Clinical characteristics, outcomes, and risk factors for mortality in hospitalized patients with COVID-19 and cancer history: a propensity score-matched study

Tackling Non-Small Cell Lung Cancer in Young Adults: From Risk Factors and Genetic Susceptibility to Lung Cancer Profile and Outcomes

Lung cancer has traditionally been associated with advanced age; however, its increasing incidence among young adults raises concerning questions regarding its etiology and unique considerations for this population. In contrast to the older population, the onset of lung cancer at younger age may be attributed to a complex interplay of incompletely understood individual susceptibility and prevalent environmental risk factors beyond tobacco smoke exposure, such as radon gas and air pollution, which are widespread globally. Consequently, this leads to distinct clinical and molecular profiles, requiring a tailored approach. Furthermore, a diagnosis of cancer represents a threatening event during the prime years of a young person's life, prompting concern about career development, social aspects, fertility aspirations, and physical independence. This poses significant additional challenges for health care professionals in a field that remains underexplored. This comprehensive review recognizes lung cancer in young adults as a distinct entity, exploring its clinical and molecular characteristics, diverse predisposing factors, and priorities in terms of quality of life, with the aim of providing practical support to oncologists and enhancing our understanding of this under-researched population.

Use of chronic medications and risk of death due to COVID-19 in hospitalised patients

OBJECTIVES

To evaluate the potential association between chronic exposure to medication and death related to COVID-19.

METHODS

This is a retrospective cross-sectional study that included all patients hospitalised due to COVID-19 from 11 March to 4 June 2020 in our centre. Chronic patient medication was classified by the Anatomical Therapeutic Chemical (ATC) classification; demographic and clinical data were analysed. Multivariate logistic regression models were used to estimate the adjusted odds ratios (aOR) of death for each drug exposure; each aOR represents an independent model adjusted by clinical factors related to COVID-19 mortality.

RESULTS

The study included 978 patients with a mean (SD) age of 64.5 (17.7) years who were predominantly male (531, 54.3%). Of all 978 patients, 182 (18.61%) died during the follow-up of the study. The most common Charlson Comorbidity Index (CCI) was 0, 4.2% were smokers, 16.7% were obese, 47.4% had hypertension, and 19.4% were diabetic. Most patients (70.8%) were prescribed at least one treatment, 32.5% used >5 treatments, and 8.6% >10. Our data suggest that COVID-19 hospitalised patients taking trimethoprim and analogues, leukotriene receptor antagonists, calcineurin inhibitors, aldosterone antagonists, selective immunosuppressants, propulsives, insulins and analogues, and benzodiazepine derivatives have a higher risk of death.

CONCLUSIONS

This study investigated the association between chronic exposure to drugs and the risk of death in COVID-19 patients. Our results have shed some light on the impact of chronic drug exposure on the risk of severe COVID-19; however, further research is needed to increase the understanding about its relevance.

Clinical Characteristics and Outcomes in Hospitalized Patients with COVID-19 and Cancer History: A Multicenter Cross-Sectional Study in Southwestern Iran

Background: Cancer patients are more exposed to opportunistic infections, such as COVID-19, due to their poor health status. This study aimed to identify the clinical characteristics of cancer and non-cancer patients with COVID-19 that may lead to death, intubation, and ICU admission. Materials and Methods: A Multicenter Cross-Sectional study was conducted on confirmed COVID-19 adult patients with and without a history of cancer from March 2019 to March 2021. Demographic and clinical features, ICU admission, intubation, and discharge status have been extracted from patients' medical records. Chi-square, odds ratio, Mann-Whitney test, and logistic regression were used to analyze the data. Results: The death rate in 1332 cancer patients was 28% compared to the 91464 noncancer patients which was 9% with an odds ratio of 3.94 and p<0.001. ICU admission rates among the cancer group were 43%, while in the noncancer group, it was 17.9% (p<0.001). Moreover, intubation was done for 20.9% of cancer patients and 7.4% of non-cancer patients (p<0.001). However, no significant difference was observed between the two groups in terms of length of stay in the hospital. Multivariable logistic regression analysis showed that age, level of consciousness, SPO2, and autoimmune disorders were associated with mortality in cancer patients with COVID-19. Conclusion: This study showed that older age, loss of consciousness, low oxygen saturation, and suffering from autoimmune disorders were the predictors of death in cancer patients with COVID-19. These results can have important implications for the management and care of cancer patients with COVID-19.

