通过机器学习了解 COVID-19 严重后果的风险：一项关于美国大型医疗保健系统中免疫介导的炎症性疾病、免疫调节药物和合并症的回顾性队列研究

IF 23.8 1区医学 Q1 MEDICAL INFORMATICS

Lancet Digital Health Pub Date : 2024-04-24 DOI:10.1016/S2589-7500(24)00021-9

Qi Wei PhD , Prof Philip J Mease MD , Michael Chiorean MD , Lulu Iles-Shih MD , Wanessa F Matos MD , Andrew Baumgartner PhD , Sevda Molani PhD , Yeon Mi Hwang MSc , Basazin Belhu BSc , Alexandra Ralevski PhD , Jennifer Hadlock MD

{"title":"通过机器学习了解 COVID-19 严重后果的风险：一项关于美国大型医疗保健系统中免疫介导的炎症性疾病、免疫调节药物和合并症的回顾性队列研究","authors":"Qi Wei PhD , Prof Philip J Mease MD , Michael Chiorean MD , Lulu Iles-Shih MD , Wanessa F Matos MD , Andrew Baumgartner PhD , Sevda Molani PhD , Yeon Mi Hwang MSc , Basazin Belhu BSc , Alexandra Ralevski PhD , Jennifer Hadlock MD","doi":"10.1016/S2589-7500(24)00021-9","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>In the context of immune-mediated inflammatory diseases (IMIDs), COVID-19 outcomes are incompletely understood and vary considerably depending on the patient population studied. We aimed to analyse severe COVID-19 outcomes and to investigate the effects of the pandemic time period and the risks associated with individual IMIDs, classes of immunomodulatory medications (IMMs), chronic comorbidities, and COVID-19 vaccination status.</p></div><div><h3>Methods</h3><p>In this retrospective cohort study, clinical data were derived from the electronic health records of an integrated health-care system serving patients in 51 hospitals and 1085 clinics across seven US states (Providence St Joseph Health). Data were observed for patients (no age restriction) with one or more IMID and for unmatched controls without IMIDs. COVID-19 was identified with a positive nucleic acid amplification test result for SARS-CoV-2. Two timeframes were analysed: March 1, 2020–Dec 25, 2021 (pre-omicron period), and Dec 26, 2021–Aug 30, 2022 (omicron-predominant period). Primary outcomes were hospitalisation, mechanical ventilation, and mortality in patients with COVID-19. Factors, including IMID diagnoses, comorbidities, long-term use of IMMs, and COVID-19 vaccination status, were analysed with multivariable logistic regression (LR) and extreme gradient boosting (XGB).</p></div><div><h3>Findings</h3><p>Of 2 167 656 patients tested for SARS-CoV-2, 290 855 (13·4%) had confirmed COVID-19: 15 397 (5·3%) patients with IMIDs and 275 458 (94·7%) without IMIDs. In the pre-omicron period, 169 993 (11·2%) of 1 517 295 people who were tested for COVID-19 tested positive, of whom 23 330 (13·7%) were hospitalised, 1072 (0·6%) received mechanical ventilation, and 5294 (3·1%) died. Compared with controls, patients with IMIDs and COVID-19 had higher rates of hospitalisation (1176 [14·6%] <em>vs</em> 22 154 [13·7%]; p=0·024) and mortality (314 [3·9%] <em>vs</em> 4980 [3·1%]; p<0·0001). In the omicron-predominant period, 120 862 (18·6%) of 650 361 patients tested positive for COVID-19, of whom 14 504 (12·0%) were hospitalised, 567 (0·5%) received mechanical ventilation, and 2001 (1·7%) died. Compared with controls, patients with IMIDs and COVID-19 (7327 [17·3%] of 42 249) had higher rates of hospitalisation (13 422 [11·8%] <em>vs</em> 1082 [14·8%]; p<0·0001) and mortality (1814 [1·6%] <em>vs</em> 187 [2·6%]; p<0·0001). Age was a risk factor for worse outcomes (adjusted odds ratio [OR] from 2·1 [95% CI 2·0–2·1]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001), whereas COVID-19 vaccination (from 0·082 [0·080–0·085]; p<0·0001 to 0·52 [0·50–0·53]; p<0·0001) and booster vaccination (from 2·1 [2·0–2·2]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001) status were associated with better outcomes. Seven chronic comorbidities were significant risk factors during both time periods for all three outcomes: atrial