Search

Shawn D Aaron,1 Andrea S Gershon,2 Yuan Gao,1 Jenna Yang,1 GA Whitmore1,3 On behalf of the Canadian Respiratory Research Network 1Ottawa Hospital Research Institute, University of Ottawa, Ottawa, 2Sunnybrook Research Institute, University of Toronto, ON, 3Desautels Faculty of Management, McGill University, Montreal, QC, Canada Purpose: Studies suggest that COPD prevalence may vary between countries. We conducted an ecological study of data from COPD prevalence articles to assess the influence of differences in country-level risk factors on COPD prevalence. Patients and methods: Our study covered English language articles published during 2003–2014. Qualified articles used spirometry to assess COPD prevalence and used representative samples from national or subnational populations. Stepwise binomial regression was used to analyze associations between study- and country-level factors and COPD prevalence. Results: Eighty articles provided 1,583 measures of COPD prevalence for subjects in different sex, age, and smoking categories for 112 districts in 41 countries. Adjusted prevalence rates for COPD were significantly lower for Australia/New Zealand and the Mediterranean and significantly higher for Latin America, compared to North America, Southeast Asia, and Northern Europe. Country-level socioeconomic development variables had an uneven and mixed association with COPD prevalence. High elevation above sea level was shown to be a protective factor for COPD. Study-level variables for the established risk factors of sex, age, and smoking explained 64% of variability in COPD prevalence. Country-level risk factors raised the explanatory power to 72%. Approximately 28% of worldwide variability in COPD prevalence remained unexplained. Conclusion: Our study suggests that COPD prevalence varies across world regions, even after adjustment for established risk factors. Major country-level risk factors contributing to the worldwide epidemic of COPD remain to be investigated. Keywords: country effects, ecological study, epidemiology, lung disease, risk factors, spirometry

Background: We investigated dyspnea; its associated risk factors; and its impact on health care utilization, quality of life, and work productivity in adults with undiagnosed respiratory symptoms., Research Question: What is the impact of dyspnea in adults with undiagnosed respiratory symptoms?, Study Design and Methods: This population-based study included 2,857 adults who were experiencing respiratory symptoms. These individuals had not been previously diagnosed with any lung conditions and were recruited from 17 Canadian centers using random digit dialing. Each participant underwent spirometry testing both before and after using a bronchodilator to determine if they met the diagnostic criteria for COPD, asthma, or preserved ratio impaired spirometry (PRISm), or if their spirometry results were normal. An age-matched control group (n = 231) was similarly recruited using random digit dialing. A dyspnea impact assessment score from 0 to 100 was produced using questions from the COPD Assessment Test and St. George's Respiratory questionnaire., Results: Individuals with PRISm (n = 172) reported more impactful dyspnea (mean score, 63.0; 95% CI, 59.5-66.4) than those with undiagnosed asthma (n = 265; mean score, 56.6; 95% CI, 53.9-59.3) or undiagnosed COPD (n = 330; mean score, 57.5; 95% CI, 55.1-59.9). All groups reported significantly more impactful dyspnea than the control group (mean score, 13.8; 95% CI, 11.8-15.7). Patient-specific risk factors including age, sex, BMI, smoking, and comorbidities explained 20.6% of the variation in dyspnea. An additional 12.4% of the variation was explained by disease classification and another 1.7% by the severity of lung function impairment assessed with spirometry. After adjusting for age, sex, and BMI, greater dyspnea impact was associated with increased health care utilization, lower quality of life, and reduced work productivity., Interpretation: Our findings showed that in community-based adults with undiagnosed respiratory symptoms, those identified with PRISm experienced the greatest impact of dyspnea. Dyspnea imposes burdens on the health care system and is associated with impaired quality of life and work productivity., Competing Interests: Financial/Nonfinancial Disclosures None declared., (Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.)

Background: Many persons with chronic obstructive pulmonary disease (COPD) or asthma have not received a diagnosis, so their respiratory symptoms remain largely untreated., Methods: We used a case-finding method to identify adults in the community with respiratory symptoms without diagnosed lung disease. Participants who were found to have undiagnosed COPD or asthma on spirometry were enrolled in a multicenter, randomized, controlled trial to determine whether early diagnosis and treatment reduces health care utilization for respiratory illness and improves health outcomes. Participants were assigned to receive the intervention (evaluation by a pulmonologist and an asthma-COPD educator who were instructed to initiate guideline-based care) or usual care by their primary care practitioner. The primary outcome was the annualized rate of participant-initiated health care utilization for respiratory illness. Secondary outcomes included changes from baseline to 1 year in disease-specific quality of life, as assessed with the St. George Respiratory Questionnaire (SGRQ; scores range from 0 to 100, with lower scores indicating better health status); symptom burden, as assessed with the COPD Assessment Test (CAT; scores range from 0 to 40, with lower scores indicating better health status); and forced expiratory volume in 1 second (FEV 1 )., Results: Of 38,353 persons interviewed, 595 were found to have undiagnosed COPD or asthma and 508 underwent randomization: 253 were assigned to the intervention group and 255 to the usual-care group. The annualized rate of a primary-outcome event was lower in the intervention group than in the usual-care group (0.53 vs. 1.12 events per person-year; incidence rate ratio, 0.48; 95% confidence interval [CI], 0.36 to 0.63; P<0.001). At 12 months, the SGRQ score was lower than the baseline score by 10.2 points in the intervention group and by 6.8 points in the usual-care group (difference, -3.5 points; 95% CI, -6.0 to -0.9), and the CAT score was lower than the baseline score by 3.8 points and 2.6 points, respectively (difference, -1.3 points; 95% CI, -2.4 to -0.1). The FEV 1 increased by 119 ml in the intervention group and by 22 ml in the usual-care group (difference, 94 ml; 95% CI, 50 to 138). The incidence of adverse events was similar in the trial groups., Conclusions: In this trial in which a strategy was used to identify adults in the community with undiagnosed asthma or COPD, those who received pulmonologist-directed treatment had less subsequent health care utilization for respiratory illness than those who received usual care. (Funded by Canadian Institutes of Health Research; UCAP ClinicalTrials.gov number, NCT03148210.)., (Copyright © 2024 Massachusetts Medical Society.)

Rationale: A significant proportion of individuals with chronic obstructive pulmonary disease (COPD) and asthma remain undiagnosed. Objectives: The objective of this study was to evaluate symptoms, quality of life, healthcare use, and work productivity in subjects with undiagnosed COPD or asthma compared with those previously diagnosed, as well as healthy control subjects. Methods: This multicenter population-based case-finding study randomly recruited adults with respiratory symptoms who had no previous history of diagnosed lung disease from 17 Canadian centers using random digit dialing. Participants who exceeded symptom thresholds on the Asthma Screening Questionnaire or the COPD Diagnostic Questionnaire underwent pre- and post-bronchodilator spirometry to determine if they met diagnostic criteria for COPD or asthma. Two control groups, a healthy group without respiratory symptoms and a symptomatic group with previously diagnosed COPD or asthma, were similarly recruited. Measurements and Main Results: A total of 26,905 symptomatic individuals were interviewed, and 4,272 subjects were eligible. Of these, 2,857 completed pre- and post-bronchodilator spirometry, and 595 (21%) met diagnostic criteria for COPD or asthma. Individuals with undiagnosed COPD or asthma reported greater impact of symptoms on health status and daily activities, worse disease-specific and general quality of life, greater healthcare use, and poorer work productivity than healthy control subjects. Individuals with undiagnosed asthma had symptoms, quality of life, and healthcare use burden similar to those of individuals with previously diagnosed asthma, whereas subjects with undiagnosed COPD were less disabled than those with previously diagnosed COPD. Conclusions: Undiagnosed COPD or asthma imposes important, unmeasured burdens on the healthcare system and is associated with poor health status and negative effects on work productivity.