COVID-19 vaccination is associated with enhanced efficacy of anti-PD-(L)1 immunotherapy in advanced NSCLC patients: a real-world study

BACKGROUND

Coronavirus disease 2019 (COVID-19) vaccine has played a major role in ending the pandemic. However, little is known about the influence of COVID-19 vaccine on the efficacy of immunotherapy in patients with non-small cell lung cancer (NSCLC).

OBJECTIVES

The goal of this study is to explore whether COVID-19 vaccine impacts the efficacy of immune checkpoint inhibitors (ICIs) in NSCLC patients.

METHODS

We retrospectively analyzed the survival data of ICI-treated 104 patients with stage III-IV NSCLC, who either received COVID-19 vaccination (n = 25) or no vaccination (n = 79). The potential risk factors, in particular roles of COVID-19 vaccination in the efficacy of ICIs in these patients, were evaluated.

RESULTS

Our results showed significantly improved ORR (28.0% vs. 11.39%, p = 0.05) and DCR (88.0% vs. 54.43%, p = 0.005) in the COVID-19 vaccinated group compared with the non-vaccinated group. Regarding the long-term survival benefits, COVID-19 vaccine showed profound influence both on the PFS (HR = 0.16, p = 0.021) and OS (HR = 0.168, p = 0.019) in patients with NSCLC under ICIs treatment. The PFS (p < 0.001) or OS (p < 0.001) was significantly improved in the COVID-19 vaccinated group, compared with the non-vaccinated group. Moreover, CD4 T cell (p = 0.047) level was higher in the COVID-19 vaccinated group than in the non-vaccinated group.

CONCLUSIONS

COVID-19 vaccination enhances anti-PD-1 immunotherapy efficacy in patients with stage III-IV NSCLC, suggesting that COVID-19 vaccination may provide additional benefit to NSCLC patients.

Identification of Clinical Features Associated with Mortality in COVID-19 Patients

Understanding clinical features and risk factors associated with COVID-19 mortality is needed to early identify critically ill patients, initiate treatments and prevent mortality. A retrospective study on COVID-19 patients referred to a tertiary hospital in Iran between March and November 2020 was conducted. COVID-19-related mortality and its association with clinical features including headache, chest pain, symptoms on computerized tomography (CT), hospitalization, time to infection, history of neurological disorders, having a single or multiple risk factors, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia were investigated. Based on the investigation outcome, decision tree and dimension reduction algorithms were used to identify the aforementioned risk factors. Of the 3008 patients (mean age 59.3 ± 18.7 years, 44% women) with COVID-19, 373 died. There was a significant association between COVID-19 mortality and old age, headache, chest pain, low respiratory rate, oxygen saturation < 93%, need for a mechanical ventilator, having symptoms on CT, hospitalization, time to infection, neurological disorders, cardiovascular diseases and having a risk factor or multiple risk factors. In contrast, there was no significant association between mortality and gender, fever, myalgia, dizziness, seizure, abdominal pain, nausea, vomiting, diarrhoea and anorexia. Our results might help identify early symptoms related to COVID-19 and better manage patients according to the extracted decision tree. The proposed ML models identified a number of clinical features and risk factors associated with mortality in COVID-19 patients. These models if implemented in a clinical setting might help to early identify patients needing medical attention and care. However, more studies are needed to confirm these findings.

Impact of coronavirus disease 2019 on lung cancer patients: A meta-analysis

Background

The coronavirus disease 2019 (COVID-19) pandemic poses a great challenge to the treatment of lung cancer patients.

