Dataset Information

Prediction models for respiratory outcomes in patients with COVID-19: integration of quantitative computed tomography parameters, demographics, and laboratory features.

ABSTRACT:

Background

We aimed to develop integrative machine-learning models using quantitative computed tomography (CT) parameters in addition to initial clinical features to predict the respiratory outcomes of coronavirus disease 2019 (COVID-19).

Methods

This was a retrospective study involving 387 patients with COVID-19. Demographic, initial laboratory, and quantitative CT findings were used to develop predictive models of respiratory outcomes. High-attenuation area (HAA) (%) and consolidation (%) were defined as quantified percentages of the area with Hounsfield units between -600 and -250 and between -100 and 0, respectively. Respiratory outcomes were defined as the development of pneumonia, hypoxia, or respiratory failure. Multivariable logistic regression and random forest models were developed for each respiratory outcome. The performance of the logistic regression model was evaluated using the area under the receiver operating characteristic curve (AUC). The accuracy of the developed models was validated by 10-fold cross-validation.

Results

A total of 195 (50.4%), 85 (22.0%), and 19 (4.9%) patients developed pneumonia, hypoxia, and respiratory failure, respectively. The mean patient age was 57.8 years, and 194 (50.1%) were female. In the multivariable analysis, vaccination status and levels of lactate dehydrogenase, C-reactive protein (CRP), and fibrinogen were independent predictors of pneumonia. The presence of hypertension, levels of lactate dehydrogenase and CRP, HAA (%), and consolidation (%) were selected as independent variables to predict hypoxia. For respiratory failure, the presence of diabetes, levels of aspartate aminotransferase, and CRP, and HAA (%) were selected. The AUCs of the prediction models for pneumonia, hypoxia, and respiratory failure were 0.904, 0.890, and 0.969, respectively. Using the feature selection in the random forest model, HAA (%) was ranked as one of the top 10 features predicting pneumonia and hypoxia and was first place for respiratory failure. The accuracies of the cross-validation of the random forest models using the top 10 features for pneumonia, hypoxia, and respiratory failure were 0.872, 0.878, and 0.945, respectively.

Conclusions

Our prediction models that incorporated quantitative CT parameters into clinical and laboratory variables showed good performance with high accuracy.

SUBMITTER: Kang J

PROVIDER: S-EPMC10089866 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction models for respiratory outcomes in patients with COVID-19: integration of quantitative computed tomography parameters, demographics, and laboratory features.

Kang Jieun J Kang Jiyeon J Seo Woo Jung WJ Park So Hee SH Kang Hyung Koo HK Park Hye Kyeong HK Hyun JongHoon J Song Je Eun JE Kwak Yee Gyung YG Kim Ki Hwan KH Kim Yeon Soo YS Lee Sung-Soon SS Koo Hyeon-Kyoung HK

Journal of thoracic disease 20230309 3

<h4>Background</h4>We aimed to develop integrative machine-learning models using quantitative computed tomography (CT) parameters in addition to initial clinical features to predict the respiratory outcomes of coronavirus disease 2019 (COVID-19).<h4>Methods</h4>This was a retrospective study involving 387 patients with COVID-19. Demographic, initial laboratory, and quantitative CT findings were used to develop predictive models of respiratory outcomes. High-attenuation area (HAA) (%) and consoli ...[more]