Background: Some patients with asthma demonstrate normal spirometry and remain undiagnosed without further testing., Objective: To determine clinical predictors of asthma in symptomatic adults with normal spirometry, and to generate a tool to help clinicians decide who should undergo bronchial challenge testing (BCT)., Methods: Using random-digit dialling and population-based case-finding, we recruited adults from the community with respiratory symptoms and no previous history of diagnosed lung disease. Participants with normal pre- and post-bronchodilator spirometry subsequently underwent BCT. Asthma was diagnosed in those with symptoms and a methacholine provocative concentration (PC 20 ) of < 8 mg/ml. Sputum and blood eosinophils, and exhaled nitric oxide were measured. Univariate analyses identified potentially predictive variables, which were then used to construct a multivariable logistic regression model to predict asthma. Model sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated., Results: Of 132 symptomatic individuals with normal spirometry, 34 (26%) had asthma. Of those ultimately diagnosed with asthma, 33 (97%) answered 'yes' to a question asking whether they experienced cough, chest tightness or wheezing provoked by exercise or cold air. Other univariate predictors of asthma included female sex, pre-bronchodilator FEV1 percentage predicted, and percent positive change in FEV1 post bronchodilator. A multivariable model containing these predictive variables yielded an AUC of 0.82 (95% CI: 0.72-0.91), a sensitivity of 82%, and a specificity of 66%. The model was used to construct a nomogram to advise clinicians which patients should be prioritized for BCT., Conclusions: Four readily available patient characteristics demonstrated a high sensitivity and AUC for predicting undiagnosed asthma in symptomatic adults with normal pre- and post-bronchodilator spirometry. These characteristics can potentially help clinicians to decide which individuals with normal spirometry should be investigated with bronchial challenge testing. However, further prospective validation of our decision tool is required., (© 2023. The Author(s).)

The progression of disease for an individual can be described mathematically as a stochastic process. The individual experiences a failure event when the disease path first reaches or crosses a critical disease level. This happening defines a failure event and a first hitting time or time-to-event, both of which are important in medical contexts. When the context involves explanatory variables then there is usually an interest in incorporating regression structures into the analysis and the methodology known as threshold regression comes into play. To date, most applications of threshold regression have been based on parametric families of stochastic processes. This paper presents a semiparametric form of threshold regression that requires the stochastic process to have only one key property, namely, stationary independent increments. As this property is frequently encountered in real applications, this model has potential for use in many fields. The mathematical underpinnings of this semiparametric approach for estimation and prediction are described. The basic data element required by the model is a pair of readings representing the observed change in time and the observed change in disease level, arising from either a failure event or survival of the individual to the end of the data record. An extension is presented for applications where the underlying disease process is unobservable but component covariate processes are available to construct a surrogate disease process. Threshold regression, used in combination with a data technique called Markov decomposition, allows the methods to handle longitudinal time-to-event data by uncoupling a longitudinal record into a sequence of single records. Computational aspects of the methods are straightforward. An array of simulation experiments that verify computational feasibility and statistical inference are reported in an online supplement. Case applications based on longitudinal observational data from The Osteoarthritis Initiative (OAI) study are presented to demonstrate the methodology and its practical use., (© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Background: It remains unclear why some symptomatic individuals with asthma or COPD remain undiagnosed. Here, we compare patient and physician characteristics between symptomatic individuals with obstructive lung disease (OLD) who are undiagnosed and individuals with physician-diagnosed OLD., Methods: Using random-digit dialling and population-based case finding, we recruited 451 participants with symptomatic undiagnosed OLD and 205 symptomatic control participants with physician-diagnosed OLD. Data on symptoms, quality of life and healthcare utilisation were analysed. We surveyed family physicians of participants in both groups to elucidate differences in physician practices that could contribute to undiagnosed OLD., Results: Participants with undiagnosed OLD had lower mean pre-bronchodilator forced expiratory volume in 1 s percentage predicted compared with those who were diagnosed (75.2% versus 80.8%; OR 0.975, 95% CI 0.963-0.987). They reported greater psychosocial impacts due to symptoms and worse energy and fatigue than those with diagnosed OLD. Undiagnosed OLD was more common in participants whose family physicians were practising for >15 years and in those whose physicians reported that they were likely to prescribe respiratory medications without doing spirometry. Undiagnosed OLD was more common among participants who had never undergone spirometry (OR 10.83, 95% CI 6.18-18.98) or who were never referred to a specialist (OR 5.92, 95% CI 3.58-9.77). Undiagnosed OLD was less common among participants who had required emergency department care (OR 0.44, 95% CI 0.20-0.97)., Conclusions: Individuals with symptomatic undiagnosed OLD have worse pre-bronchodilator lung function and present with greater psychosocial impacts on quality of life compared with their diagnosed counterparts. They were less likely to have received appropriate investigations and specialist referral for their respiratory symptoms., Competing Interests: Conflict of interest: M. Cherian reports no conflict of interest. K.M.A. Magner reports no conflict of interest. G.A. Whitmore reports no conflict of interest. K.L. Vandemheen reports no conflict of interest. C. Bergeron reports grants, contracts or honoraria from Novartis, Biohaven, AstraZeneca, Sanofi, Valeo and Grifols; and advisory board participation Sanofi, AstraZeneca, GlaxoSmithKline, Takeda and Valeo. L-P. Boulet reports grants, contracts, consulting fees or honoraria from Amgen, AstraZeneca, GlaxoSmithKline, Merck, Sanofi-Regeneron, Covis and Novartis; royalties or licences from UptoDate and Taylor & Francis; leadership roles with the Global Initiative for Asthma (GINA), Global Asthma Association (INTERASMA) and Canadian Thoracic Society; and holds the Laval University Chair on Knowledge Transfer, Prevention and Education in Respiratory and Cardiovascular Health. A. Cote reports grants, contracts, consulting fees or honoraria from GlaxoSmithKline, AstraZeneca, Valeo, Sanofi-Regeneron and Covis; and advisory board participation with AstraZeneca, Sanofi and Valeo. S.K. Field reports grants, contracts, consulting fees or honoraria from Bayer, Insmed, Merck, Valeo and GlaxoSmithKline. E. Penz reports grants, contracts, consulting fees or honoraria from the Saskatchewan Health Research Foundation, CIHR, Respiratory Research Centre, SCPOR, AstraZeneca, Saskatchewan Cancer Agency, GlaxoSmithKline, Sanofi, Genzyme, ICBEM and Boehringer Ingelheim; and leadership roles with the Canadian Thoracic Society COPD Assembly, CIHR Institute Advisory Board and Youth4Change. R.A. McIvor reports no conflict of interest. C. Lemière repots grants, contracts, consulting fees or honoraria from GlaxoSmithKline, AstraZeneca, Sanofi and Novartis; and royalties or licences from UptoDate. S. Gupta reports no conflict of interest. I. Mayers reports no conflict of interest. M. Bhutani reports grants, contracts, consulting fees, support for travel or honoraria from the CIHR, AstraZeneca, GlaxoSmithKline, Novartis, Grifols, Sanofi, Covis, Valeo, Lung Association of Saskatchewan, Canadian Thoracic Society and Lung Association of Alberta and Northwest Territories; and leadership roles with the Canadian Thoracic Society and Alberta Health Services. P. Hernandez reports grants, contracts, support for travel or honoraria from the CIHR, Cyclomedia, Boehringer Ingelheim, Vertex, Grifols, AstraZeneca, Boehringer Ingelheim, Janssen and Canadian Thoracic Society; advisory board participation with Acceleron, AstraZeneca, Boehringer Ingelheim, Covis, GlaxoSmithKline, Grifols, Janssen, Novartis, Sanofi, Takeda and Valeo; and leadership roles with the Canadian Thoracic Society. M.D. Lougheed reports grants, contracts or honoraria from the CIHR, AstraZeneca, GlaxoSmithKline, Canadian Thoracic Society and MDBriefcase; advisory board participation with AstraZeneca; leadership roles with the Canadian Thoracic Society, Health Quality Ontario and the Lung Association. C.J. Licskai reports no conflict of interest. T. Azher reports no conflict of interest. M. Ainslie reports no conflict of interest. N. Ezer reports grants, contracts or honoraria from the CIHR, Rossy Cancer Network, Covis Pharma, GlaxoSmithKline, AstraZeneca, Fédération des Omnipracticiens du Québec and Médecin du Québec Magazine; advisory board participation with GlaxoSmithKline; leadership role with the Quebec Ministry of Health Lung Cancer Screening Implementation Committee; and receipt of study drug from Covis. S. Mulpuru reports no conflict of interest. S.D. Aaron reports honoraria from AstraZeneca, Sanofi and GlaxoSmithKline; and advisory board participation with AstraZeneca, GlaxoSmithKline and Sanofi., (Copyright ©The authors 2023. For reproduction rights and permissions contact permissions@ersnet.org.)