Materials and methods

The PubMed, Embase, and Web of Science databases were searched for studies published before March 15, 2022, and Stata 14.0 software was used to perform a meta-analysis with a random-effects model. The odds ratio (OR) along with the corresponding 95% confidence interval (CI) was reported.

Results

Our meta-analysis included 80 articles with 318,352 patients involved. The proportion of lung cancer patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was 2.4% (95% CI: 0.02-0.03) prior to the Omicron variant outbreak. Among COVID-19 patients, those with lung cancer showed a higher mortality rate than those with other types of malignant solid tumors (OR = 1.82, 95% CI: 1.61-2.06) and non-cancer patients (OR = 4.67, 95% CI: 3.61-6.05); however, no significant difference was observed in the mortality rate between patients with lung cancer and those with hematologic malignancies (OR = 1.07, 95% CI: 0.85-1.33). SARS-CoV-2 infection significantly increased the mortality rate in lung cancer patients (OR = 8.94, 95% CI: 6.50-12.31). By contrast, the all-cause mortality rate in lung cancer patients (OR = 1.04, 95% CI: 0.69-1.57) and the proportion of patients diagnosed with advanced lung cancer (OR = 1.04, 95% CI: 0.85-1.27) did not significantly change before and after the pandemic.

Conclusions

More attention should be paid on improving the health of lung cancer patients during the COVID-19 pandemic.

Cerebrovascular accident in a child with precursor B-cell acute lymphoblastic leukemia and coronavirus disease 2019: a case report

BACKGROUND

Coronavirus disease 2019 can lead to rare but severe and life-threatening diseases in susceptible high-risk populations, including patients with immunodeficiency. A rare event in this report is stroke following COVID-19 disease in a patient with an immunocompromised background due to leukemia and anti-cancer treatments.

CASE PRESENTATION

A 6-year-old iranian girl with precursor B-cell leukemia receiving vincristine therapy presented with fever and absolute neutrophil count < 500. Her severe acute respiratory syndrome coronavirus 2 polymerase chain reaction test was positive. During hospitalization, she had abrupt onset tachypnea, reduced O₂ saturation, and generalized tonic-clonic seizures treated with phenytoin and levetiracetam. Right parietal lobe ischemia was found on a brain computed tomography scan, and the cerebrospinal fluid polymerase chain reaction test was positive for severe acute respiratory syndrome coronavirus 2. Several days later, she developed lower extremity paralysis and speech impairment, so speech therapy and physiotherapy were initiated. The patient also received dexamethasone, mannitol, heparin, and remdesivir. She was discharged with enoxaparin and levetiracetam. Chemotherapy resumed 2 weeks following discharge. Her speech and walking improved after 10 months of follow-up, and bone marrow aspiration showed total remission.

CONCLUSION

Owing to the link between coronavirus disease 2019 and hematologic cancers with hypercoagulopathy and the tendency of patients with leukemia to have coronavirus disease 2019 complications, children with leukemia as well as suspected coronavirus disease 2019 must be hospitalized to prevent blood clot formation.

Effects of SARS-CoV-2 infections in patients with cancer on mortality, ICU admission and incidence: a systematic review with meta-analysis involving 709,908 participants and 31,732 cancer patients

Background

Cancer patients constitute one of the highest-risk patient groups during the COVID-19 pandemic. In this study, it was aimed to perform a systematic review and meta-analysis to determine both the incidence and ICU (Intensive Care Unit) admission rates and mortality in SARS-CoV-2 infected cancer patients.

Methods

The PRISMA guidelines were closely followed during the design, analysis, and reporting of this systematic review and meta-analysis. A comprehensive literature search was performed for the published papers in PubMed/Medline, Scopus, medRxiv, Embase, and Web of Science (WoS) databases. SARS-CoV-2 infection pooled incidence in the cancer populations and the risk ratio (RR) of ICU admission rates/mortality in cancer and non-cancer groups, with 95% confidence intervals (CIs), were calculated using the random-effects model.

