Even if the COPD exacerbation resolves, many patients never return to their baseline level of health [5].

COPD exacerbations: Prognosis, discharge planning, and prevention

Does Early Treatment of Exacerbation ImproveOutcome in Chronic Obstructive Pulmonary Disease?

For example, a benefit–harm analysis forroflumilast as preventive therapy for COPD exacerbationsreported that benefits of roflumilast outweighed itspotential harm when patients have severe exacerbationrisk of at least 22% over a year.24 Using data from thisbenefit–harm analysis, the accompanying web app ofACCEPT can be used to inform therapeutic decisions onuse of roflumilast for a given patient. Another example isin the potential use of preventative daily azithromycintherapy in COPD. Azithromycin reduces annual exacer-bation rate by 27%.8

Lung function didnot decrease significantly during the prodromal period, but byDay 0, PEFR had fallen from baseline by a median 8.6 (IQR 0to 22.9) L/min, FEV1 by 24.0 (IQR 216.1 to 84.3) ml, and FVCby 76.0 (IQR 240.4 to 216.4) ml. The declines in lung func-tion, whether measured by PEFR, FEV1, or FVC, were allhighly significant (p , 0.001). Significantly greater decreasesin PEFR were seen when the exacerbation was associated withsymptoms of increased dyspnea (r 5 20.12 [n 5 449]; p 50.014), colds (r 5 20.09 [n 5 449]; p 5 0.047), or increasedwheeze (r 5 20.12 [n 5 449]; p 5 0.009), but not with othersymptoms.

Before onset of exacerbation there was deterioration inthe symptoms of dyspnea, sore throat, cough, and symptoms of acommon cold (all p , 0.05), but not lung function.

The bad news is that this study suggests that the EXACT seems to be relatively insensitive in detectingexacerbation events. Only 34 (27%) out of 128 of London diary card exacerbations exceeded the EXACTthreshold for an exacerbation event (defined as a 12-point increase in EXACT score above baseline for twoconsecutive days or a 9-point increase for three days). Even more worryingly, of the 85 London COPDCohort diary card-defined exacerbations that were treated with oral antibiotics and/or corticosteroids by thestudy team during the 2-year study period, only 34% were picked up using EXACT.

The results of the study are certainly mixed. The good news is that mean EXACT scores did increase, asexpected, during exacerbation events relative to the stable state, and that the time taken for EXACT scores toreturn to baseline was significantly correlated to both diary-card symptom recovery time and lung functionrecovery. This information suggests that EXACT can be used to measure the duration of COPDexacerbation events.

The EXACT has previously been used in conjunction with a personal digital assistant [14, 24] or smartphone[25].

Thus, this study has highlightedimportant potential limitations of the EXACT in its ability to independently identify events that were capturedby physician review (HCU) or London COPD cohort diary cards.

Patients completed a paper version of the EXACT at least once under supervision in the clinic and wereinstructed to complete the EXACT diary each evening before bedtime, based on their symptomsexperienced that day.

The exacerbations of chronic pulmonary disease tool (EXACT) is a PRO daily symptom diary developed tocapture frequency, severity and duration of exacerbations in clinical trials of COPD [14].

An exacerbation was defined as an increase in respiratorysymptoms for two consecutive days, with at least one major symptom (dyspnoea, sputum purulence orsputum volume) plus either another major or a minor symptom (wheeze, cold, sore throat and cough), thefirst of which was defined as the day of onset of the exacerbation.

The PaCO2 is currently obtained invasively by tak-ing blood samples at discrete time instants. To motivate animprovement, this paper justifies PaCO 2 monitoring forCOPD patients continuously and noninvasively by transcuta-neous CO2 measurements (PtcCO2).

Pulse oximeters, however, cannot detect changes in the arte-rial carbon dioxide (CO2) partial pressure (PaCO2), which weargue is one of the most significant parameters for COPDpatients

A previousstudy [13] has suggested that symptoms tend to worsen duringthe 7 days immediately before an exacerbation episode.

Here, we present a case of COPD exacerbation detected using RPM ina clinical setting. The RPM system (Spire Health, 2021) has been vali-dated for use with chronic respiratory disease patients [9,10] and iscomprised of: (1) Health Tags, undergarment waistband-adhered phys-iologic monitors which include photoplethysmography, activity, andrespiratory force sensors, (2) an in-home stationary device to collect andupload sensor data, and (3) a web dashboard to display patient data andnotifications to clinicians.