Individuals in many observational studies and clinical trials for chronic diseases are enrolled well after onset or diagnosis of their disease. Times to events of interest after enrollment are therefore residual or left-truncated event times. Individuals entering the studies have disease that has advanced to varying extents. Moreover, enrollment usually entails probability sampling of the study population. Finally, event times over a short to moderate time horizon are often of interest in these investigations, rather than more speculative and remote happenings that lie beyond the study period. This research report looks at the issue of delayed entry into these kinds of studies and trials. Time to event for an individual is modelled as a first hitting time of an event threshold by a latent disease process, which is taken to be a Wiener process. It is emphasized that recruitment into these studies often involves length-biased sampling. The requisite mathematics for this kind of sampling and delayed entry are presented, including explicit formulas needed for estimation and inference. Restricted mean survival time (RMST) is taken as the clinically relevant outcome measure. Exact parametric formulas for this measure are derived and presented. The results are extended to settings that involve study covariates using threshold regression methods. Methods adapted for clinical trials are presented. An extensive case illustration for a clinical trial setting is then presented to demonstrate the methods, the interpretation of results, and the harvesting of useful insights. The closing discussion covers a number of important issues and concepts., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Background: Many people with asthma and COPD remain undiagnosed. We developed and validated a new case-finding questionnaire to identify symptomatic adults with undiagnosed obstructive lung disease., Methods: Adults in the community with no prior history of physician-diagnosed lung disease who self-reported respiratory symptoms were contacted via random-digit dialling. Pre- and post-bronchodilator spirometry was used to confirm asthma or COPD. Predictive questions were selected using multinomial logistic regression with backward elimination. Questionnaire performance was assessed using sensitivity, predictive values and area under the receiver operating characteristic curve (AUC). The questionnaire was assessed for test-retest reliability, acceptability and readability. External validation was prospectively conducted in an independent sample and predictive performance re-evaluated., Results: A 13-item Undiagnosed COPD and Asthma Population Questionnaire (UCAP-Q) case-finding questionnaire to predict undiagnosed asthma or COPD was developed. The most appropriate risk cut-off was determined to be 6% for either disease. Applied to the derivation sample (n=1615), the questionnaire yielded a sensitivity of 92% for asthma and 97% for COPD; specificity of 17%; and an AUC of 0.69 (95% CI 0.64-0.74) for asthma and 0.82 (95% CI 0.78-0.86) for COPD. Prospective validation using an independent sample (n=471) showed sensitivities of 93% and 92% for asthma and COPD, respectively; specificity of 19%; with AUCs of 0.70 (95% CI 0.62-0.79) for asthma and 0.81 (95% CI 0.74-0.87) for COPD. AUCs for UCAP-Q were higher compared to AUCs for currently recommended case-finding questionnaires for asthma or COPD., Conclusions: The UCAP-Q demonstrated high sensitivities and AUCs for identifying undiagnosed asthma or COPD. A web-based calculator allows for easy calculation of risk probabilities for each disease., Competing Interests: Conflict of interest: C. Huynh reports no conflicts of interest. G.A. Whitmore reports no conflicts of interest. K.L. Vandemheen reports no conflicts of interest. J.M. FitzGerald reports no conflicts of interest. C. Bergeron reports no conflicts of interest. L-P. Boulet reports receiving grants, consulting fees or honoraria from Amgen, AstraZeneca, GlaxoSmithKline, Merck, Novartis and Sanofi-Regeneron. A. Cote reports receiving honoraria from GlaxoSmithKline, AstraZeneca, Sanofi and Covis. S.K. Field reports receiving consulting fees or honoraria from Merck, GlaxoSmithKline, Novartis and Boehringer Ingelheim. E. Penz reports receiving honoraria from AstraZeneca, GlaxoSmithKline, Novartis, ICEBM and Boehringer Ingelheim. R.A. McIvor reports no conflicts of interest. C. Lemière reports receiving consulting fees or honoraria from Sanofi, TEVA, GlaxoSmithKline and AstraZeneca. S. Gupta reports no conflicts of interest. I. Mayers reports no conflicts of interest. M. Bhutani reports payments or honoraria from AZ, GSK, Novartis, Grifols, Sanofi, Covis and Valeo. P. Hernandez reports payments or honoraria from AZ, GSK, Novartis and Valeo. M.D. Lougheed reports receiving grants from AZ and GSK. C.J. Licskai reports receiving honoraria from AstraZeneca, GlaxoSmithKline, Novartis and Boehringer Ingelheim. T. Azher reports no conflicts of interest. M. Ainslee reports receiving honoraria from Boehringer Ingelheim. I. Fraser reports no conflicts of interest. M. Mahdavian reports no conflicts of interest. G.G. Alvarez reports no conflicts of interest. T. Kendzerska reports speaker honoraria from AstraZeneca. S.D. Aaron reports sitting on advisory boards and honoraria payments from GlaxoSmithKline, Sanofi and AstraZeneca., (Copyright ©The authors 2022. For reproduction rights and permissions contact permissions@ersnet.org.)

Background: The actual burden of COPD and asthma may be much higher than appreciated, since a large proportion of individuals are not diagnosed. Our study objective was to compare health care utilization, burden of symptoms and quality of life in subjects with self-reported respiratory symptoms who were subsequently found to have undiagnosed airflow obstruction compared to those having no airflow obstruction., Methods: This cross-sectional case-finding study used data from the Undiagnosed COPD and Asthma Population (UCAP) study. Adult subjects with respiratory symptoms who had no history of diagnosed lung disease were recruited in a two-step case-finding process using random digit-dialling of land lines and cell phones located within a 90-min radius of 16 Canadian study sites. Participants were assessed for COPD, asthma or no airflow obstruction using pre- and post-bronchodilator spirometry based on American Thoracic Society diagnostic criteria., Results: 1660 participants were recruited, of these 1615 had adequate spirometry and 331 (20.5%) subjects met spirometry criteria for undiagnosed asthma or COPD. Subjects with undiagnosed asthma or COPD had increased respiratory symptoms as assessed by the COPD Assessment Test (CAT), and higher St. George's Respiratory Questionnaire (SGRQ) scores indicating worse health-related quality of life, compared to subjects with no airflow obstruction. No between-group differences were found in health care utilization or work or school absenteeism., Conclusion: Undiagnosed asthma and COPD are common in Canadian adults experiencing breathing problems and are associated with a greater burden of symptoms and poorer health-related quality of life. These results suggest that patients may benefit from early identification and treatment of undiagnosed asthma and COPD., Competing Interests: Declaration of competing interest All authors in this paper declare that they have no conflict of interest., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

