1
|
Zeng S, Arjomandi M, Luo G. Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. JMIR Med Inform 2022; 10:e33043. [PMID: 35212634 PMCID: PMC8917430 DOI: 10.2196/33043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Revised: 11/15/2021] [Accepted: 01/02/2022] [Indexed: 11/13/2022] Open
Abstract
Background Chronic obstructive pulmonary disease (COPD) is a major cause of death and places a heavy burden on health care. To optimize the allocation of precious preventive care management resources and improve the outcomes for high-risk patients with COPD, we recently built the most accurate model to date to predict severe COPD exacerbations, which need inpatient stays or emergency department visits, in the following 12 months. Our model is a machine learning model. As is the case with most machine learning models, our model does not explain its predictions, forming a barrier for clinical use. Previously, we designed a method to automatically provide rule-type explanations for machine learning predictions and suggest tailored interventions with no loss of model performance. This method has been tested before for asthma outcome prediction but not for COPD outcome prediction. Objective This study aims to assess the generalizability of our automatic explanation method for predicting severe COPD exacerbations. Methods The patient cohort included all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019. In a secondary analysis of 43,576 data instances, we used our formerly developed automatic explanation method to automatically explain our model’s predictions and suggest tailored interventions. Results Our method explained the predictions for 97.1% (100/103) of the patients with COPD whom our model correctly predicted to have severe COPD exacerbations in the following 12 months and the predictions for 73.6% (134/182) of the patients with COPD who had ≥1 severe COPD exacerbation in the following 12 months. Conclusions Our automatic explanation method worked well for predicting severe COPD exacerbations. After further improving our method, we hope to use it to facilitate future clinical use of our model. International Registered Report Identifier (IRRID) RR2-10.2196/13783
Collapse
Affiliation(s)
- Siyang Zeng
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Mehrdad Arjomandi
- Medical Service, San Francisco Veterans Affairs Medical Center, San Francisco, CA, United States.,Department of Medicine, University of California, San Francisco, CA, United States
| | - Gang Luo
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| |
Collapse
|
2
|
Giguere A, Holroyd-Leduc JM, Straus SE, Urquhart R, Turcotte V, Durand PJ, Turgeon A. Prioritization of indicators of the quality of care provided to older adults with frailty by key stakeholders from five canadian provinces. BMC Geriatr 2022; 22:149. [PMID: 35197016 PMCID: PMC8864862 DOI: 10.1186/s12877-022-02843-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2021] [Accepted: 02/15/2022] [Indexed: 11/10/2022] Open
Abstract
Background To meet the needs of older adults with frailty better, it is essential to understand which aspects of care are important from their perspective. We therefore sought to assess the importance of a set of quality indicators (QI) for monitoring outcomes in this population. Methods In this mixed-method study, key stakeholders completed a survey on the importance of 36 QIs, and then explained their ratings in a semi-structured interview. Stakeholders included older adults with frailty and their caregivers, healthcare providers (HCPs), and healthcare administrators or policy/decision makers (DMs). We conducted descriptive statistical analyses of quantitative variables, and deductive thematic qualitative analyses of interview transcripts. Results The 42 participants (8 older adults, 18 HCPs, and 16 DMs) rated six QIs as more important: increasing the patients’ quality of life; increasing healthcare staff skills; decreasing patients’ symptoms; decreasing family caregiver burden; increasing patients’ satisfaction with care; and increasing family doctor continuity of care. Conclusions Key stakeholders prioritized QIs that focus on outcomes targeted to patients and caregivers, whereas the current healthcare systems generally focus on processes of care. Quality improvement initiatives should therefore take better account of aspects of care that are important for older adults with frailty, such as having a chance to express their individual goals of care, receiving quality communications from HCPs, or monitoring symptoms that they might not spontaneously describe. Our results point to the need for patient-centred care that is oriented toward quality of life for older adults with frailty. Supplementary Information The online version contains supplementary material available at 10.1186/s12877-022-02843-9.