Case

Seemungal et al. reported a 7-day prodrome prior to diagnosis ofexacerbation [6]. With this in mind, the use of respiratory RPM has thepotential to reduce COPD treatment delays leading to improved care.Increased respiratory rate has demonstrated predictive ability for ex-acerbations of COPD [7,8]. Shah et al. observed an increased respiratoryrate in the 5 days preceding hospitalization for COPD exacerbations,highlighting the window of opportunity for intervention [7].

Acute changes in lung function (forcedexpiratory volume in 1 s (FEV 1)) or the FEV1/forced vital capacity ratio are not sensitive, and do notcorrelate well with AECOPD [57, 58].

Studies that have assessed the incidence of symptom-based AECOPDs compared to event-based AECOPDsin the same patients followed over time suggest that observed exacerbation rates are much higher ifsymptom-based definitions are used. The Investigating New Standards for Prophylaxis in ReducingExacerbations (INSPIRE) study compared the incidence of AECOPD using symptom-based definitions anda treatment-based definition and found that the incidence rate was three AECOPDs per patient-year if asymptom-based definition was used and 1.5 AECOPDs per patient-year if an event-based definition wasused, suggesting that 50% of symptom-defined COPD exacerbations are not treated by physicians [27].

A further advantage is that validated tools to capture symptom-basedAECOPDs exist and include patient diary cards [18] and the validated Exacerbation of ChronicPulmonary Disease Tool (EXACT) [19].

Advantages and disadvantages of event-based definitions of AECOPD

Advantages and disadvantages of symptom-based definitions of AECOPD

The 2018 GOLD document defines COPD exacerbation as “an acute worsening ofrespiratory symptoms that results in additional therapy”. Exacerbations are classified as 1) mild if they aretreated with short-acting bronchodilators only; 2) moderate if they are treated with short-actingbronchodilators plus antibiotics and/or oral corticosteroids; or 3) severe if the patient visits the emergencyroom or requires hospitalisation because of an exacerbation [16].

Symptom-based definitions rely on patient-reported worsening of respiratory symptoms either to ahealthcare practitioner or within a symptom diary.

ecause of global variability in the available resources to treat patients and local customsaffecting the criteria for hospital visits and admissions, there is substantial variability in reported ECOPD outcomes.(11)

Currently, exacerbations are classified after the event has occurred as:► Mild (treated with short acting bronchodilators only, SABDs)► Moderate (treated with SABDs and oral corticosteroids ± antibiotics) or► Severe (patient requires hospitalization or visits the emergency room). Severe exacerbations may also beassociated with acute respiratory failure.

Currently, exacerbations are classified after the event has occurred as:► Mild (treated with short acting bronchodilators only, SABDs)► Moderate (treated with SABDs and oral corticosteroids ± antibiotics) or► Severe (patient requires hospitalization or visits the emergency room). Severe exacerbations may also beassociated with acute respiratory failure.

Frequently used definitions and diagnostic criteria for COPD exacerbations

An openingwas defined as the first day of a positive symptom score indi-cating worsening of respiratory symptoms from baseline (ie,a symptom score $1 point)

This prodrome phase is ofgreat interest, as knowledge of exacerbation onsetcan help physicians to time early therapeuticinterventions appropriately. 7

However, it should be stressed thataction plans that contain only minimal or no patient self-management education have not been shown to reduce urgenthealthcare utilisation for COPD. 12

Previous studies suggest that prompt treatment ofexacerbations is associated with better clinical outcomes.

One implication isthat COPD action plans, with provision of prespecifiedprescriptions for antibiotics and oral steroids, may be appro-priate to ensure prompt and appropriate management of exac-erbations. 10

The onset, or prodrome,of COPD exacerbations is a subject that has received very littlestudy to date.

Thefindings show that patients who receive prompt therapy afterthe onset of their exacerbation are likely to recover more rapidlythan those who delay reporting and thus initiation of treatment.Furthermore, patients who habitually fail to seek therapy fortheir exacerbations have poorer health-related quality of lifeand are more likely to be hospitalized for the management ofan exacerbation

patients withCOPD often have poor understanding of their disease and symp-toms, with the result that exacerbations are often not reportedto healthcare professionals for treatment (2).