Results

A total of 58 studies, involving 709,908 participants and 31,732 cancer patients, were included in this study. The incidence in cancer patients was calculated as 8% (95% CI: 8–9%). Analysis results showed that mortality and ICU admission rate was significantly higher in patients with cancer (RR = 2.26, 95% CI: 1.94–2.62, P < 0.001; RR = 1.45, 95% CI: 1.28–1.64, p < 0.001, respectively).

Conclusion

As a result, cancer was an important comorbidity and risk factor for all SARS-CoV-2 infected patients. This infection could result in severe and even fatal events in cancer patients. Cancer is associated with a poor prognosis in the COVID-19 pandemic. Cancer patients should be assessed more sensitively in the COVID-19 outbreak.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00432-022-04191-y.

Effect of cancer on outcome of COVID-19 patients: a systematic review and meta-analysis of studies of unvaccinated patients

Background:

Since the beginning of the SARS-CoV-2 pandemic, cancer patients affected by COVID-19 have been reported to experience poor prognosis; however, a detailed quantification of the effect of cancer on outcome of unvaccinated COVID-19 patients has not been performed.

Methods:

To carry out a systematic review of the studies comparing the outcome of unvaccinated COVID-19 patients with and without cancer, a search string was devised which was used to identify relevant publications in PubMed up to December 31, 2020. We selected three outcomes: mortality, access to ICU, and COVID-19 severity or hospitalization. We considered results for all cancers combined as well as for specific cancers. We conducted random-effects meta-analyses of the results, overall and after stratification by region. We also performed sensitivity analyses according to quality score and assessed publication bias.

Results:

For all cancer combined, the pooled odds ratio (OR) for mortality was 2.32 (95% confidence interval [CI] 1.82–2.94, I² for heterogeneity 90.1%, 24 studies), that for ICU admission was 2.39 (95% CI 1.90–3.02, I² 0.0%, 5 studies), that for disease severity or hospitalization was 2.08 (95% CI 1.60–2.72, I² 92.1%, 15 studies). The pooled mortality OR for hematologic neoplasms was 2.14 (95% CI 1.87–2.44, I² 20.8%, 8 studies). Data were insufficient to perform a meta-analysis for other cancers. In the mortality meta-analysis for all cancers, the pooled OR was higher for studies conducted in Asia than studies conducted in Europe or North America. There was no evidence of publication bias.

Conclusions:

Our meta-analysis indicates a twofold increased risk of adverse outcomes (mortality, ICU admission, and severity of COVID-19) in unvaccinated COVID-19 patients with cancer compared to COVID-19 patients without cancer. These results should be compared with studies conducted in vaccinated patients; nonetheless, they argue for special effort to prevent SARS-CoV-2 infection in patients with cancer.

Funding:

No external funding was obtained.

The Impact of COVID-19 on the Delivery of Systemic Anti-Cancer Treatment at Guy's Cancer Centre

BACKGROUND

This study aimed to assess the outcome of cancer patients undergoing systemic anti-cancer treatment (SACT) at our centre to help inform future clinical decision-making around SACT during the COVID-19 pandemic.

METHODS

Patients receiving at least one episode of SACT for solid tumours at Guy's Cancer Centre between 1 March and 31 May 2020 and the same period in 2019 were included in the study. Data were collected on demographics, tumour type/stage, treatment type (chemotherapy, immunotherapy, biological-targeted) and SARS-CoV2 infection.

RESULTS

A total of 2120 patients received SACT in 2020, compared to 2449 in 2019 (13% decrease). From 2019 to 2020, there was an increase in stage IV disease (62% vs. 72%), decrease in chemotherapy (42% vs. 34%), increase in immunotherapy (6% vs. 10%), but similar rates of biologically targeted treatments (37% vs. 38%). There was a significant increase in 1st and 2nd line treatments in 2020 (68% vs. 81%; p < 0.0001) and reduction in 3rd and subsequent lines (26% vs. 15%; p = 0.004) compared to 2019. Of the 2020 cohort, 2% patients developed SARS-CoV2 infections.