Collapse
Affiliation(s)
- Anik Giguere
- Department of Family Medicine and Emergency Medicine, Université Laval, Quebec, Canada. .,Quebec Excellence Centre on Aging, Quebec, Canada. .,VITAM - Research Centre on Sustainable Health (Centre de recherche en santé durable), 2480, chemin de la Canardière, QC, G1J 0A4, Québec, Canada.
| | | | - Sharon E Straus
- Department of Medicine, University of Toronto, Toronto, Canada
| | - Robin Urquhart
- Department of Community Health and Epidemiology, Dalhousie University, Halifax, Canada
| | | | - Pierre J Durand
- Department of Social and Preventive Medicine, Université Laval, Quebec, Canada
| | - Alexis Turgeon
- Population Health and Optimal Health Practices Research Unit, Division of Critical Care Medicine, CHU de Quebec - Université Laval Research Centre, Université Laval, Quebec, Canada
| |
Collapse
|
3
|
Zeng S, Arjomandi M, Tong Y, Liao ZC, Luo G. Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. J Med Internet Res 2022; 24:e28953. [PMID: 34989686 PMCID: PMC8778560 DOI: 10.2196/28953] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2021] [Revised: 07/03/2021] [Accepted: 11/19/2021] [Indexed: 12/14/2022] Open
Abstract
Background Chronic obstructive pulmonary disease (COPD) poses a large burden on health care. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause an irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target patients at high risk for preventive care management to reduce severe COPD exacerbations and improve outcomes. Objective The aim of this study is to develop a more accurate model to predict severe COPD exacerbations. Methods We examined all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019 and identified 278 candidate features. By performing secondary analysis on 43,576 University of Washington Medicine data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD. Results The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 9.99% (752/7529) of the patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6801/7529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6698/7347). Conclusions Our model provided a more accurate prediction of severe COPD exacerbations in the next year compared with prior published models. After further improvement of its performance measures (eg, by adding features extracted from clinical notes), our model could be used in a decision support tool to guide the identification of patients with COPD and at high risk for care management to improve outcomes. International Registered Report Identifier (IRRID) RR2-10.2196/13783
Collapse
Affiliation(s)
- Siyang Zeng
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Mehrdad Arjomandi
- Medical Service, San Francisco Veterans Affairs Medical Center, San Francisco, CA, United States.,Department of Medicine, University of California, San Francisco, CA, United States
| | - Yao Tong
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Zachary C Liao
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Gang Luo
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| |
Collapse
|
4
|
Predicting Severe Chronic Obstructive Pulmonary Disease Exacerbations. Developing a Population Surveillance Approach with Administrative Data. Ann Am Thorac Soc 2021; 17:1069-1076. [PMID: 32383971 DOI: 10.1513/annalsats.202001-070oc] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022] Open
Abstract
Rationale: Automatic prediction algorithms based on routinely collected health data may be able to identify patients at high risk for hospitalizations related to acute exacerbations of chronic obstructive pulmonary disease (COPD).Objectives: To conduct a proof-of-concept study of a population surveillance approach for identifying individuals at high risk of severe COPD exacerbations.Methods: We used British Columbia's administrative health databases (1997-2016) to identify patients with diagnosed COPD. We used data from the previous 6 months to predict the risk of severe exacerbation in the next 2 months after a randomly selected index date. We applied statistical and machine-learning algorithms for risk prediction (logistic regression, random forest, neural network, and gradient boosting). We used calibration plots and receiver operating characteristic curves to evaluate model performance based on a randomly chosen future date at least 1 year later (temporal validation).Results: There were 108,433 patients in the development dataset and 113,786 in the validation dataset; of these, 1,126 and 1,136, respectively, were hospitalized for COPD within their outcome windows. The best prediction algorithm (gradient boosting) had an area under the receiver operating characteristic curve of 0.82 (95% confidence interval, 0.80-0.83), which was significantly higher than the corresponding value for the model with exacerbation history as the only predictor (current standard of care: 0.68). The predicted risk scores were well calibrated in the validation dataset.Conclusions: Imminent COPD-related hospitalizations can be predicted with good accuracy using administrative health data. This model may be used as a means to target high-risk patients for preventive exacerbation therapies.