fibrillation, coronary artery disease, heart failure, chronic kidney disease, chronic obstructive pulmonary disease, chronic liver disease, and cancer. Two IMIDs, asthma (adjusted OR from 0·33 [0·32–0·34]; p<0·0001 to 0·49 [0·48–0·51]; p<0·0001) and psoriasis (from 0·52 [0·48–0·56] to 0·80 [0·74–0·87]; p<0·0001), were associated with a reduced risk of severe outcomes. IMID diagnoses did not appear to be significant risk factors themselves, but results were limited by small sample size, and vasculitis had high feature importance in LR. IMMs did not appear to be significant, but less frequently used IMMs were limited by sample size. XGB outperformed LR, with the area under the receiver operating characteristic curve for models across different time periods and outcomes ranging from 0·77 to 0·92.</p></div><div><h3>Interpretation</h3><p>Our results suggest that age, chronic comorbidities, and not being fully vaccinated might be greater risk factors for severe COVID-19 outcomes in patients with IMIDs than the use of IMMs or the IMIDs themselves. Overall, there is a need to take age and comorbidities into consideration when developing COVID-19 guidelines for patients with IMIDs. Further research is needed for specific IMIDs (including IMID severity at the time of SARS-CoV-2 infection) and IMMs (considering dosage and timing before a patient's first COVID-19 infection).</p></div><div><h3>Funding</h3><p>Pfizer, Novartis, Janssen, and the National Institutes of Health.</p></div>","PeriodicalId":48534,"journal":{"name":"Lancet Digital Health","volume":"6 5","pages":"Pages e309-e322"},"PeriodicalIF":23.8000,"publicationDate":"2024-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589750024000219/pdfft?md5=7f87bbc61788e0cf2d2147dbbc0ff7e1&pid=1-s2.0-S2589750024000219-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Machine learning to understand risks for severe COVID-19 outcomes: a retrospective cohort study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US health-care system\",\"authors\":\"Qi Wei PhD , Prof Philip J Mease MD , Michael Chiorean MD , Lulu Iles-Shih MD , Wanessa F Matos MD , Andrew Baumgartner PhD , Sevda Molani PhD , Yeon Mi Hwang MSc , Basazin Belhu BSc , Alexandra Ralevski PhD , Jennifer Hadlock MD\",\"doi\":\"10.1016/S2589-7500(24)00021-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><p>In the context of immune-mediated inflammatory diseases (IMIDs), COVID-19 outcomes are incompletely understood and vary considerably depending on the patient population studied. We aimed to analyse severe COVID-19 outcomes and to investigate the effects of the pandemic time period and the risks associated with individual IMIDs, classes of immunomodulatory medications (IMMs), chronic comorbidities, and COVID-19 vaccination status.</p></div><div><h3>Methods</h3><p>In this retrospective cohort study, clinical data were derived from the electronic health records of an integrated health-care system serving patients in 51 hospitals and 1085 clinics across seven US states (Providence St Joseph Health). Data were observed for patients (no age restriction) with one or more IMID and for unmatched controls without IMIDs. COVID-19 was identified with a positive nucleic acid amplification test result for SARS-CoV-2. Two timeframes were analysed: March 1, 2020–Dec 25, 2021 (pre-omicron period), and Dec 26, 2021–Aug 30, 2022 (omicron-predominant period). Primary outcomes were hospitalisation, mechanical ventilation, and mortality in patients with COVID-19. Factors, including IMID diagnoses, comorbidities, long-term use of IMMs, and COVID-19 vaccination status, were analysed with multivariable logistic regression (LR) and extreme gradient boosting (XGB).