The lower airways of 25 to 50% of patients with COPD arecolonized by bacteria, especially noncapsulated Haemophilusinfluenzae, Streptococcus pneumoniae, and Moraxella catarrhalis.

Recent studies have shown that about one-half of COPD exacer-bations are associated with viral infections, the majority of whichare due to rhinovirus (32–36).

Lung function changes, such as decreases in peak expiratoryflow rate (PEFR) or FEV1 immediately before exacerbation, aregenerally small and not useful in predicting exacerbations, butlarger decreases in PEFR are associated with dyspnea, longerrecovery time after exacerbations, and the presence of symptom-atic colds (11).

There have now been several large population studies (8–10)showing that the number and severity of exacerbations are lowerin patients with mild to moderate COPD (FEV1  50% pre-dicted), whereas in severe disease the rate of COPD exacerba-tions may increase to 1.5 to 2.5/patient/yr.

The primary outcome was the occurrence ofat least one COPD-related hospitalizationwithin the 2-month period after the indexdate (the outcome window).

A history of previous exacerbations isconsidered the best predictor of futureexacerbations and forms the current basis ofrisk stratification in guidelines (22, 23).

Adistinct advantage of this approach is thatrisk prediction can be performed remotelyand can be made arbitrarily complex toimprove its accuracy. In this “populationsurveillance” approach, individuals who areidentified as high-risk can then be contactedfor preventive disease management.

Most previous risk-predictionmodels for COPD exacerbations weredeveloped for use at point of care (5–8);however, an alternative approach is to useroutinely collected health data (9).

Using the definition of exacerba-tion based on health care utilization, they foundthat the degree of airflow obstruction, health-related quality of life, an elevated white-cellcount, and a history of gastroesophageal refluxwere independently associated with increasedexacerbation frequency in the entire cohort;however, a history of previous exacerbationsbest predicted the subsequent occurrence of ex-acerbations in all stages of COPD severity.

Whendefined on the basis of health care utilization,exacerbations are classified as moderate or, ifhospitalization ensues, as severe, with those epi-sodes managed by patients themselves relegatedto the mild category.3

Consequently, confirmation that an “exacerba-tion” has actually occurred requires not only theworsening of the patient’s respiratory symptomsbut also the prescription of additional treatmentby a health care provider

Stepwise logisticregression is commonly used for variable selection 16 and this method was prespecified during the study design

he outcome was the occurrence of AECOPD (ie occurrence versus no occurrence)

When only lifestyle or environmental dataare automatically uploaded daily, the system still predictswhether AECOPD will occur within the next 7 days.

For model comparison with machine learning–basedclassification, we selected the following classifiers: decisiontrees [15], random forests [16], k-nearest neighbor clustering[17], linear discriminant analysis, and adaptive boosting [18]

Classification algorithms for this study were selected accordingto previously published studies on COPD such as those of Wanget al [13] and Rahman et al [14].

severe exacerbationswere those that required an emergency departmentvisit or admission to hospital. 3,8–10

Inclinical practice, a history of two or more exacerbationsand one severe exacerbation per year is used toguide therapeutic choices for exacerbation prevention.3

ACCEPT predicts rate and severity of exacerbations.

For example, ACCEPT can predict thenumber of exacerbations at a given time period, time tonext exacerbation, and probability of having a specificnumber of non-severe or severe exacerbations within agiven follow-up time (up to 1 year). By contrast, logisticregression models, used in most previous clinicalprediction models, predict the probability of having at leastone exacerbation in a single timeframe.6

Outcomes of interest were rates of exacerbations andsevere exacerbations over 1 year.

In conclusion, our study confirms the obser-vation that exacerbations become more frequentand more severe as the severity of underlyingCOPD increases and shows that the most impor-tant determinant of frequent exacerbations is ahistory of exacerbations.

Wedefined frequent exacerbations as two or moreexacerbations in a year because this definition co-incides with current health care utilization crite-ria for frequent exacerbations.

The casedefinition of an exacerbation was a functional one,based on the decision by a patient’s primary cli-nician or by study personnel to prescribe antibi-otics or systemic corticosteroids, alone or in com-bination.

We show that the combination of a low dailystep count and high CRP or IL-6 level isassociated with an increased rate of AEsand COPD-related hospitalizations

Results ofthe logistic regression and ROC analysis showed that theinfluences of the BODE index and the GOLD stage on exac-erbation risk during the first year of follow-up was similar.