Background: ∼5-10% of adults may have undiagnosed airflow obstruction. The objective of this study was to develop a population-based case-finding strategy to assess the prevalence of undiagnosed airflow obstruction (asthma or COPD) amongst adults with respiratory symptoms in Canada., Methods: Adults without a previous history of asthma, COPD or lung disease were recruited using random digit-dialling and asked if they had symptoms of dyspnoea, cough, sputum or wheeze within the past 6 months. Those who answered affirmatively completed the Asthma Screening Questionnaire (ASQ), COPD-Diagnostic Questionnaire (COPD-DQ) and COPD Assessment Test (CAT). Those with an ASQ score of ≥6 or a COPD-DQ score of ≥20 underwent pre- and post-bronchodilator spirometry to diagnose asthma or COPD., Results: 12 117 individuals were contacted at home and assessed for study eligibility. Of the 1260 eligible individuals, 910 (72%) enrolled and underwent spirometry. Ultimately, 184 subjects (20% of those enrolled) had obstructive lung disease (73 asthma and 111 COPD). Individuals found to have undiagnosed asthma or COPD had more severe respiratory symptoms and impaired quality of life compared with those without airflow obstruction. The ASQ, COPD-DQ, and CAT had ROC areas for predicting undiagnosed asthma or COPD of 0.49, 0.64 and 0.56, respectively. Four descriptive variables (age, BMI, sex and pack-years smoked) produced better receiver operating characteristic (ROC) values than the questionnaires (ROC area=0.68)., Conclusion: 20% of randomly selected individuals who report respiratory symptoms in Canada have undiagnosed airflow obstruction due to asthma or COPD. Questionnaires could exclude subjects at low risk but lack the ability to accurately find subjects with undiagnosed disease., Competing Interests: Conflict of interest: M. Preteroti has nothing to disclose. Conflict of interest: G.A. Whitmore has nothing to disclose. Conflict of interest: K.L. Vandemheen has nothing to disclose. Conflict of interest: J.M. FitzGerald has nothing to disclose. Conflict of interest: C. Lemiere reports grants and personal fees for advisory board work, consultancy and lectures from AstraZeneca, grants and personal fees for advisory board work and lectures from TEVA Innovation, personal fees for advisory board work and consultancy from GlaxoSmithKline, personal fees for advisory board work from Sanofi, outside the submitted work. Conflict of interest: L-P. Boulet reports research grants for participation in multicentre studies from AstraZeneca, Boston Scientific, GlaxoSmithKline, Hoffman La Roche, Novartis, Ono Pharma, Sanofi and Takeda, support for research projects introduced by the investigator from AstraZeneca, Boehringer Ingelheim, GlaxoSmithKline, Merck and Takeda, fees for consulting and advisory boards from AstraZeneca, Novartis and Methapharm, nonprofit grants for production of educational materials from AstraZeneca, Boehringer Ingelheim, GlaxoSmithKline, Merck and Novartis, conference fees from AstraZeneca, GlaxoSmithKline, Merck and Novartis, support for participation in conferences and meetings from Novartis and Takeda. Conflict of interest: E. Penz reports CIHR funding of UCAP study, during the conduct of the study; grants, personal fees for advisory board work, consultancy and lectures, and non-financial (travel) support from AstraZeneca, personal fees for advisory board work and non-financial (travel) support from GlaxoSmithKline and Boehringer Ingelheim, outside the submitted work. Conflict of interest: S.K. Field reports grants from GSK, InsMed, Novartis and Boehringer Ingelheim, outside the submitted work. Conflict of interest: S. Gupta has nothing to disclose. Conflict of interest: R.A. McIvor has nothing to disclose. Conflict of interest: I. Mayers has nothing to disclose. Conflict of interest: P. Hernandez reports grants from CIHR, during the conduct of the study; personal fees for consultancy from Actelion, GlaxoSmithKline, Novartis, Sanofi and Teva, personal fees for consultancy and educational activities from AstraZeneca, grants and personal fees for consultancy and educational activities from Boehringer Ingelheim, grants from Cyclomedica, Grifols and Prometic, outside the submitted work. Conflict of interest: D. Lougheed reports grants from AstraZeneca, GlaxoSmithKline, Hoffman LaRoche Ltd, Novartis, Government of Ontario's Innovation Fund, Allergen NCE, Janssen, Canadian Institutes of Health Research, Manitoba Workers Compensation Board and Ontario Lung Association/Canada Health Infoway, grants and honoraria for educational activities from Ontario Lung Association, honoraria for educational activities from Canadian Thoracic Society, honoraria for advisory board work from AstraZeneca PRECISION Program, outside the submitted work; and is the nominated Canadian Thoracic Society representative on the Canadian Lung Association's Board of Directors. Conflict of interest: M. Ainslie has nothing to disclose. Conflict of interest: C. Licskai reports grants and personal fees from AstraZeneca, Boehringer Ingelheim, Novartis and Pfizer, personal fees from GSK, outside the submitted work. Conflict of interest: T. Azher has nothing to disclose. Conflict of interest: I. Fraser has nothing to disclose. Conflict of interest: M. Madavian reports personal fees for lectures from AstraZeneca, personal fees for lectures and non-financial (drug sample) support from Novartis and Boehringer Ingelheim, non-financial (drug sample) support from GSK, outside the submitted work. Conflict of interest: S.D. Aaron has nothing to disclose., (Copyright ©ERS 2020.)

Introduction: We aimed to develop a clinical tool for predicting 1- and 2-year risk of death for patients with cystic fibrosis (CF). The model considers patients' overall health status as well as risk of intermittent shock events in calculating the risk of death., Methods: Canadian CF Registry data from 1982 to 2015 were used to develop a predictive risk model using threshold regression. A 2-year risk of death estimated conditional probability of surviving the second year given survival for the first year. UK CF Registry data from 2007 to 2013 were used to externally validate the model., Results: The combined effect of CF chronic health status and CF intermittent shock risk provided a simple clinical scoring tool for assessing 1-year and 2-year risk of death for an individual CF patient. At a threshold risk of death of ≥20%, the 1-year model had a sensitivity of 74% and specificity of 96%. The area under the receiver operating curve (AUC) for the 2-year mortality model was significantly greater than the AUC for a model that predicted survival based on forced expiratory volume in 1 s <30% predicted (AUC 0.95 versus 0.68 respectively, p<0.001). The Canadian-derived model validated well with the UK data and correctly identified 79% of deaths and 95% of survivors in a single year in the UK., Conclusions: The prediction models provide an accurate risk of death over a 1- and 2-year time horizon. The models performed equally well when validated in an independent UK CF population., Competing Interests: Conflict of interest: S. Stanojevic has nothing to disclose. Conflict of interest: J. Sykes has nothing to disclose. Conflict of interest: A.L. Stephenson has nothing to disclose. Conflict of interest: S.D. Aaron has nothing to disclose. Conflict of interest: G.A. Whitmore has nothing to disclose., (Copyright ©ERS 2019.)

Rationale: Patients with uncontrolled, persistent asthma can show substantial health improvements when administered placebo. Objectives: We analyzed five randomized, placebo-controlled clinical trials that assessed subjects with uncontrolled, persistent asthma to determine the magnitudes of placebo effects across different clinical outcomes. Methods: Placebo effects for objective asthma-related outcomes, healthcare utilization outcomes, and patient-reported outcomes were estimated, with adjustments for regression to the mean. Results: Statistically significant improvements in all clinical outcomes were seen in patients randomized to placebo across all trials. Placebo effects were largest for healthcare utilization outcomes, including exacerbations (median reduction, 0.44 events/yr; 31% risk reduction; range, 19-56%), emergency department visits (median reduction, 0.19 events/yr; 50% risk reduction; range, 36-82%), and hospitalizations for asthma (median reduction, 0.26 events/yr; 66% risk reduction; range, 61-74%). Patient-reported outcomes exhibited intermediate placebo effects. Median improvements in the Asthma Control Questionnaire and St. George's Respiratory Questionnaire scores in placebo-treated patients were 0.53 units (25% improvement; range, 18-30%) and 8.3 units (19.5% improvement; range 19-20%), respectively. Forced expiratory volume in 1 second exhibited the smallest relative placebo effects (median increase, 77 ml; 4.2% improvement; range, 3.4-4.9%). Subgroup analyses did not reveal patient subgroups that were more susceptible to placebo effects. Pre- and postrandomization counts for asthma exacerbations showed patterns consistent with the expected negative binomial distribution except for significant departures in prerandomization exacerbations for two trials. Conclusions: Patients with uncontrolled asthma derived consistent benefit from randomization to placebo. Observed placebo effects may represent beneficial effects of both sham therapy and a structured asthma regimen dictated by the study protocol. In the case of healthcare utilization outcomes, recall errors in self-reported healthcare events may have introduced biases that inflated placebo effect estimates.

