Prediction of Mortality Using Different COPD Risk Assessments - A 12-Year Follow-Up

RiskPath: Explainable deep learning for multistep biomedical prediction in longitudinal data

Many diseases are the end outcomes of multifactorial risks that interact and increment over months or years. Timeseries AI methods have attracted increasing interest given their ability to operate on native timeseries data to predict disease outcomes. Instantiating such models in risk stratification tools has proceeded more slowly, in part limited by factors such as structural complexity, model size and explainability. Here, we present RiskPath, an explainable AI toolbox that offers advanced timeseries methods and additional functionality relevant to risk stratification use cases in classic and emerging longitudinal cohorts. Theoretically-informed optimization is integrated in prediction to specify optimal model topology or explore performance-complexity tradeoffs. Accompanying modules allow the user to map the changing importance of predictors over the disease course, visualize the most important antecedent time epochs contributing to disease risk or remove predictors to construct compact models for clinical applications with minimal performance impact.

The DOSE index in chronic obstructive pulmonary disease: evaluating healthcare costs

BACKGROUND AND OBJECTIVES

The DOSE index, which incorporates Dyspnea, Obstruction, Smoking, and Exacerbations, is a widely used tool for assessing the severity and prognosis of Chronic Obstructive Pulmonary Disease (COPD). In addition to risk assessment, it has potential clinical utility in predicting healthcare costs, which are primarily driven by exacerbations. While several indices, such as the BODE (Body-mass index, Obstruction, Dyspnea, Exercise) and ADO (Age, Dyspnea, Obstruction) indices, exist for risk prediction, there is a lack of dedicated tools for forecasting healthcare costs. This study explores the potential of the DOSE index compared to other indices, including BODE, ADO, and the Charlson Comorbidity Index (CCI), for this purpose.

MATERIALS AND METHODS

This cross-sectional retrospective study analyzed data from 396 COPD cases. We examined associations between the DOSE index, BODE index, ADO index, CCI, and healthcare costs, including hospitalizations and emergency room treatments. Healthcare costs were categorized as direct medical expenses.

RESULTS

Significant associations were observed between the DOSE index and various healthcare parameters. DOSE quartiles showed strong correlations with outpatient visits (p = 0.013) and outpatient medical expenses (p = 0.011). In addition, hospitalization frequency, duration, and associated costs were significantly correlated with higher DOSE quartiles (p < 0.001). A significant difference was found when comparing DOSE quartiles between patients with high (CCI ≥ 3) and low (CCI < 3) comorbidity scores (p = 0.018). The DOSE index outperformed other indices, likely due to its inclusion of exacerbations, a key driver of healthcare costs.

CONCLUSION

The DOSE index demonstrates potential in predicting healthcare costs, particularly due to its inclusion of exacerbation frequency. This study highlights the importance of considering exacerbations alongside traditional risk factors for more accurate cost forecasting in COPD management. Our findings suggest that the DOSE index may be a valuable tool in both clinical and economic assessments of COPD patients, though further research is warranted to validate these findings in larger datasets.

Treatment intensity level as a proxy for severity of chronic obstructive pulmonary disease: A risk stratification tool

BACKGROUND

Increasing severity of chronic obstructive pulmonary disease (COPD) is associated with increasing risk of poor outcomes. Using health registry data, we aimed to assess the association between treatment intensity levels (TIL), as a proxy for underlying COPD severity, and long-term outcomes.

METHODS

Using Danish nationwide registries, we identified patients diagnosed with COPD during 2001-2016, who were alive at index date of 1 January 2017. We stratified patients into exclusive TILs from least to most severe: no use, short term therapy, mono-, dual-, triple therapy, oral corticosteroid (OCS), and long-term oxygen treatment (LTOT). Survival analyses were used to assess 5-year outcomes by TIL.

RESULTS

We identified 53,803 patients with COPD in the study period (median age: 72 years [inter quartile range, 64-80], 48 % male). The three most severe TILs were associated with a significant incremental increase in all-cause mortality with an adjusted hazard ratio (aHR) for triple therapy, OCS and LTOT of 1.44 (95 % CI: 1.38-1.51), 1.67 (95 % CI: 1.59-1.75), and 2.91 (95 % CI: 2.76-3.07) compared with those receiving no therapy as reference. The same pattern was evident for the composite outcome of 5-year mortality or COPD-related hospitalization with an aHR for triple therapy, OCS and LTOT of 2.30 (95 % CI: 2.22-2.38), 2.85 (95 % CI: 2.74-2.96), and 4.00 (95 % CI: 3.81-4.20), respectively.

CONCLUSION

Increasing TILs were associated with increasing five-year mortality and risk of COPD-related hospitalization. TILs may be used as a proxy for underlying COPD severity in epidemiological studies.

The treatable traits approach to adults with obstructive airways disease in primary and secondary care

The treatable traits approach is based on the recognition that the different clinical phenotypes of asthma and chronic obstructive airways disease (COPD) are a heterogeneous group of conditions with different underlying mechanisms and clinical manifestations, and that the identification and treatment of the specific clinical features or traits facilitates a personalised approach to management. Fundamentally, it recognises two important concepts. Firstly, that treatment for obstructive lung disease can achieve better outcomes if guided by specific clinical characteristics. Secondly, that in patients with a diagnosis of asthma, and/or COPD, poor respiratory health may also be due to numerous overlapping disorders that can present with symptoms that may be indistinguishable from asthma and/or COPD, comorbidities that might require treatment in their own right, and lifestyle or environmental factors that, if addressed, might lead to better control rather than simply increasing airways directed treatment. While these concepts are well accepted, how best to implement this personalised medicine approach in primary and secondary care within existing resource constraints remains uncertain. In this review, we consider the evidence base for this management approach and propose that the priority now is to assess different prototype templates for the identification and management of treatable traits in both asthma and COPD, in primary, secondary and tertiary care, to provide the evidence that will guide their use in clinical practice in different health care systems.