Exacerbations were gradedaccording to either: treatment in primary care, emer-gency room visit, or hospitalization. The BODE indexwas a good predictor of both the number and the sever-ity of exacerbations in COPD, especially in those exacer-bations that required hospital admission

Recently, Williams et al. sug-gested that the incremental shuttle walking test (ISWT)could be substituted for the 6MWT as an alternativemeasure of exercise capacity within the index and intro-duced the i-BODE (4). As field exercise tests, the ISWTand 6MWT are closely related (5, 6), though ISWT isconsidered to be closer to a maximal exercise test (7),whereas the 6MWT reflects a more functional exerciseperformance

The BODE index has been found to be better than forcedexpiratory volume in 1 second (FEV1 ) in predicting the risk of death and hos-pitalization among patients with COPD (2, 3).

Another potential limitation is thechanges in treatment of COPD over thestudy period.

The principal finding of this study isthat simultaneously elevated levels ofCRP, fibrinogen, and leukocytes wereassociated with increased risk of fre-quent exacerbations in individuals withstable COPD.

Frequent ex-acerbations were defined as 2 or moreexacerbations less than 1 year apart.

An exacerbation of COPD was de-fined as a short-course treatment withoral corticosteroids alone or in combi-nation with an antibiotic or as a hos-pital admission due to COPD

However, some patients with COPDalso have evidence of low-grade sys-temic inflammation with increased lev-els of such inflammatory biomarkers

However, when predicting risk of fu-ture exacerbations based on previousevents, the positive predictive value re-mains low,9 indicating that additionaldeterminants of exacerbation suscep-tibility remain to be identified

Finally, the ECLIPSE study wasconducted in multiple countries, which may have dif-ferent policies for hospitalizations and may follow(slightly) different treatment strategies. To explore thispossibility, we analyzed the subset of data collectedfrom three countries contributing the majority ofpatients (United States, United Kingdom, and Norway)and did not find significant differences among thesecountries in incidence of hospitalized exacerbations(e-Table 2), suggesting that if anything, this effect islikely small.

On theother hand, we acknowledge that our results may notbe immediately generalizable to the entire primarycare population of patients with COPD because inour study, patients were recruited mainly from pulmo-nary clinics.

In a subgroup of patients without recent hospitalizedexacerbation at baseline, fibrinogen was identified asan additional risk factor of future risk of hospital admis-sions for COPD exacerbations. Inflammatory pathwaysplay a prominent role in exacerbations of COPD.Fibrinogen has been recognized to independently contrib-ute to clinically important outcomes in COPD, includinghospitalization for COPD. 46,47 Our results indicate fibrin-ogen levels are predictive of the future hospitalizedexacerbations in the absence of information on past his-tory of these events. Plasma fibrinogen is under regula-tory qualification as a risk factor for mortality andhospitalization in COPD.48

following an exacerbation 29-32 ; inactivity associatedwith hospitalization may cause muscle mass loss anddysfunction33; comorbidities may develop or worsen dueto treatment side effects (eg, systemic steroids inducinghyperglycemia and/or muscle weakness)34; patients maybe exposed to nosocomial infections35; and hospitaliza-tion may cause and/or aggravate depression.36

We found that a previous hospitalized exacerbation inthe past year was the strongest predictor of future exac-erbations requiring hospitalization.

(1) COPD exacerba-tions requiring hospital admission are relatively fre-quent events occurring in about 30% of patients duringthe 3-year follow-up; (2) past history of hospitalizedexacerbations is most predictive of future events, andother risk factors include the severity of airflow limita-tion, poor health status, radiologic evidence of emphy-sema, older age, and presence of systemic inflammation;and (3) a history of hospitalized exacerbations heraldspoor survival

Exacerbations of COPD accel-erate disease progression5-7

xacerbation wasdefined on the basis of symptom-based diagnosis such asincreased cough and sputum production, a change of sputumcolor, and worsening of dyspnea from a stable state andbeyond-normal day-to-day variations, i.e., showing acute onsetand necessitating a change in regular medication, in accor-dance with a previous report [21]. Moderate exacerbationsrequired a prescription for antibiotics and/or systemic corticos-teroids, and severe exacerbations required hospitalization [22].

the CODEX indexis the most useful in predicting survival, hospital read-missions, and a combination of the two in the short andmedium term in patients hospitalized for AECOPD.