Rationale: The reliability of using between-visit variation in forced expiratory volume in 1 second (FEV 1 ) to diagnose asthma is understudied, and hence uncertain., Objective: To determine whether FEV 1 variability measured over recurrent visits is significantly associated with a diagnosis of current asthma., Methods: Randomly selected adults (N = 964) with a history of physician-diagnosed asthma were studied from 2005 to 2007 and from 2012 to 2016. A diagnosis of current asthma was confirmed in those participants who exhibited bronchial hyperresponsiveness to methacholine and/or acute worsening of asthma symptoms while being weaned off asthma medications. Regression analyses and receiver operating curves were used to evaluate the ability of between-visit FEV 1 variability to diagnose asthma., Results: A current diagnosis of asthma was confirmed in 584 of 964 participants (60%). Between-visit absolute variability in FEV 1 was significantly greater in those in whom current asthma was confirmed, compared with those in whom current asthma was ruled out (7.3% vs. 4.8%; mean difference between the two groups, 2.5%; 95% confidence interval, 1.7-3.3%). However, a 12% and 200-ml between-visit variation in FEV 1 , which is the diagnostic threshold recommended by Global Initiative for Asthma, exhibited a sensitivity of only 0.17 and a specificity of 0.94 for confirming current asthma. A between-visit absolute variability in FEV 1  ≥ 12% and 200 ml increased the pretest probability of asthma from 60% to a posttest probability of 81%., Conclusions: A 12% and 200-ml between-visit variation in FEV 1 , if present, has reasonably good specificity for diagnosing asthma, but has poor sensitivity compared with bronchial challenge testing. Between-visit variability in FEV 1 is a relatively unhelpful test to establish a diagnosis of asthma.

Rationale: Chronic obstructive pulmonary disease (COPD) is a chronic, progressive disease, and reversal of COPD diagnosis is thought to be uncommon., Objectives: To determine whether a spirometric diagnosis of mild or moderate COPD is subject to variability and potential error., Methods: We examined two prospective cohort studies that enrolled subjects with mild to moderate post-bronchodilator airflow obstruction. The Lung Health Study (n = 5,861 subjects; study duration, 5 yr) and the Canadian Cohort of Obstructive Lung Disease (CanCOLD) study (n = 1,551 subjects; study duration, 4 yr) were examined to determine frequencies of (1) diagnostic instability, represented by how often patients initially met criteria for a spirometric diagnosis of COPD but then crossed the diagnostic threshold to normal and then crossed back to COPD over a series of annual visits, or vice versa; and (2) diagnostic reversals, defined as how often an individual's COPD diagnosis at the study outset reversed to normal by the end of the study., Measurements and Main Results: Diagnostic instability was common and occurred in 19.5% of the Lung Health Study subjects and 6.4% of the CanCOLD subjects. Diagnostic reversals of COPD from the beginning to the end of the study period occurred in 12.6% and 27.2% of subjects in the Lung Health Study and CanCOLD study, respectively. The risk of diagnostic instability was greatest for subjects whose baseline FEV 1 /FVC value was closest to the diagnostic threshold, and the risk of diagnostic reversal was greatest for subjects who quit smoking during the study., Conclusions: A single post-bronchodilator spirometric assessment may not be reliable for diagnosing COPD in patients with mild to moderate airflow obstruction at baseline.

Background: We previously identified factors associated with a greater risk of death post-transplant. The purpose of this study was to develop a clinical tool to estimate the risk of death after transplant based on pre-transplant variables., Methods: We utilized the Canadian CF registry to develop a nomogram that incorporates pre-transplant clinical measures to assess post-lung transplant survival. The 1-, 3-, and 5-year survival estimates were calculated using Cox proportional hazards models., Results: Between 1988 and 2012, 539 adult Canadians with CF received a lung transplant with 208 deaths in the study period. Four pre-transplant factors most predictive of poor post-transplant survival were older age at transplantation, infection with B. cepacia complex, low FEV 1 percent predicted, and pancreatic sufficiency. A nonlinear relationship was found between risk of death and FEV 1 percent predicted, age at transplant, and BMI. We constructed a risk calculator based on our model to estimate the 1-, 3-, and 5-year probability of survival after transplant which is available online., Conclusions: Our risk calculator quantifies the risk of death associated with lung transplant using pre-transplant factors. This tool could aid clinicians and patients in the decision-making process and provide information regarding the timing of lung transplantation., (© 2017 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.)

Objectives: We constructed a statistical model to assess the risk of death for cystic fibrosis (CF) patients between scheduled annual clinical visits. Our model includes a CF health index that shows the influence of risk factors on CF chronic health and on the severity and frequency of CF exacerbations., Study Design and Setting: Our study used Canadian CF registry data for 3,794 CF patients born after 1970. Data up to 2010 were analyzed, yielding 44,390 annual visit records. Our stochastic process model postulates that CF health between annual clinical visits is a superposition of chronic disease progression and an exacerbation shock stream. Death occurs when an exacerbation carries CF health across a critical threshold. The data constitute censored survival data, and hence, threshold regression was used to connect CF death to study covariates. Maximum likelihood estimates were used to determine which clinical covariates were included within the regression functions for both CF chronic health and CF exacerbations., Results: Lung function, Pseudomonas aeruginosa infection, CF-related diabetes, weight deficiency, pancreatic insufficiency, and the deltaF508 homozygous mutation were significantly associated with CF chronic health status. Lung function, age, gender, age at CF diagnosis, P aeruginosa infection, body mass index <18.5, number of previous hospitalizations for CF exacerbations in the preceding year, and decline in forced expiratory volume in 1 second in the preceding year were significantly associated with CF exacerbations. When combined in one summative model, the regression functions for CF chronic health and CF exacerbation risk provided a simple clinical scoring tool for assessing 1-year risk of death for an individual CF patient. Goodness-of-fit tests of the model showed very encouraging results. We confirmed predictive validity of the model by comparing actual and estimated deaths in repeated hold-out samples from the data set and showed excellent agreement between estimated and actual mortality., Conclusion: Our threshold regression model incorporates a composite CF chronic health status index and an exacerbation risk index to produce an accurate clinical scoring tool for prediction of 1-year survival of CF patients. Our tool can be used by clinicians to decide on optimal timing for lung transplant referral., (Copyright © 2015 Elsevier Inc. All rights reserved.)