Collapse
|
5
|
Hartford W, Asgarova S, MacDonald G, Berger M, Cristancho S, Nimmon L. Macro and meso level influences on distributed integrated COPD care delivery: a social network perspective. BMC Health Serv Res 2021; 21:491. [PMID: 34024272 PMCID: PMC8141100 DOI: 10.1186/s12913-021-06532-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2020] [Accepted: 05/10/2021] [Indexed: 11/12/2022] Open
Abstract
Background Care guidelines for people with chronic obstructive pulmonary disease (COPD) recommend an integrated approach for holistic, flexible, and tailored interventions. Continuity of care is also emphasised. However, many patients with COPD experience fragmented care. Discontinuities in healthcare and related social services are likely to result in disjointed rather than integrated care which can negatively affect patient health outcomes. The purpose of this qualitative study was to improve our understanding of, and how, contextual features pertaining to structures and processes of COPD integrated care influence delivery of care within patients’ healthcare networks. Methods We conducted individual interviews with 28 participants (9 patients, 16 healthcare professionals, and 3 spousal caregivers). Participants were recruited through the lung clinic at a city hospital in western Canada. We employed a social network paradigm to analyse and interpret the data. Results The analysis revealed an overarching theme of fragmented COPD care with two sub-themes: (1) Funding shortfalls and availability of resources, and (2) Dis(mis)connected communication pathways. The overarching theme depicts variations, delays, and discontinuities in patient care. The sub-themes describe how macro level influences and meso level shortfalls were perceived to influence the availability of respiratory care resources that contributed to fragmented COPD care. Conclusions Employing a social network lens drew particular attention to family physicians’ pivotal role in delivering community-based COPD care. While an integrated approach to care is recommended by care guidelines, institutional and organizational structures and processes, such as financial and communication structures, may inhibit delivery of integrated care. Thus, macro and meso level structures and processes have the potential to shape patient care by constraining family physicians’ purposive and communication actions necessary for facilitating an integrated distributed approach to care. We propose a context of care which fosters a context for family physicians’ delivery of patient-centered care. Integrated care delivery may improve patients’ wellbeing and alleviate financial constraints on the healthcare system.
Collapse
Affiliation(s)
- Wendy Hartford
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.
| | - Sevinj Asgarova
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.,University of British Columbia, Vancouver, Canada.,Centre for Health Education Scholarship, Faculty of Medicine, University of British Columbia, 429-2194, Health Sciences Mall, V6T 1Z3, Vancouver, Canada
| | - Graham MacDonald
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.,University of British Columbia, Vancouver, Canada
| | - Mary Berger
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.,Dalhousie University, Halifax, Canada
| | - Sayra Cristancho
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.,Centre for Education Research and Innovation, Schulich School of Medicine and Dentistry, University of Western Ontario Canada, Medical Sciences Building, Suite 100, N6G 2V4, London, Ontario, Canada
| | - Laura Nimmon
- Department of Occupational Science and Occupational Therapy, Faculty of Medicine, University of British Columbia, 2211 Wesbrook Mall T325, BC, V6T 2B5, Vancouver, Canada.,Centre for Health Education Scholarship, Faculty of Medicine, University of British Columbia, 429-2194, Health Sciences Mall, V6T 1Z3, Vancouver, Canada
| |
Collapse
|
6
|
Luo G, Stone BL, Sheng X, He S, Koebnick C, Nkoy FL. Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis. JMIR Res Protoc 2021; 10:e27065. [PMID: 34003134 PMCID: PMC8170556 DOI: 10.2196/27065] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2021] [Revised: 04/12/2021] [Accepted: 04/19/2021] [Indexed: 12/05/2022] Open
Abstract