Multicomponent scales have been developed toimprove prognosis prediction in COPD, and they haveproved to be better predictors of survival than anyisolated variable.

This newly proposed CODEX index is essentially anevolution of the BODE and BODEX indexes, retain-ing their cutoffs for dyspnea, obstruction, and previousexacerbations, but replacing BMI with comorbiditymeasured using the original Charlson index modifiedby age.

Second, we reportedthe usefulness of this CODEX index in evaluating therisk of readmission, as well as the composite end point(readmission and/or mortality).

Time-dependentvariables from hospital discharge were analyzed with Cox logisticregression and Kaplan-Meier statistics.

CODEX was designed to predict mortality and hospitalreadmission in 3–12 months after discharge of patients hospi-talized for AECOPD.6

BODE2 (body mass index [BMI], airflow obstruction, dyspnea, andexercise capacity), BODEX3 (BMI, airflow obstruction, dyspnea, and previous severeexacerbations), ADO4 (age, dyspnea, and airflow obstruction), and DOSE5 (dyspnea,airflow obstruction, smoking status, and exacerbation frequency

When the recordings met criteria number 1 a red lineappeared on the corresponding day of the patient’s time-score plot (Fig. 2) and an electronic mail message wasautomatically sent to the research team.

To establish a baseline all patients entered an exacer-bation-free run-in period of 14 days where they recordedsymptom score and lung function as described above.Baseline for each symptom score and FEV 1 was the medianand the mean value respectively of the 14-day run-in periodrecordings

. AECOPD was, therefore, regarded to be present ifat least one of the following criteria was encountered:1. An increase of at least 1 degree of 2 symptom scoresand/or a decline in FEV 1  10% from baseline for 2successive days.2. A patient presenting with symptoms they felt to bethose of AECOPD and sought help that resulted in thembeing given a course of antibiotics and/or prednisolone.

Conventional threshold-basedalgorithms, adopted in the majority of reviewed stud-ies (n ¼ 12), show poor performance in early detect-ing respiratory exacerbations or identifying severityand duration in COPD, 13,53 with the best reportedaccuracy being 73% of exacerbations detected. 52 ; bestsensitivity/specificity 66%/93%55 24 h before hospi-talization.

Whilst the 7-day recall scoresand the daily diary scores have been found to beequivalent in detecting changes over time of theimpact of COPD symptoms, only daily data seemto be suitable if the outcome of interest is detectingthe onset of exacerbations. 85

In COPD, physiological measurements have notproved to be able to predict deteriorations, eitherbecause they change late in the time course ofexacerbation, they cannot be measured reliably orbecause therapeutic interventions during the experi-ment alter the outcomes hindering the accuracy ofalgorithms. 17

One study used a com-promise solution, 56 whereby the patient with a lowrisk of exacerbation monitored on a weekly basis andwhen risk increased according to the predictivemodel, reporting tasks could be scheduled daily toensure timely detection.

A common limitation in the selected studies was theexamination of a relatively small group of patientswho presented a high rate of exacerbations. Winterperiods were extensively selected for trials becauseexacerbations are more likely than in other sea-sons. 51 Although this may have enabled recruit-ment of ‘at-risk’ populations it may have affectedgeneralizability of results.

EXACT-PRO was specifically designed and validated fordetecting COPD exacerbation

(EXACT)

An ‘event-based’ definition of an exacerbation, 70including self-administration of medication orunscheduled visits to emergency units and/or admis-sions, was used in nine studies (n ¼ 6 in COPD andn ¼ 3 in asthma studies). Symptom-based definitionsof exacerbation (e.g. Anthonisen criteria 71 ) were usedin seven COPD studies.

Exacerbation criteria

Cox proportional hazards modeling would alsohave been a valid approach for risk estimation, but we choselogistic regression analysis because we considered each exac-erbation within our predefined time frame of 2 years to beof equal importance, regardless of whether this exacerbationoccurred early or late in the follow-up period.

We were not able to include all potential predictorsavailable from the literature, such as exercise capacity, theSt George’s Respiratory Questionnaire, oxygen therapy,and gastroesophageal reflux

Unfortunately, wecould not evaluate the widely accepted BODE index,5 becausewe did not perform a 6-minute walking test in any of ourcohorts.