Background: Contemporary studies evaluating post-transplant survival are limited and often include data from single centers or selected sub-groups. The purpose of this study was to evaluate overall transplant survival and to identify risk factors associated with death after transplant., Methods: The Canadian Cystic Fibrosis Registry, a population-based cohort, was used to describe survival after lung transplant. Pre-transplant factors associated with post-transplant survival were estimated using Cox proportional hazards models., Results: Between 1988 and 2012, 580 patients received a lung transplant. In the entire cohort, post-lung transplant 1-year survival was 87.8%, 5-year survival was 66.7%, and 10-year survival was 50.2%. Median post-transplant survival was 3.3 years (95% confidence interval [CI] = 2.13-6.56) in patients infected with Burkholderia cepacia complex compared with 12.36 years (95% CI = 10.34-17.96) in patients without B cepacia infection (hazard ratio [HR] = 2.63, 95% CI = 2.0-3.44). After adjustment, there was a non-significant trend toward better post-transplant survival with increasing year of transplant (HR = 0.98, 95% CI = 0.96-1.00). Pancreatic sufficiency (HR = 2.13, 95% CI = 1.41-3.20) and age at transplant such that youngest and oldest had the poorest survival (p < 0.001) were significant negative predictors of survival. The risk of death after transplant for patients infected with B cepacia was highest within the first year (HR = 6.29, 95% CI = 3.87-10.21) but remained elevated >1 year after transplant (HR = 1.92, 95% CI = 1.33-2.77) compared with patients without B cepacia infection., Conclusions: After lung transplantation, 5-year survival in Canadians with CF is 67%, and 50% of patients live >10 years. Despite these impressive probabilities, age at transplant, pancreatic sufficiency and B cepacia infection remain important determinants of survival after lung transplantation., (Copyright © 2015 International Society for Heart and Lung Transplantation. Published by Elsevier Inc. All rights reserved.)

Previously established predictors of survival may no longer apply in the current era of cystic fibrosis (CF) care. Our objective was to identify risk factors associated with survival in a contemporary CF population. We used the Canadian CF Registry, a population-based cohort, to calculate median age of survival and summarise patient characteristics from 1990 to 2012. Clinical, demographic and geographical factors, and survival were estimated for a contemporary cohort (2000-2012) using Cox proportional hazards models. There were 5787 individuals in the registry between 1990 and 2012. Median survival age increased from 31.9 years (95% CI 28.3-35.2 years) in 1990 to 49.7 years (95% CI 46.1-52.2 years) in the most current 5-year window ending in 2012. Median forced expiratory volume in 1 s improved (p=0.04) and fewer subjects were malnourished (p<0.001) over time. Malnourished patients (hazard ratio (HR) 2.1, 95% CI 1.6-2.8), those with multiple exacerbations (HR 4.5, 95% CI 3.2-6.4) and women with CF-related diabetes (HR 1.8, 95% CI 1.2-2.7) were at increased risk of death. Life expectancy in Canadians with CF is increasing. Modifiable risk factors such as malnutrition and pulmonary exacerbations are associated with an increased risk of death. The sex gap in CF survival may be explained by an increased hazard for death in women with CF-related diabetes., (Copyright ©ERS 2015.)

Osteoporotic hip fractures in the elderly are associated with a high mortality in the first year following fracture and a high incidence of disability among survivors. We study first and second fractures of elderly women using data from the Study of Osteoporotic Fractures. We present a new conceptual framework, stochastic model, and statistical methodology for time to fracture. Our approach gives additional insights into the patterns for first and second fractures and the concomitant risk factors. Our modeling perspective involves a novel time-to-event methodology called threshold regression, which is based on the plausible idea that many events occur when an underlying process describing the health or condition of a person or system encounters a critical boundary or threshold for the first time. In the parlance of stochastic processes, this time to event is a first hitting time of the threshold. The underlying process in our model is a composite of a chronic degradation process for skeletal health combined with a random stream of shocks from external traumas, which taken together trigger fracture events., (Copyright © 2014 John Wiley & Sons, Ltd.)

Recurrent events are commonly encountered in the natural sciences, engineering, and medicine. The theory of renewal and regenerative processes provides an elegant mathematical foundation for idealized recurrent event processes. In real-world applications, however, the contexts tend to be complicated by a variety of practical intricacies, including observation schemes with different phase and data structures. This paper formulates a recurrent event process as a succession of independent and identically distributed first hitting times for a Wiener sample path as it passes through successive equally-spaced levels. We develop exact mathematical results for statistical inferences based on several observation schemes that include observation initiated at a renewal point, observation of a stationary process over a finite window, and other variants. We also consider inferences drawn from different data structures, including gap times between renewal points (or fragments thereof) and counts of renewal events occurring within an observation window. We explore the precision of estimates using simulated scenarios and develop empirical regression functions for planning the sample size of a recurrent event study. We demonstrate our results using data from a clinical trial for chronic obstructive pulmonary disease in which the recurrent events are successive exacerbations of the condition. The case study demonstrates how covariates can be incorporated into the analysis using threshold regression.

Background: The natural history and time course of the onset of exacerbation events of chronic obstructive pulmonary disease (COPD) is incompletely understood., Methods: A prospective cohort of 212 patients with COPD was monitored using daily symptom diaries for a median of 2.8 years to characterise the time course of COPD exacerbation onset. Decision rules based on weighted self-reported symptoms were used to define opening and closing of exacerbation events. Event time intervals were analysed and logistic regression was used to determine the effects of patient covariates on exacerbation events., Results: Patients recorded 4439 episodes of worsening respiratory symptoms from baseline; 2444 (55%) events resolved spontaneously and 1995 (45%) resulted in a COPD exacerbation. In 1115 of the 1995 COPD exacerbations (56%) the onset was sudden and the exacerbation threshold was crossed on the same day symptoms began. In contrast, 44% of exacerbations were characterised by gradual onset of symptoms (median duration from symptom onset to exacerbation 4 days). Patients who experienced sudden onset exacerbations had greater mean daily symptom scores (7.86 vs. 6.55 points, p<0.001), greater peak symptom scores (10.7 vs. 10.2 points, p=0.003), earlier peak symptoms (4.5 vs. 8.0 days, p<0.001) and shorter median recovery times back to baseline health status (11 vs. 13 days, p<0.001). Multivariable analysis showed that gradual onset exacerbations were statistically associated with a longer duration of exacerbation recovery (OR 1.28, 95% CI 1.06 to 1.54, p=0.010)., Conclusions: COPD exacerbations exhibit two distinct patterns-sudden and gradual onset. Sudden onset exacerbations are associated with increased respiratory symptoms but shorter exacerbation recovery times.

Birth weight and gestational age are important measures of a newborn's intrinsic health, serving both as outcome measures and explanatory variables in health studies. The measures are highly correlated but occasionally inconsistent. We anticipate that health researchers and other scientists would be helped by summary indexes of birth weight and gestational age that give more precise indications of whether the birth outcome is healthy or not. We propose a pair of indexes that we refer to as the birth normalcy index or BNI and birth discrepancy index or BDI. Both indexes are simple functions of birth weight and gestational age and in logarithmic form are orthogonal by construction. The BNI gauges whether the birth weight and gestational age combination are in a normal range. The BDI gauges whether birth weight and gestational age are consistent. We present a three-component mixture model for BNI, with the components representing premature, at-risk, and healthy births. The BNI distribution is derived from a stochastic model of fetal development proposed by Whitmore and Su (2007, Lifetime Data Analysis 13, 161-190) and takes the form of a mixture of inverse Gaussian distributions. We present a noncentral t-distribution as a model for BDI. BNI and BDI are also well suited for making comparisons of birth outcomes in different reference populations. A simple z-score and t-score are proposed for such comparisons. The BNI and BDI distributions can be estimated for births in any reference population of interest using threshold regression., (© 2011, The International Biometric Society.)

Objective: Respiratory exacerbations are a major source of morbidity in patients with chronic obstructive pulmonary disease (COPD). In this article, we model COPD health status as a formal stochastic process. A successful model will provide a suitable statistical structure for analysis of the effects of medical interventions on a patient's health status, and, possibly, offer new insights into the underlying disease process., Study Design and Setting: Our approach uses a regression methodology for time-to-event data called threshold regression (TR). We test the methodology on COPD data from a randomized clinical trial. Two TR models are studied: one based on a Poisson process and the other, a Wiener diffusion process., Results: Both models provide reasonably accurate fits to the clinical trial data. The insights offered by the fitted models are interpreted. Analysis of the clinical trial data set using these TR models revealed that patients who experienced multiple exacerbations showed a progressive acceleration in rate of exacerbations, and successive shortening of stable intervals between exacerbations., Conclusion: TR techniques allow for realistic modeling of the COPD health state. A hybrid Poisson/Wiener diffusion TR model that incorporates the causal determinants of disease operating in each patient may be preferable., (Copyright © 2010 Elsevier Inc. All rights reserved.)