</p></div><div><h3>Findings</h3><p>Of 2 167 656 patients tested for SARS-CoV-2, 290 855 (13·4%) had confirmed COVID-19: 15 397 (5·3%) patients with IMIDs and 275 458 (94·7%) without IMIDs. In the pre-omicron period, 169 993 (11·2%) of 1 517 295 people who were tested for COVID-19 tested positive, of whom 23 330 (13·7%) were hospitalised, 1072 (0·6%) received mechanical ventilation, and 5294 (3·1%) died. Compared with controls, patients with IMIDs and COVID-19 had higher rates of hospitalisation (1176 [14·6%] <em>vs</em> 22 154 [13·7%]; p=0·024) and mortality (314 [3·9%] <em>vs</em> 4980 [3·1%]; p<0·0001). In the omicron-predominant period, 120 862 (18·6%) of 650 361 patients tested positive for COVID-19, of whom 14 504 (12·0%) were hospitalised, 567 (0·5%) received mechanical ventilation, and 2001 (1·7%) died. Compared with controls, patients with IMIDs and COVID-19 (7327 [17·3%] of 42 249) had higher rates of hospitalisation (13 422 [11·8%] <em>vs</em> 1082 [14·8%]; p<0·0001) and mortality (1814 [1·6%] <em>vs</em> 187 [2·6%]; p<0·0001). Age was a risk factor for worse outcomes (adjusted odds ratio [OR] from 2·1 [95% CI 2·0–2·1]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001), whereas COVID-19 vaccination (from 0·082 [0·080–0·085]; p<0·0001 to 0·52 [0·50–0·53]; p<0·0001) and booster vaccination (from 2·1 [2·0–2·2]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001) status were associated with better outcomes. Seven chronic comorbidities were significant risk factors during both time periods for all three outcomes: atrial fibrillation, coronary artery disease, heart failure, chronic kidney disease, chronic obstructive pulmonary disease, chronic liver disease, and cancer. Two IMIDs, asthma (adjusted OR from 0·33 [0·32–0·34]; p<0·0001 to 0·49 [0·48–0·51]; p<0·0001) and psoriasis (from 0·52 [0·48–0·56] to 0·80 [0·74–0·87]; p<0·0001), were associated with a reduced risk of severe outcomes. IMID diagnoses did not appear to be significant risk factors themselves, but results were limited by small sample size, and vasculitis had high feature importance in LR. IMMs did not appear to be significant, but less frequently used IMMs were limited by sample size. XGB outperformed LR, with the area under the receiver operating characteristic curve for models across different time periods and outcomes ranging from 0·77 to 0·92.</p></div><div><h3>Interpretation</h3><p>Our results suggest that age, chronic comorbidities, and not being fully vaccinated might be greater risk factors for severe COVID-19 outcomes in patients with IMIDs than the use of IMMs or the IMIDs themselves. Overall, there is a need to take age and comorbidities into consideration when developing COVID-19 guidelines for patients with IMIDs. Further research is needed for specific IMIDs (including IMID severity at the time of SARS-CoV-2 infection) and IMMs (considering dosage and timing before a patient's first COVID-19 infection).</p></div><div><h3>Funding</h3><p>Pfizer, Novartis, Janssen, and the National Institutes of Health.</p></div>\",\"PeriodicalId\":48534,\"journal\":{\"name\":\"Lancet Digital Health\",\"volume\":\"6 5\",\"pages\":\"Pages e309-e322\"},\"PeriodicalIF\":23.8000,\"publicationDate\":\"2024-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2589750024000219/pdfft?md5=7f87bbc61788e0cf2d2147dbbc0ff7e1&pid=1-s2.0-S2589750024000219-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Lancet Digital Health\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2589750024000219\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICAL INFORMATICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Lancet Digital Health","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589750024000219","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICAL INFORMATICS","Score":null,"Total":0}