For both cohorts we used the same “operational” definitionfor exacerbation of COPD, that is, symptomatic deteriorationrequiring pulsed oral steroid use or hospitalization.15–1

For both cohorts we used the same “operational” definitionfor exacerbation of COPD, that is, symptomatic deteriorationrequiring pulsed oral steroid use or hospitalization.15–1

An increase in respiratory rates and thepercentage of respiratory cycles triggered by the patients nearly systematically precededexacerbation in patients with COPD treated by home NIV [ 25].

mean decrease of 700 steps per day was associated with an increasein the EXACT score indicating the start of an exacerbation [21 ].

The COPD “frequent exacerbator” phenotype is consistently defined by atleast two treated exacerbations per year and is associated with poor long-term outcomesand an accelerated decline in lung function

The primary composite outcome was death or admissionsfrom the baseline data collection until 60 months. Thesecondary outcome was exacerbations from the baselinedata collection until 60 months.

Seven out of nine studies foundin the literature confirmed the finding that female patientshave a higher number of total exacerbations.15–17,19,21,22,31

Participants were asked to use the following definition foran exacerbation: a moderate exacerbation was defined asan increase in symptoms requiring a visit to a health careprovider and a course of antibiotics and/or oral steroids.A severe exacerbation was defined as an exacerbation requir-ing hospitalization.

History of Exacerbations

The prediction period was divided into non-overlap-ping 10-day prediction windows for each patient (Figure3). Before the start of each 10-day prediction window,lookback periods of 10, 30, 60, 90,180, 365 days or theentire patient history were set up depending on the vari-able. For details refer to Supplemental Table 1.

Seasonality isknown to affect COPD exacerbations, most frequently occur-ring in the winter months,37–39 which is likely to reflect anincreased prevalence of respiratory infections, reduced immu-nity, altered environmental conditions, and physiologicalresponses during these months.40,41

Timing of Re-Exacerbation RiskTo understand the timing and dynamics of re-exacerbationrisk, and to evaluate the choice of cut points for early andlate re-exacerbations, Kaplan–Meier cumulative incidencecurves of time to first re-exacerbation amongst all patientsin cohort A were plotted.

The cut-off pointfor early and late re-exacerbations was chosen based on clinicaljudgment, and was informed by an analysis of dailyre-hospitalization risk in the US.18 The 90-day cut-off pointwas also chosen based on clinical development support for anAECOPD therapy. Patients were classed as having nore-exacerbations if they did not re-exacerbate within the180-day period after the index date.

Re-exacerbations were defined a priori as either early (occur-ring within 1–90 days after the index date) or late (occurringbetween 91–180 days after the index date

This included start date, end (reso-lution) date, treatment (oral corticosteroid/antibiotics),severity (including hospitalization), and outcome (includ-ing death). Data was collected at scheduled visits (baselineand 3, 6, 12, 18, 24, 30, and 36 months), using an electro-nic case-report form and based on either patients’ recall ofexacerbation events or available medical records forexacerbation events, and was supplemented by monthlyphone calls to ECLIPSE participants

First, we aimed to develop and validatea predictive model capable of identifying factors potentiallypredictive of experiencing early, late, or no re-exacerbationwithin 180 days.

A challenge in COPD is the variation between patients and how to set alarm limits for anindividual patient. Of the 16 articles included in this review, only eight studies (three at high riskof bias, one at low quality and two at moderate quality) [ 5, 13, 14 ,18 – 21, 25] mentioned that they hadcustomised the alarm limits for each individual. Methods used were reported in six out of the eightstudies

Exacerbations were defined as subject-reported worsen-ing in respiratory health, requiring therapy with systemic cortico-steroids and/or antibiotics. Frequent exacerbations were definedas 2 or more exacerbations in 1 year, and severe exacerbations weredefined as those leading to hospitalization or emergency room vis-its [9]

Acute exacerbationreadmission within 30 days due to the short acute exacer-bation cycle, not only severely damages lung function andincreases the risk of death, but also occupies a large num-ber of medical resources [4]

Our study assumes that the SVM model can achieve acertain prediction effect in predicting the risk of readmis-sion in COPD patients, and the results have certain refer-ence value. Therefore, it is proposed to use SVM to builda 30-day acute exacerbation readmission risk predictionmodel for elderly COPD patients, and evaluate its predic-tion effect, so as to provide a basis for early identificationof patients with high risk of readmission in the future.

such as bloodeosinophil count, chronic bronchitis, gastroesophagealreflux, socioeconomic status, and insurance coverageimprove risk prediction remains to be investigated.