Proportional hazards (PH) regression is a standard methodology for analyzing survival and time-to-event data. The proportional hazards assumption of PH regression, however, is not always appropriate. In addition, PH regression focuses mainly on hazard ratios and thus does not offer many insights into underlying determinants of survival. These limitations have led statistical researchers to explore alternative methodologies. Threshold regression (TR) is one of these alternative methodologies (see Lee and Whitmore, Stat Sci 21:501-513, 2006, for a review). The connection between PH regression and TR has been examined in previous published work but the investigations have been limited in scope. In this article, we study the connections between these two regression methodologies in greater depth and show that PH regression is, for most purposes, a special case of TR. We show two methods of construction by which TR models can yield PH functions for survival times, one based on altering the TR time scale and the other based on varying the TR boundary. We discuss how to estimate the TR time scale and boundary, with or without the PH assumption. A case demonstration is used to highlight the greater understanding of scientific foundations that TR can offer in comparison to PH regression. Finally, we discuss the potential benefits of positioning PH regression within the first-hitting-time context of TR regression.

Time-to-event data with time-varying covariates pose an interesting challenge for statistical modeling and inference, especially where the data require a regression structure but are not consistent with the proportional hazard assumption. Threshold regression (TR) is a relatively new methodology based on the concept that degradation or deterioration of a subject's health follows a stochastic process and failure occurs when the process first reaches a failure state or threshold (a first-hitting-time). Survival data with time-varying covariates consist of sequential observations on the level of degradation and/or on covariates of the subject, prior to the occurrence of the failure event. Encounters with this type of data structure abound in practical settings for survival analysis and there is a pressing need for simple regression methods to handle the longitudinal aspect of the data. Using a Markov property to decompose a longitudinal record into a series of single records is one strategy for dealing with this type of data. This study looks at the theoretical conditions for which this Markov approach is valid. The approach is called threshold regression with Markov decomposition or Markov TR for short. A number of important special cases, such as data with unevenly spaced time points and competing risks as stopping modes, are discussed. We show that a proportional hazards regression model with time-varying covariates is consistent with the Markov TR model. The Markov TR procedure is illustrated by a case application to a study of lung cancer risk. The procedure is also shown to be consistent with the use of an alternative time scale. Finally, we present the connection of the procedure to the concept of a collapsible survival model.

In epidemiological and clinical studies, time-to-event data often violate the assumptions of Cox regression due to the presence of time-dependent covariate effects and unmeasured risk factors. An alternative approach, which does not require proportional hazards, is to use a first hitting time model which treats a subject's health status as a latent stochastic process that fails when it reaches a threshold value. Although more flexible than Cox regression, existing methods do not account for unmeasured covariates in both the initial state and the rate of the process. To address this issue, we propose a Bayesian methodology that models an individual's health status as a Wiener process with subject-specific initial state and drift. Posterior inference proceeds via a Markov chain Monte Carlo methodology with data augmentation steps to sample the final health status of censored observations. We apply our method to data from melanoma patients with nonproportional hazards and find interesting differences from a similar model without random effects. In a simulation study, we show that failure to account for unmeasured covariates can lead to inaccurate estimates of survival probabilities.

A case-control study of lung cancer mortality in U.S. railroad workers in jobs with and without diesel exhaust exposure is reanalyzed using a new threshold regression methodology. The study included 1256 workers who died of lung cancer and 2385 controls who died primarily of circulatory system diseases. Diesel exhaust exposure was assessed using railroad job history from the US Railroad Retirement Board and an industrial hygiene survey. Smoking habits were available from next-of-kin and potential asbestos exposure was assessed by job history review. The new analysis reassesses lung cancer mortality and examines circulatory system disease mortality. Jobs with regular exposure to diesel exhaust had a survival pattern characterized by an initial delay in mortality, followed by a rapid deterioration of health prior to death. The pattern is seen in subjects dying of lung cancer, circulatory system diseases, and other causes. The unique pattern is illustrated using a new type of Kaplan-Meier survival plot in which the time scale represents a measure of disease progression rather than calendar time. The disease progression scale accounts for a healthy-worker effect when describing the effects of cumulative exposures on mortality.

A first-hitting-time (FHT) survival model postulates a health status process for a patient that gradually declines until the patient dies when the level first reaches a critical threshold. Threshold regression (TR) is a new regression methodology that incorporates the effects of covariates on the threshold and process parameters of this FHT model. In this study, we use TR to analyze data from a randomized clinical trial of treatment for multiple myeloma. The trial compares VELCADE and high-dose dexamethasone, the former a new therapy and the latter an established therapy for this disease. Patients are switched between the two drugs based on patient response. The novel contribution of this work is the modeling of this clinical trial design using a mixture of TR models. Specifically, we propose a mixture FHT model to fit the survival distribution. The model includes a composite time scale that differentiates the rate of disease progression before and after switching. The analysis shows significant benefit from initial treatment by VELCADE. A comparison is made with a Cox proportional hazards regression analysis of the same data.

Babies born live under 2,500 g or with a gestational age under 37 weeks are often inadequately developed and have elevated risks of infant mortality, congenital malformations, mental retardation, and other physical and neurological impairments. In this paper, we model birth weight as a first hitting time (FHT) of a birthing boundary in a Wiener process representing fetal development. We associate the parameters of the process and boundary with covariates describing maternal characteristics and the birthing environment using a relatively new regression methodology called threshold regression. Two FHT models for birth weight are developed. One is a mixture model and the other a competing risks model. These models are tested in a case demonstration using a 4%-systematic sample of the more than four million live births in the United States in 2002. An extensive data set for these births was provided by the National Center for Health Statistics. The focus of this paper is on the conceptual framework, models and methodology. A full empirical study is deferred to a later occasion.

This article proposes nonparametric inference procedures for analyzing microarray gene expression data that are reliable, robust, and simple to implement. They are conceptually transparent and require no special-purpose software. The analysis begins by normalizing gene expression data in a unique way. The resulting adjusted observations consist of gene-treatment interaction terms (representing differential expression) and error terms. The error terms are considered to be exchangeable, which is the only substantial assumption. Thus, under a family null hypothesis of no differential expression, the adjusted observations are exchangeable and all permutations of the observations are equally probable. The investigator may use the adjusted observations directly in a distribution-free test method or use their ranks in a rank-based method, where the ranking is taken over the whole data set. For the latter, the essential steps are as follows: (1) Calculate a Wilcoxon rank-sum difference or a corresponding Kruskal-Wallis rank statistic for each gene. (2) Randomly permute the observations and repeat the previous step. (3) Independently repeat the random permutation a suitable number of times. Under the exchangeability assumption, the permutation statistics are independent random draws from a null cumulative distribution function (c.d.f) approximated by the empirical c.d.f Reference to the empirical c.d.f tells if the test statistic for a gene is outlying and, hence, shows differential expression. This feature is judged by using an appropriate rejection region or computing a p-value for each test statistic, taking into account multiple testing. The distribution-free analog of the rank-based approach is also available and has parallel steps which are described in the article. The proposed nonparametric analysis tends to give good results with no additional refinement, although a few refinements are presented that may interest some investigators. The implementation is illustrated with a case application involving differential gene expression in wild-type and knockout mice of an E. coli lipopolysaccharide (LPS) endotoxin treatment, relative to a baseline untreated condition.