CONCLUSIONS

These real-world data from a tertiary Cancer Centre suggest that despite the challenges faced due to the COVID-19 pandemic, SACT was able to be continued without any significant effects on the mortality of solid-tumour patients. There was a low rate (2%) of SARS-CoV-2 infection which is comparable to the 1.4%-point prevalence in our total cancer population.

OUP accepted manuscript

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2, has currently affected >220 million individuals worldwide. The complex interplay of immune dysfunction, active malignancy, the effect of cancer treatment on the immune system and additional comorbidities associated with cancer and COVID-19 all affect the outcomes of COVID-19 in patients with cancer. We have discussed the published findings (through the end of September 2021) on the effects of cancer on the morbidity and mortality of COVID-19, common factors between cancer and COVID-19, the interaction of cancer and COVID-19 treatments, the impact of COVID-19 on cancer clinical services, immune test findings in cancer patients with COVID-19 and the long-term effects of COVID-19 on cancer survivors.

Identifying the Risk Factors for Mortality in Patients with Cancer and COVID-19 in Hamadan, the West of Iran

Purpose

Since cancer patients are at higher risk of COVID-19, the present study was conducted to investigate the epidemiology of these patients and identify the affecting risk factors on their mortality.

Methods

The present retrospective cohort study was conducted on 66 hospitalized patients with cancer and COVID-19 in Hamadan in 2020. In the present study, demographic, clinical, and laboratory information and patients’ outcome were collected through a checklist and its impact on death was assessed. Data were analyzed in SPSS-24 software and the significance level of the tests was considered at 5%.

Results

The mean (standard deviation (SD)) age of patients was 61.6 (13.5) years. Forty patients (60.6%) were male. Twenty and five patients (37.9%) died at the end of study. The results of logistic regression model revealed that the nausea, mechanical ventilation, admission to ICU, and length of hospital stay in the ward had a significant impact on the odds of death among cancer patients with COVID-19 (p < 0.05).

Conclusion

Owing to high mortality rate in cancer patients with COVID-19 and due to underlying diseases and more severe clinical symptoms than other patients with coronavirus, these patients need intensive care and specific treatments. However, screening these patients and early identifying and vaccinating of them can reduce the mortality rate in these patients.

COVID-19 as a mediator of interferon deficiency and hyperinflammation: Rationale for the use of JAK1/2 inhibitors in combination with interferon

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) elicits an interferon (IFN) deficiency state, which aggravates the type I interferon deficiency and slow IFN responses, which associate with e.g. aging and obesity. Additionally, SARS-CoV-2 may also elicit a cytokine storm, which accounts for disease progression and ultimately the urgent need of ventilator support. Based upon several reports, it has been argued that early treatment with IFN-alpha2 or IFN-beta, preferentially in the early disease stage, may prohibit disease progression. Similarly, preliminary studies have shown that JAK1/2 inhibitor treatment with ruxolitinib or baricitinib may decrease mortality by dampening the deadly cytokine storm, which - in addition to the virus itself - also contributes to multi-organ thrombosis and multi-organ failure. Herein, we describe the rationale for treatment with IFNs (alpha2 or beta) and ruxolitinib emphasizing the urgent need to explore these agents in the treatment of SARS-CoV-2 - both as monotherapies and in combination. In this context, we take advantage of several safety and efficacy studies in patients with the chronic myeloproliferative blood cancers (essential thrombocythemia, polycythemia vera and myelofibrosis) (MPNs), in whom IFN-alpha2 and ruxolitinib have been used successfully for the last 10 (ruxolitinib) to 30 years (IFN) as monotherapies and most recently in combination as well. In the context of these agents being highly immunomodulating (IFN boosting immune cells and JAK1/2 inhibitors being highly immunosuppressive and anti-inflammatory), we also discuss if statins and hydroxyurea, both agents possessing anti-inflammatory, antithrombotic and antiviral potentials, might be inexpensive agents to be repurposed in the treatment of SARS-CoV-2.

