diffuse large B-cell lymphoma: a systematic literature review.

This systematic literature review was designed to assess information on the clinical efficacy and safety of interventions used in the treatment of refractory or relapsed diffuse large B-cell lymphoma (R/R DLBCL) and to perform a meta-analysis if possible. We searched databases (PubMed, EMBASE, and Cochrane Library for articles from 1997 to August 2, 2012 reported in English), conference abstracts, bibliographic reference lists, and the ClinicalTrials.gov database for phase II to IV studies with results. Studies had to report on patients with R/R DLBCL who were not eligible to receive high-dose therapy (HDT) with stem cell transplantation (SCT) (autologous or allogeneic). Mixed-type non-Hodgkin lymphoma (NHL) studies were required to report R/R DLBCL outcomes separately. We identified 55 studies that presented outcomes data separately for patients with R/R DLBCL. Of 7 comparative studies, only 4 were randomized controlled trials (RCTs). In the 2 RCTs with a common regimen, the patient populations differed too greatly to perform a valid meta-analysis. The 48 single-arm studies identified were typically small (n < 50 in most), with 31% reporting median progression-free survival (PFS) or overall survival (OS) specifically for the R/R DLBCL population. In these studies, median OS ranged from 4 to 13 months. The small number of RCTs in R/R DLBCL precludes identifying optimal treatments. Small sample size, infrequent reporting of OS and PFS separated by histologic type, and limited information on patient characteristics also hinder comparison of results. Randomized studies are needed to demonstrate which current therapies have advantages for improving survival and other important clinical outcomes in patients with R/R DLBCL.

Impact of reporting bias in network meta-analysis of antidepressant placebo-controlled trials.

BACKGROUND: Indirect comparisons of competing treatments by network meta-analysis (NMA) are increasingly in use. Reporting bias has received little attention in this context. We aimed to assess the impact of such bias in NMAs. METHODS: We used data from 74 FDA-registered placebo-controlled trials of 12 antidepressants and their 51 matching publications. For each dataset, NMA was used to estimate the effect sizes for 66 possible pair-wise comparisons of these drugs, the probabilities of being the best drug and ranking the drugs. To assess the impact of reporting bias, we compared the NMA results for the 51 published trials and those for the 74 FDA-registered trials. To assess how reporting bias affecting only one drug may affect the ranking of all drugs, we performed 12 different NMAs for hypothetical analysis. For each of these NMAs, we used published data for one drug and FDA data for the 11 other drugs. FINDINGS: Pair-wise effect sizes for drugs derived from the NMA of published data and those from the NMA of FDA data differed in absolute value by at least 100% in 30 of 66 pair-wise comparisons (45%). Depending on the dataset used, the top 3 agents differed, in composition and order. When reporting bias hypothetically affected only one drug, the affected drug ranked first in 5 of the 12 NMAs but second (n = 2), fourth (n = 1) or eighth (n = 2) in the NMA of the complete FDA network. CONCLUSIONS: In this particular network, reporting bias biased NMA-based estimates of treatments efficacy and modified ranking. The reporting bias effect in NMAs may differ from that in classical meta-analyses in that reporting bias affecting only one drug may affect the ranking of all drugs.