引用次数: 0

摘要

背景在免疫介导的炎症性疾病（IMIDs）中，COVID-19 的结果尚不完全清楚，而且根据所研究的患者人群的不同而有很大差异。我们旨在分析 COVID-19 的严重后果，并研究大流行时期的影响以及与单个 IMID、免疫调节药物 (IMM)类别、慢性合并症和 COVID-19 疫苗接种状况相关的风险。方法在这项回顾性队列研究中，临床数据来自一个综合医疗保健系统的电子健康记录，该系统为美国 7 个州 51 家医院和 1085 家诊所的患者提供服务（Providence St Joseph Health）。研究人员观察了患有一种或多种IMID的患者（无年龄限制）和未患有IMID的非匹配对照组的数据。如果 SARS-CoV-2 核酸扩增检测结果呈阳性，则可确定 COVID-19。分析了两个时间段：2020 年 3 月 1 日至 2021 年 12 月 25 日（前微粒体时期）和 2021 年 12 月 26 日至 2022 年 8 月 30 日（微粒体主导时期）。主要结果是 COVID-19 患者的住院、机械通气和死亡率。采用多变量逻辑回归（LR）和极梯度增强（XGB）分析了包括 IMID 诊断、合并症、长期使用 IMMs 和 COVID-19 疫苗接种情况在内的各种因素：其中 15 397 人（5-3%）有 IMID，275 458 人（94-7%）无 IMID。在前微粒体时期，在接受 COVID-19 检测的 1 517 295 人中，有 169 993 人（11-2%）检测结果呈阳性，其中 23 330 人（13-7%）住院治疗，1072 人（0-6%）接受机械通气，5294 人（3-1%）死亡。与对照组相比，IMIDs 和 COVID-19 患者的住院率（1176 [14-6%] vs 22 154 [13-7%]；p=0-024）和死亡率（314 [3-9%] vs 4980 [3-1%]；p<0-0001）均较高。在欧米伽马主导期，650 361 名患者中有 120 862 人（18-6%）的 COVID-19 检测呈阳性，其中 14 504 人（12-0%）住院治疗，567 人（0-5%）接受机械通气，2001 人（1-7%）死亡。与对照组相比，IMIDs 和 COVID-19 患者（42 249 例中的 7327 例 [17-3%] ）的住院率（13 422 例 [11-8%] vs 1082 例 [14-8%]；p<0-0001）和死亡率（1814 例 [1-6%] vs 187 例 [2-6%]；p<0-0001）均较高。年龄是导致较差结果的风险因素（调整后的比值比 [OR] 从 2-1 [95% CI 2-0-2-1]; p<0-0001 到 3-0 [2-9-3-0]; p<0-0001），而接种 COVID-19 疫苗（从 0-082 [0-080-0-085]；p<0-0001到0-52 [0-50-0-53]; p<0-0001）和加强接种（从2-1 [2-0-2-2]; p<0-0001到3-0 [2-9-3-0]; p<0-0001）状态与更好的预后相关。在这两个时间段内，有七种慢性合并症是影响所有三种结果的重要风险因素：心房颤动、冠心病、心力衰竭、慢性肾病、慢性阻塞性肺病、慢性肝病和癌症。哮喘（调整后 OR 从 0-33 [0-32-0-34]; p<0-0001 到 0-49 [0-48-0-51]; p<0-0001）和银屑病（从 0-52 [0-48-0-56] 到 0-80 [0-74-0-87]; p<0-0001）这两种 IMID 与严重后果的风险降低有关。IMID诊断本身似乎并不是重要的风险因素，但由于样本量较小，结果受到限制，而且脉管炎在LR中具有较高的特征重要性。IMMs似乎并不重要，但较少使用的IMMs受到样本量的限制。我们的结果表明，年龄、慢性并发症和未完全接种疫苗可能是导致 IMIDs 患者出现严重 COVID-19 后果的更大风险因素，而不是 IMMs 的使用或 IMIDs 本身。总之，在为 IMIDs 患者制定 COVID-19 指南时，需要将年龄和合并症考虑在内。对于特定的 IMIDs（包括感染 SARS-CoV-2 时 IMID 的严重程度）和 IMMs（考虑患者首次感染 COVID-19 之前的剂量和时间），还需要进一步研究。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Machine learning to understand risks for severe COVID-19 outcomes: a retrospective cohort study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US health-care system

Background

In the context of immune-mediated inflammatory diseases (IMIDs), COVID-19 outcomes are incompletely understood and vary considerably depending on the patient population studied. We aimed to analyse severe COVID-19 outcomes and to investigate the effects of the pandemic time period and the risks associated with individual IMIDs, classes of immunomodulatory medications (IMMs), chronic comorbidities, and COVID-19 vaccination status.