ANMCO POSITION PAPER: cardio-oncology in the COVID era (CO and CO)

The COVID-19 pandemic and its impact on patients with cancer and cardiovascular disease have confirmed the particular vulnerability of these populations. Indeed, not only a higher risk of contracting the infection has been reported but also an increased occurrence of a more severe course and unfavourable outcome. Beyond the direct consequences of COVID-19 infection, the pandemic has an enormous impact on global health systems. Screening programmes and non-urgent tests have been postponed; clinical trials have suffered a setback. Similarly, in the area of cardiology care, a significant decline in STEMI accesses and an increase in cases of late presenting heart attacks with increased mortality and complication rates have been reported. Health care systems must therefore get ready to tackle the 'rebound effect' that will likely show a relative increase in the short- and medium-term incidence of diseases such as heart failure, myocardial infarction, arrhythmias, and cardio- and cerebrovascular complications. Scientific societies are taking action to provide general guidance and recommendations aimed at mitigating the unfavourable outcomes of this pandemic emergency. Cardio-oncology, as an emerging discipline, is more flexible in modulating care pathways and represents a beacon of innovation in the development of multi-specialty patient management. In the era of the COVID-19 pandemic, cardio-oncology has rapidly modified its clinical care pathways and implemented flexible monitoring protocols that include targeted use of cardiac imaging, increased use of biomarkers, and telemedicine systems. The goal of these strategic adjustments is to minimize the risk of infection for providers and patients while maintaining standards of care for the treatment of oncologic and cardiovascular diseases. The aim of this document is to evaluate the impact of the pandemic on the management of cardio-oncologic patients with the-state-of-the-art knowledge about severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease (COVID-19) in order to optimize medical strategies during and after the pandemic.

Safeguarding COVID-19 and cancer management: drug design and therapeutic approach

Recent clinical cohort studies have highlighted that there is a three-fold greater SARS-Cov-2 infection risk in cancer patients, and overall mortality in individuals with tumours is increased by 41% with respect to general COVID-19 patients. Thus, access to therapeutics and intensive care is compromised for people with both diseases (comorbidity) and there is risk of delayed access to diagnosis. This comorbidity has resulted in extensive burden on the treatment of patients and health care system across the globe; moreover, mortality of hospitalized patients with comorbidity is reported to be 30% higher than for individuals affected by either disease. In this data-driven review, we aim specifically to address drug discoveries and clinical data of cancer management during the COVID-19 pandemic. The review will extensively address the treatment of COVID-19/cancer comorbidity; treatment protocols and new drug discoveries, including the description of drugs currently available in clinical settings; demographic features; and COVID-19 outcomes in cancer patients worldwide.

Mortality in adult patients with solid or hematological malignancies and SARS-CoV-2 infection with a specific focus on lung and breast cancers: A systematic review and meta-analysis

BACKGROUND

A systematic review and meta-analysis was performed to estimate mortality in adult patients with solid or hematological malignancies and SARS-CoV-2 infection.

METHODS

A systematic search of PubMed, up to 31 January 2021, identified publications reporting the case-fatality rate (CFR) among adult patients with solid or hematological malignancies and SARS-CoV-2 infection. The CFR, defined as the rate of death in this population, was assessed with a random effect model; 95% confidence intervals (CI) were calculated.

RESULTS

Among 135 selected studies (N = 33,879 patients), the CFR was 25.4% (95% CI 22.9%-28.2%). At a sensitivity analysis including studies with at least 100 patients, the CFR was 21.9% (95% CI 19.1%-25.1%). Among COVID-19 patients with lung (N = 1,135) and breast (N = 1,296) cancers, CFR were 32.4% (95% CI 26.5%-39.6%) and 14.2% (95% CI 9.3%-21.8%), respectively.