Second, ACCEPT does not advance ourunderstanding of how various risk factors operatein combination. Many variables appear to be simplymarkers of severity rather than biological predictors ofreal risk. The authors address one of these: contrary toestablished literature, current smoking confers reducedrisk of exacerbation, probably because patients withsevere disease and high frequency of exacerbations aremore likely to have quit smoking.

Finally, preventionof severe exacerbations is needed before they occur,and performance of this risk tool in individuals whohave never had an exacerbation is not clear and needsto be tested.

First, although ACCEPTshowed good-to-excellent discrimination overalland appears superior to exacerbation history alone,improvement in risk prediction was smaller in thosewith previous history of exacerbations than in thosewithout.

Thus, the major improvement in risk prediction withACCEPT appears to be for severe exacerbations.

Usinga joint survival–logistic model, this risk tool providesan individualised risk estimate for exacerbations in thesubsequent year and their severity, as well as the rate offuture events.

Severe exacerbations are especially important asthey are associated with rapid decline of lung functionand 50% of patients die within 2 years after admissionto hospital.

HOME OR OFFICE MANAGEMENT OF COPD EXACERBATIONS

More than 80percent of exacerbations of COPD can be managed on an outpatient basis, sometimes afterinitial treatment in the office or emergency department.

ADVICE RELATED TO COVID-19

Vitamin D supplementation — Adhering to current guidelines regarding vitamin Dsupplementation in patients with a 25-hydroxyvitamin D level <20 or 30 ng/mL (50 or 75nmol/L) reduces COPD exacerbations in addition to benefits in reducing falls and fractures

Noninvasive ventilation — For patients who require noninvasive ventilation (NIV) during ahospitalization for a COPD exacerbations and who remain hypercapnic, nocturnal NIV athome significantly reduces the risk of rehospitalization

Prophylactic azithromycin

defined as "an acuteevent characterized by a worsening of the patient's respiratory symptoms that is beyondnormal day-to-day variations and leads to a change in medication

PREVENTION

Pulmonary rehabilitation

Smoking cessation (see "Overview of smoking cessation management in adults")•Proper use of medications (including inhaler technique) ( table 5 and table 6and table 7 and table 8) (see "The use of inhaler devices in adults")•Vaccination against seasonal influenza (see "Seasonal influenza vaccination inadults")•Vaccination against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)(see "COVID-19: Vaccines")•Pneumococcal vaccination ( figure 1) (see "Pneumococcal vaccination in adults")

Patients were contacted by telephone by atrained clinical research assistant at months 1, 2, and 3 afterrecruitment and were asked about potential hospitalizationsbecause of ECOPD. Whenever this was identified, hospital,data of admission, and reason for hospitalization were recordedusing standardized questionnaires. The attending pulmonolo-gist of each patient, blinded to the respiratory results, reviewedall available information and validated the episode of ECOPDhospitalization

First, weanalyzed individual changes in mean respiratory frequency usingtime series analysis of breathing rate in each patient whorequired ECOPD hospitalization during follow-up. This timeseries included 5 baseline days and the 5 days that precededhospitalization. Baseline was defined as the first 5 consecutivefollow-up days with valid recorded data and a minimum com-pliance with oxygen therapy of 4 h/d, before any exacerbationhad occurred. Individual changes were analyzed using the YoungC statistic, which is appropriate for the study of changing trendsin short series with a small number of measures. 16 Second, weanalyzed the change in mean respiratory frequency between the5 baseline days and the 5 days that preceded hospitalization ofall individual time series considered together using analysis ofvariance for repeated measures. Third, we analyzed the discrimi-nating power of the change in the mean respiratory frequency topredict ECOPD hospitalizations using receiver operating char-acteristic (ROC) curves in two different potentially relevantclinical scenarios (increase of breathing rate from baseline to24 or 48 h before hospitalization).

Patients were contacted by telephone by atrained clinical research assistant at months 1, 2, and 3 afterrecruitment and were asked about potential hospitalizationsbecause of ECOPD. Whenever this was identified, hospital,data of admission, and reason for hospitalization were recordedusing standardized questionnaires. The attending pulmonolo-gist of each patient, blinded to the respiratory results, reviewedall available information and validated the episode of ECOPDhospitalization.