Background Asthma and chronic obstructive pulmonary disease (COPD) impose a heavy burden on health care. Approximately one-fourth of patients with asthma and patients with COPD are prone to exacerbations, which can be greatly reduced by preventive care via integrated disease management that has a limited service capacity. To do this well, a predictive model for proneness to exacerbation is required, but no such model exists. It would be suboptimal to build such models using the current model building approach for asthma and COPD, which has 2 gaps due to rarely factoring in temporal features showing early health changes and general directions. First, existing models for other asthma and COPD outcomes rarely use more advanced temporal features, such as the slope of the number of days to albuterol refill, and are inaccurate. Second, existing models seldom show the reason a patient is deemed high risk and the potential interventions to reduce the risk, making already occupied clinicians expend more time on chart review and overlook suitable interventions. Regular automatic explanation methods cannot deal with temporal data and address this issue well. Objective To enable more patients with asthma and patients with COPD to obtain suitable and timely care to avoid exacerbations, we aim to implement comprehensible computational methods to accurately predict proneness to exacerbation and recommend customized interventions. Methods We will use temporal features to accurately predict proneness to exacerbation, automatically find modifiable temporal risk factors for every high-risk patient, and assess the impact of actionable warnings on clinicians’ decisions to use integrated disease management to prevent proneness to exacerbation. Results We have obtained most of the clinical and administrative data of patients with asthma from 3 prominent American health care systems. We are retrieving other clinical and administrative data, mostly of patients with COPD, needed for the study. We intend to complete the study in 6 years. Conclusions Our results will help make asthma and COPD care more proactive, effective, and efficient, improving outcomes and saving resources. International Registered Report Identifier (IRRID) PRR1-10.2196/27065
Collapse
Affiliation(s)
- Gang Luo
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States
| | - Bryan L Stone
- Department of Pediatrics, University of Utah, Salt Lake City, UT, United States
| | - Xiaoming Sheng
- College of Nursing, University of Utah, Salt Lake City, UT, United States
| | - Shan He
- Care Transformation and Information Systems, Intermountain Healthcare, West Valley City, UT, United States
| | - Corinna Koebnick
- Department of Research & Evaluation, Kaiser Permanente Southern California, Pasadena, CA, United States
| | - Flory L Nkoy
- Department of Pediatrics, University of Utah, Salt Lake City, UT, United States
| |
Collapse
|
7
|
Bandurska E, Damps-Konstańska I, Popowski P, Jędrzejczyk T, Janowiak P, Świętnicka K, Zarzeczna-Baran M, Jassem E. Cost-Effectiveness Analysis of Integrated Care in Management of Advanced Chronic Obstructive Pulmonary Disease (COPD). Med Sci Monit 2019; 25:2879-2885. [PMID: 31002103 PMCID: PMC6486702 DOI: 10.12659/msm.913358] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2018] [Accepted: 01/02/2019] [Indexed: 11/09/2022] Open
Abstract
BACKGROUND Chronic obstructive pulmonary disease (COPD) is a common disease that occurs all over the world. Models of care, initially accessed from the clinical point of view, must also be evaluated in terms of their economic effectiveness, as health care systems are limited. The Integrated Care Model (ICM) is a procedure dedicated to patients suffering from advanced COPD that offers home-oriented support from a multidisciplinary team. The main aim of the present study was to evaluate the cost-effectiveness of the ICM. MATERIAL AND METHODS We included 44 patients in the study (31 males, 13 females) with an average age 72 years (Me=71). Costs of care were estimated based on data received from public payer records and included general costs, COPD-related costs, and exacerbation-related costs. To evaluate cost-effectiveness, cost-effectiveness analysis (CEA) was used. The incremental cost-effectiveness ratio (ICER) was calculated based on changes in health care resources utilization and the value of costs observed in 2 consecutive 6-month periods before and after introducing ICM. RESULTS Costs of care of all types decreased after introducing ICM. Demand for ambulatory visits changed significantly (p=0.037) together with a substantial decrease in the number of emergency department appointments and hospitalizations (p=0.033). ICER was more profitable for integrated care than for standard care when assessing costs of avoiding negative parameters such as hospitalizations (-227 EUR), exacerbations-related hospitalizations (-312 EUR), or emergency procedures (-119 EUR). CONCLUSIONS ICM is a procedure that meets the criteria of cost-effectiveness. It allows for avoiding negative parameters such as unplanned hospitalizations with higher economic effectiveness than the standard type of care used in managing COPD.