CONCLUSIONS

Patients with solid or hematological malignancies and SARS-CoV-2 infection have a high probability of mortality, with comparatively higher and lower CFRs in patients with lung and breast cancers, respectively.

COVID-19 Risk Factors for Cancer Patients: A First Report with Comparator Data from COVID-19 Negative Cancer Patients

Very few studies investigating COVID-19 in cancer patients have included cancer patients as controls. We aimed to identify factors associated with the risk of testing positive for SARS CoV2 infection in a cohort of cancer patients. We analyzed data from all cancer patients swabbed for COVID-19 between 1st March and 31st July 2020 at Guy's Cancer Centre. We conducted logistic regression analyses to identify which factors were associated with a positive COVID-19 test. Results: Of the 2152 patients tested for COVID-19, 190 (9%) tested positive. Male sex, black ethnicity, and hematological cancer type were positively associated with risk of COVID-19 (OR = 1.85, 95%CI:1.37-2.51; OR = 1.93, 95%CI:1.31-2.84; OR = 2.29, 95%CI:1.45-3.62, respectively) as compared to females, white ethnicity, or solid cancer type, respectively. Male, Asian ethnicity, and hematological cancer type were associated with an increased risk of severe COVID-19 (OR = 3.12, 95%CI:1.58-6.14; OR = 2.97, 95%CI:1.00-8.93; OR = 2.43, 95%CI:1.00-5.90, respectively). This study is one of the first to compare the risk of COVID-19 incidence and severity in cancer patients when including cancer patients as controls. Results from this study have echoed those of previous reports, that patients who are male, of black or Asian ethnicity, or with a hematological malignancy are at an increased risk of COVID-19.

Machine learning-based prognostic modeling using clinical data and quantitative radiomic features from chest CT images in COVID-19 patients

OBJECTIVE

To develop prognostic models for survival (alive or deceased status) prediction of COVID-19 patients using clinical data (demographics and history, laboratory tests, visual scoring by radiologists) and lung/lesion radiomic features extracted from chest CT images.

METHODS

Overall, 152 patients were enrolled in this study protocol. These were divided into 106 training/validation and 46 test datasets (untouched during training), respectively. Radiomic features were extracted from the segmented lungs and infectious lesions separately from chest CT images. Clinical data, including patients' history and demographics, laboratory tests and radiological scores were also collected. Univariate analysis was first performed (q-value reported after false discovery rate (FDR) correction) to determine the most predictive features among all imaging and clinical data. Prognostic modeling of survival was performed using radiomic features and clinical data, separately or in combination. Maximum relevance minimum redundancy (MRMR) and XGBoost were used for feature selection and classification. The receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC), sensitivity, specificity, and accuracy were used to assess the prognostic performance of the models on the test datasets.

RESULTS

For clinical data, cancer comorbidity (q-value < 0.01), consciousness level (q-value < 0.05) and radiological score involved zone (q-value < 0.02) were found to have high correlated features with outcome. Oxygen saturation (AUC = 0.73, q-value < 0.01) and Blood Urea Nitrogen (AUC = 0.72, q-value = 0.72) were identified as high clinical features. For lung radiomic features, SAHGLE (AUC = 0.70) and HGLZE (AUC = 0.67) from GLSZM were identified as most prognostic features. Amongst lesion radiomic features, RLNU from GLRLM (AUC = 0.73), HGLZE from GLSZM (AUC = 0.73) had the highest performance. In multivariate analysis, combining lung, lesion and clinical features was determined to provide the most accurate prognostic model (AUC = 0.95 ± 0.029 (95%CI: 0.95-0.96), accuracy = 0.88 ± 0.046 (95% CI: 0.88-0.89), sensitivity = 0.88 ± 0.066 (95% CI = 0.87-0.9) and specificity = 0.89 ± 0.07 (95% CI = 0.87-0.9)).

CONCLUSION

Combination of radiomic features and clinical data can effectively predict outcome in COVID-19 patients. The developed model has significant potential for improved management of COVID-19 patients.