Comparison of BODE and ADO Indices in Predicting COPD-Related Medical Costs

Background and Objectives:The ADO (age, dyspnea, and airflow obstruction) and BODE (body mass index, airflow obstruction, dyspnea, and exercise capacity) indices are often used to evaluate the prognoses for chronic obstructive pulmonary disease(COPD); however, an index suitable for predicting medical costs has yet to be developed. Materials and Methods: We investigated the BODE and ADO indices to predict medical costs and compare their predictive power. A total of 396 patients with COPD were retrospectively enrolled. Results: For hospitalization frequencies, BODE was R2 = 0.093 (p < 0.001), and ADO was R2 = 0.065 (p < 0.001); for hospitalization days, BODE was R2 = 0.128 (p < 0.001), and ADO was R2 = 0.071 (p < 0.001); for hospitalization expenses, BODE was R2 = 0.020 (p = 0.047), and ADO was R2 = 0.012 (p = 0.179). BODE and ADO did not differ significantly in the numbers of outpatient visits (BODE, R2 = 0.012, p = 0.179; ADO, R2 = 0.017, p = 0.082); outpatient medical expenses (BODE, R2 = 0.012, p = 0.208; ADO, R2 = 0.008, p = 0.364); and total medical costs (BODE, R2 = 0.018, p = 0.072; ADO, R2 = 0.016, p = 0.098). In conclusion, BODE and ADO indices were correlated with hospitalization frequency and hospitalization days. However, the BODE index exhibits slightly better predictive accuracy than the ADO index in these items.

The Impact of the Age, Dyspnoea, and Airflow Obstruction (ADO) Index on the Medical Burden of Chronic Obstructive Pulmonary Disease (COPD)

There are currently no good indicators that can be used to predict the medical expenses of chronic obstructive pulmonary disease (COPD). This was a retrospective study that focused on the correlation between the age, dyspnoea, and airflow obstruction (ADO) index and the Charlson comorbidity index (CCI) on the medical burden in COPD patients, specifically, those of patients with complete ADO index and CCI data in our hospital from January 2015 to December 2016. Of the 396 patients with COPD who met the inclusion criteria, 382 (96.5%) were male, with an average age of 71.3 ± 8.4 years. Healthcare resource utilisation was positively correlated with the ADO index. A significant association was found between the ADO index and CCI of COPD patients (p < 0.001). In-hospitalization expenses were positively correlated with the CCI (p < 0.001). Under the same CCI, the higher the ADO score, the higher the hospitalisation expenses. The ADO quartiles were positively correlated with the number of hospitalisations (p < 0.001), hospitalisation days (p < 0.001), hospitalisation expenses (p = 0.03), and total medical expenses (p = 0.037). Findings from this study show that the ADO index can predict the medical burden of COPD.

Chronic obstructive pulmonary disease risk assessment tools: is one better than the others?

PURPOSE OF REVIEW

Risk assessment tools are essential in COPD care to help clinicians identify patients at higher risk of accelerated lung function decline, respiratory exacerbations, hospitalizations, and death.

RECENT FINDINGS

Conventional methods of assessing risk have focused on spirometry, patient-reported symptoms, functional status, and a combination of these tools in composite indices. More recently, qualitatively and quantitatively assessed chest imaging findings, such as emphysema, large and small airways disease, and pulmonary vascular abnormalities have been associated with poor long-term outcomes in COPD patients. Although several blood and sputum biomarkers have been investigated for risk assessment in COPD, most still warrant further validation. Finally, novel remote digital monitoring technologies may be valuable to predict exacerbations but their large-scale performance, ease of implementation, and cost effectiveness remain to be determined.

SUMMARY

Given the complex heterogeneity of COPD, any single metric is unlikely to fully capture the risk of poor long-term outcomes. Therefore, clinicians should review all available clinical data, including spirometry, symptom severity, functional status, chest imaging, and bloodwork, to guide personalized preventive care of COPD patients. The potential of machine learning tools and remote monitoring technologies to refine COPD risk assessment is promising but remains largely untapped pending further investigation.

Uptake of Clinical Prognostic Tools in COPD Exacerbations Requiring Hospitalisation

Clinical prognostic tools are used to objectively predict outcomes in many fields of medicine. Whilst over 400 have been developed for use in chronic obstructive pulmonary disease (COPD), only a minority have undergone full external validation and just one, the DECAF score, has undergone an implementation study supporting use in clinical practice. Little is known about how such tools are used in the UK. We distributed surveys at two time points, in 2017 and 2019, to hospitals included in the Royal College of Physicians of London national COPD secondary care audit program. The survey assessed the use of prognostic tools in routine care of hospitalized COPD patients. Hospital response rates were 71/196 in 2017 and 72/196 in 2019. The use of the DECAF and PEARL scores more than doubled in decisions about unsupported discharge (7%-15.3%), admission avoidance (8.1%-17%) and readmission avoidance (4.8%-13.1%); it more than tripled (8.8%-27.8%) in decisions around hospital-at-home or early supported discharge schemes. In other areas, routine use of clinical prognostic tools was uncommon. In palliative care decisions, the use of the Gold Standards Framework Prognostic Indicator Guidance fell (5.6%-1.4%). In 2017, 43.7% of hospitals used at least one clinical prognostic tool in routine COPD care, increasing to 52.1% in 2019. Such tools can help challenge prognostic pessimism and improve care. To integrate these further into routine clinical care, future research should explore current barriers to their use and focus on implementation studies.Supplemental data for this article is available online at https://dx.doi.org/10.1080/15412555.2021.1959540.