This article examines the application of a first hitting time (FHT) model, using an operational time scale, to assess mortality risk differentials of the work environment. A major case application is presented that applies the model to three job categories of railroad workers. The data set involves a study of more than 50 000 workers with mortality assessed from 1959 to 1996. Lung cancer mortality was assessed because of a suspected link to diesel exhaust exposure. Based on a model that stipulates that death occurs when the disease state of a subject first hits a threshold value, the FHT model provides insights into factors influencing disease progression. In this application, in particular, the findings suggest that a job category in 1959 alters the risk of death from lung cancer.

A microarray study aims at having a high probability of declaring genes to be differentially expressed if they are truly expressed, while keeping the probability of making false declarations of expression acceptably low. Thus, in formal terms, well-designed microarray studies will have high power while controlling type I error risk. Achieving this objective is the purpose of this paper. Here, we discuss conceptual issues and present computational methods for statistical power and sample size in microarray studies, taking account of the multiple testing that is generic to these studies. The discussion encompasses choices of experimental design and replication for a study. Practical examples are used to demonstrate the methods. The examples show forcefully that replication of a microarray experiment can yield large increases in statistical power. The paper refers to cDNA arrays in the discussion and illustrations but the proposed methodology is equally applicable to expression data from oligonucleotide arrays., (Copyright 2002 John Wiley & Sons, Ltd.)

There is considerable scientific interest in knowing the probability that a site-specific transcription factor will bind to a given DNA sequence. Microarray methods provide an effective means for assessing the binding affinities of a large number of DNA sequences as demonstrated by Bulyk et al. (2001, Proceedings of the National Academy of Sciences, USA 98, 7158-7163) in their study of the DNA-binding specificities of Zif268 zinc fingers using microarray technology. In a follow-up investigation, Bulyk, Johnson, and Church (2002, Nucleic Acid Research 30, 1255-1261) studied the interdependence of nucleotides on the binding affinities of transcription proteins. Our article is motivated by this pair of studies. We present a general statistical methodology for analyzing microarray intensity measurements reflecting DNA-protein interactions. The log probability of a protein binding to a DNA sequence on an array is modeled using a linear ANOVA model. This model is convenient because it employs familiar statistical concepts and procedures and also because it is effective for investigating the probability structure of the binding mechanism.

This paper describes a general methodology for the analysis of differential gene expression based on microarray data. First, we characterize the data by a linear statistical model that accounts for relevant sources of variation in the data and then we consider estimation of the model parameters. Because microarray studies typically involve thousands of genes, we propose a two-stage method for parameter estimation. The interaction terms for genes and experimental conditions in this model capture all relevant information about differential gene expression in the microarray data. We propose a mixture distribution model for a summary statistic of differential expression that consists of null and alternative component distributions. The mixture model suggests two methods for identifying genes exhibiting differential expression. One is a frequentist method that identifies distinguished genes and the other an empirical Bayes procedure that yields estimated posterior probabilities of differential expression, conditional on observed microarray readings.

We present statistical methods for analyzing replicated cDNA microarray expression data and report the results of a controlled experiment. The study was conducted to investigate inherent variability in gene expression data and the extent to which replication in an experiment produces more consistent and reliable findings. We introduce a statistical model to describe the probability that mRNA is contained in the target sample tissue, converted to probe, and ultimately detected on the slide. We also introduce a method to analyze the combined data from all replicates. Of the 288 genes considered in this controlled experiment, 32 would be expected to produce strong hybridization signals because of the known presence of repetitive sequences within them. Results based on individual replicates, however, show that there are 55, 36, and 58 highly expressed genes in replicates 1, 2, and 3, respectively. On the other hand, an analysis by using the combined data from all 3 replicates reveals that only 2 of the 288 genes are incorrectly classified as expressed. Our experiment shows that any single microarray output is subject to substantial variability. By pooling data from replicates, we can provide a more reliable analysis of gene expression data. Therefore, we conclude that designing experiments with replications will greatly reduce misclassification rates. We recommend that at least three replicates be used in designing experiments by using cDNA microarrays, particularly when gene expression data from single specimens are being analyzed.

Serial dilution assays are widely employed for estimating substance concentrations and minimum inhibitory concentrations. The Poisson-Bernoulli model for such assays is appropriate for count data but not for continuous measurements that are encountered in applications involving substance concentrations. This paper presents practical inference methods based on a log-normal model and illustrates these methods using a case application involving bacterial toxins.

Many models have been proposed that relate failure times and stochastic time-varying covariates. In some of these models, failure occurs when a particular observable marker crosses a threshold level. We are interested in the more difficult, and often more realistic, situation where failure is not related deterministically to an observable marker. In this case, joint models for marker evolution and failure tend to lead to complicated calculations for characteristics such as the marginal distribution of failure time or the joint distribution of failure time and marker value at failure. This paper presents a model based on a bivariate Wiener process in which one component represents the marker and the second, which is latent (unobservable), determines the failure time. In particular, failure occurs when the latent component crosses a threshold level. The model yields reasonably simple expressions for the characteristics mentioned above and is easy to fit to commonly occurring data that involve the marker value at the censoring time for surviving cases and the marker value and failure time for failing cases. Parametric and predictive inference are discussed, as well as model checking. An extension of the model permits the construction of a composite marker from several candidate markers that may be available. The methodology is demonstrated by a simulated example and a case application.

Count data often show overdispersion compared to the Poisson distribution. Overdispersion is typically modeled by a random effect for the mean, based on the gamma distribution, leading to the negative binomial distribution for the count. This paper considers a larger family of mixture distributions, including the inverse Gaussian mixture distribution. It is demonstrated that it gives a significantly better fit for a data set on the frequency of epileptic seizures. The same approach can be used to generate counting processes from Poisson processes, where the rate or the time is random. A random rate corresponds to variation between patients, whereas a random time corresponds to variation within patients.

Engineering degradation tests allow industry to assess the potential life span of long-life products that do not fail readily under accelerated conditions in life tests. A general statistical model is presented here for performance degradation of an item of equipment. The degradation process in the model is taken to be a Wiener diffusion process with a time scale transformation. The model incorporates Arrhenius extrapolation for high stress testing. The lifetime of an item is defined as the time until performance deteriorates to a specified failure threshold. The model can be used to predict the lifetime of an item or the extent of degradation of an item at a specified future time. Inference methods for the model parameters, based on accelerated degradation test data, are presented. The model and inference methods are illustrated with a case application involving self-regulating heating cables. The paper also discusses a number of practical issues encountered in applications.

Most materials and components degrade physically before they fail. Engineering degradation tests are designed to measure these degradation processes. Measurements in the tests reflect the inherent randomness of degradation itself as well as measurement errors created by imperfect instruments, procedures and environments. This paper describes a statistical model for measured degradation data that takes both sources of variation into account. The degradation process in the model is taken to be a Wiener diffusion process. The measurement errors are assumed to be independent normal random outcomes that are independent of the degradation process. The paper describes inference procedures for the model and discusses some practical issues that must be considered in dealing with the statistical problem. A case study is presented.

Properties of the inverse gaussian distribution are presented with comments on fitting the distribution to lentgh-of-stay data. A conceptual framework for the hospitalization process is described; it suggests that the inverse gaussian distribution has considerable potential as both a descriptive and prescriptive model of length of stay, especially in the setting of psychiatric hospitals.

The mortality component of contemporary health indexes is discussed. Since these indexes reduce to mortality indexes when only life and death states enter the analysis, they share the conceptual weaknesses of mortality indexes. Also, they do not incorporate consumption variables explicity and therefore provide no structure for relating health status and living standard. Some attention is devoted to methodological problems of assessing survival probabilities, either from survey or experimental data or from beliefs of experts or individuals who are affected directly. The final section deals with individual preferences for survival lotteries. Conceptual weaknesses of common indexes are discussed, several canonical models for survival preferences are presented, the interdependence of individual utilities is discussed, and methods for eliciting individual survival preferences are considered, along with some illustrative empirical results.