Methods

In this retrospective cohort study, clinical data were derived from the electronic health records of an integrated health-care system serving patients in 51 hospitals and 1085 clinics across seven US states (Providence St Joseph Health). Data were observed for patients (no age restriction) with one or more IMID and for unmatched controls without IMIDs. COVID-19 was identified with a positive nucleic acid amplification test result for SARS-CoV-2. Two timeframes were analysed: March 1, 2020–Dec 25, 2021 (pre-omicron period), and Dec 26, 2021–Aug 30, 2022 (omicron-predominant period). Primary outcomes were hospitalisation, mechanical ventilation, and mortality in patients with COVID-19. Factors, including IMID diagnoses, comorbidities, long-term use of IMMs, and COVID-19 vaccination status, were analysed with multivariable logistic regression (LR) and extreme gradient boosting (XGB).

Findings

Of 2 167 656 patients tested for SARS-CoV-2, 290 855 (13·4%) had confirmed COVID-19: 15 397 (5·3%) patients with IMIDs and 275 458 (94·7%) without IMIDs. In the pre-omicron period, 169 993 (11·2%) of 1 517 295 people who were tested for COVID-19 tested positive, of whom 23 330 (13·7%) were hospitalised, 1072 (0·6%) received mechanical ventilation, and 5294 (3·1%) died. Compared with controls, patients with IMIDs and COVID-19 had higher rates of hospitalisation (1176 [14·6%] vs 22 154 [13·7%]; p=0·024) and mortality (314 [3·9%] vs 4980 [3·1%]; p<0·0001). In the omicron-predominant period, 120 862 (18·6%) of 650 361 patients tested positive for COVID-19, of whom 14 504 (12·0%) were hospitalised, 567 (0·5%) received mechanical ventilation, and 2001 (1·7%) died. Compared with controls, patients with IMIDs and COVID-19 (7327 [17·3%] of 42 249) had higher rates of hospitalisation (13 422 [11·8%] vs 1082 [14·8%]; p<0·0001) and mortality (1814 [1·6%] vs 187 [2·6%]; p<0·0001). Age was a risk factor for worse outcomes (adjusted odds ratio [OR] from 2·1 [95% CI 2·0–2·1]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001), whereas COVID-19 vaccination (from 0·082 [0·080–0·085]; p<0·0001 to 0·52 [0·50–0·53]; p<0·0001) and booster vaccination (from 2·1 [2·0–2·2]; p<0·0001 to 3·0 [2·9–3·0]; p<0·0001) status were associated with better outcomes. Seven chronic comorbidities were significant risk factors during both time periods for all three outcomes: atrial fibrillation, coronary artery disease, heart failure, chronic kidney disease, chronic obstructive pulmonary disease, chronic liver disease, and cancer. Two IMIDs, asthma (adjusted OR from 0·33 [0·32–0·34]; p<0·0001 to 0·49 [0·48–0·51]; p<0·0001) and psoriasis (from 0·52 [0·48–0·56] to 0·80 [0·74–0·87]; p<0·0001), were associated with a reduced risk of severe outcomes. IMID diagnoses did not appear to be significant risk factors themselves, but results were limited by small sample size, and vasculitis had high feature importance in LR. IMMs did not appear to be significant, but less frequently used IMMs were limited by sample size. XGB outperformed LR, with the area under the receiver operating characteristic curve for models across different time periods and outcomes ranging from 0·77 to 0·92.

Interpretation

Our results suggest that age, chronic comorbidities, and not being fully vaccinated might be greater risk factors for severe COVID-19 outcomes in patients with IMIDs than the use of IMMs or the IMIDs themselves. Overall, there is a need to take age and comorbidities into consideration when developing COVID-19 guidelines for patients with IMIDs. Further research is needed for specific IMIDs (including IMID severity at the time of SARS-CoV-2 infection) and IMMs (considering dosage and timing before a patient's first COVID-19 infection).

Funding

Pfizer, Novartis, Janssen, and the National Institutes of Health.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Lancet Digital Health Multiple-

CiteScore

41.20

自引率

1.60%

发文量

232

审稿时长

13 weeks

期刊介绍： The Lancet Digital Health publishes important, innovative, and practice-changing research on any topic connected with digital technology in clinical medicine, public health, and global health. The journal’s open access content crosses subject boundaries, building bridges between health professionals and researchers.By bringing together the most important advances in this multidisciplinary field,The Lancet Digital Health is the most prominent publishing venue in digital health. We publish a range of content types including Articles,Review, Comment, and Correspondence, contributing to promoting digital technologies in health practice worldwide.