Collapse
Affiliation(s)
- Ewa Bandurska
- Department of Public Health and Social Medicine, Medical University of Gdańsk, Gdańsk, Poland
| | | | - Piotr Popowski
- Department of Public Health and Social Medicine, Medical University of Gdańsk, Gdańsk, Poland
| | | | - Piotr Janowiak
- Department of Allergology, Medical University of Gdańsk, Gdańsk, Poland
| | | | - Marzena Zarzeczna-Baran
- Department of Public Health and Social Medicine, Medical University of Gdańsk, Gdańsk, Poland
| | - Ewa Jassem
- Department of Allergology, Medical University of Gdańsk, Gdańsk, Poland
| |
Collapse
|
8
|
Onk D, Özçelik F, Onk OA, Günay M, Akarsu Ayazoğlu T, Ünver E. Assessment of Renal and Hepatic Tissue-Protective Effects of N-Acetylcysteine via Ammonia Metabolism: A Prospective Randomized Study. Med Sci Monit 2018. [PMID: 29540661 PMCID: PMC5866733 DOI: 10.12659/msm.908172] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/13/2023] Open
Abstract
Background The present study sought to assess the renal and liver protective effect of N-acetylcysteine through NH3 and urea metabolism in patients with chronic obstructive pulmonary disease who were scheduled for coronary artery bypass grafting surgery. Material/Methods Patients with chronic obstructive pulmonary disease (COPD) who were scheduled for coronary artery bypass grafting were divided into 2 groups so as to receive (Group 1, n=35) or not receive (Group 2, n=35) 900 mg/day of n-acetylcysteine for 7 days before the operation starting from their admission to the service by a pulmonologist with the purpose of treating COPD until the day of surgery. Both groups were subjected to the same anesthesia protocol. Blood samples were taken preoperatively, within the first 15th minute following cessation of the cardiopulmonary bypass, at postoperative 24th hour, and at postoperative 48th hour. Blood tests included ammonia (NH3), lactate, blood urea nitrogen, creatinine, aspartate transaminase (AST), alanine transaminase (ALT), alkaline phosphatase (ALP), troponin I (Tn I), and creatinine kinase-muscle brain (CKMB). Results There was a significant difference between the groups’ NH3 and lactate levels after cardiopulmonary bypass, postoperative 24th hour, and postoperative 48th hour (respectively, NH3: 39.0±8.8 vs. 55.4±19.6 and 40.1±8.4 vs. 53.2±20.2 mcg/dl, lactate: 1.7±0.9 vs. 2.1±1.2 and 1.2±0.5 vs. 1.8±1.4 mmol/L; p<0.01). Creatinine and BUN levels in Group 2 were found to be significantly higher at the postoperative 48th hour compared to the levels of Group 1 (P<0.05). Conclusions N-acetylcysteine pretreatment appears to improve renal and hepatic functions through regulation of ammonia and nitrogen metabolism and reduction of lactate in patients with chronic obstructive pulmonary disease who undergo coronary artery bypass grafting surgery. We found that N-acetylcysteine improved kidney and/or liver functions.
Collapse
Affiliation(s)
- Didem Onk
- Department of Anesthesiology, Faculty of Medicine, Erzincan University, Erzincan, Turkey
| | - Fatih Özçelik
- Department of Medical Biochemistry, Sultan Abdulhamid Han Training Hospital, University of Health Sciences, Istanbul, Turkey
| | - Oruç Alper Onk
- Department of Cardiovascular Surgery, Faculty of Medicine, Erzincan University, Erzincan, Turkey
| | - Murat Günay
- Department of Biochemistry, Faculty of Medicine, Erzincan University, Erzincan, Turkey
| | - Tülin Akarsu Ayazoğlu
- Department of Anesthesiology, Goztepe Training and Research Hospital, Istanbul, Turkey
| | - Ethem Ünver
- Department of Chest Diseases, Faculty of Medicine, Erzincan University, Erzincan, Turkey
| |
Collapse
|