PMID: 37065603

Similar Datasets

Project description:ObjectivesTo determine whether quantitative parameters derived from dual-energy computed tomography (DECT) were predictive of the aggressiveness of oral tongue squamous cell carcinoma (OTSCC) including the pathologic stages, histologic differentiation, lymph node status, and perineural invasion (PNI).MethodsBetween August 2019 and March 2021, 93 patients (mean age, 54.6 ± 13.8 years; 66 men) with pathologically diagnosed OTSCC were enrolled in this prospective study. Preoperative DECT was performed and quantitative parameters (e.g., slope of the spectral Hounsfield unit curve [λHu], normalized iodine concentration [nIC], normalized effective atomic number [nZeff], and normalized electron density [nRho]) were measured on arterial phase (AP) and venous phase (VP) DECT imaging. Quantitative parameters from DECT were compared between patients with different pathologic stages, histologic differentiation, lymph node statuses, and perineural invasion statuses. Logistic regression analysis was utilized to assess independent parameters and the diagnostic performance was analyzed by the receiver operating characteristic curves (ROC).ResultsλHu and nIC in AP and λHu, nZeff, and nIC in VP were significantly lower in stage III-IV lesions than in stage I-II lesions (p < 0.001 to 0.024). λHu in VP was an independent predictor of tumor stage with an odds ratio (OR) of 0.29, and area under the curve (AUC) of 0.80. λHu and nIC were higher in well-differentiated lesions than in poorly differentiated lesions (p < 0.001 to 0.021). The nIC in VP was an independent predictor of histologic differentiation with OR of 0.31, and AUC of 0.78. λHu and nIC in VP were lower in OTSCCs with lymph node metastasis than those without metastasis (p < 0.001 to 0.005). λHu in VP was the independent predictor of lymph node status with OR of 0.42, and AUC of 0.74. No significant difference was found between OTSCCs without PNI and those with PNI in terms of the quantitative DECT parameters.ConclusionDECT can be a complementary means for the preoperative prediction of the aggressiveness of OTSCC.

Project description:Quantitative parameters from Tc-99m pertechnetate single-photon emission computed tomography/computed tomography (SPECT/CT) are emerging as novel diagnostic markers for functional thyroid diseases. We intended to assess the utility of SPECT/CT parameters in patients with destructive thyroiditis.Thirty-five destructive thyroiditis patients (7 males and 28 females; mean age, 47.3 ± 13.0 years) and 20 euthyroid patients (6 males and 14 females; mean age, 45.0 ± 14.8 years) who underwent Tc-99m pertechnetate quantitative SPECT/CT were retrospectively enrolled. Quantitative parameters from the SPECT/CT (%uptake, standardized uptake value [SUV], thyroid volume, and functional thyroid mass [SUVmean × thyroid volume]) and thyroid hormone levels were investigated to assess correlations and predict the prognosis for destructive thyroiditis. The occurrence of hypothyroidism was the outcome for prognosis.All the SPECT/CT quantitative parameters were significantly lower in the 35 destructive thyroiditis patients compared to the 20 euthyroid patients using the same SPECT/CT scanner and protocol (p < 0.001 for all parameters). T3 and free T4 did not correlate with any SPECT/CT parameters, but thyroid-stimulating hormone (TSH) significantly correlated with %uptake (p = 0.004), SUVmean (p < 0.001), SUVmax (p = 0.002), and functional thyroid mass (p < 0.001). Of the 35 destructive thyroiditis patients, 16 progressed to hypothyroidism. On univariate and multivariate analyses, only T3 levels were associated with the later occurrence of hypothyroidism (p = 0.002, exp(?) = 1.022, 95% confidence interval: 1.008 - 1.035).Novel quantitative SPECT/CT parameters could discriminate patients with destructive thyroiditis from euthyroid patients, suggesting the robustness of the quantitative SPECT/CT approach. However, disease progression of destructive thyroiditis could not be predicted using the parameters, as these only correlated with TSH, but not with T3, the sole predictor of the later occurrence of hypothyroidism.

Project description:BackgroundPeripheral quantitative computed tomography (pQCT) can provide information complementary to dual x-ray absorptiometry (DXA), however, there is sparse normative data to enable meaningful clinical interpretation and comparison. This study aimed to develop age-stratified normative data for pQCT-derived bone parameters in Australian men.MethodsParticipants were men (n = 508, age 33-96 yr) from the Geelong Osteoporosis Study. Bone parameters at 4% (n = 469) and 66% (n = 436) of radial length, and 4% (n = 449) and 66% (n = 438) of tibial length were acquired using pQCT (XCT 2000, Stratec Medizintechnik, Pforzheim, Germany). Best models of age, height and weight for each parameter were developed and where parameters exhibited variation with age, age decade mean (±SD) values were determined. Scatterplots were used to visualise the relationships between each of the parameters and age, height and weight.ResultsThirteen parameters at tibial and radial sites were correlated with age, height and weight, allowing for their inclusion in multiple linear regression models. A positive association with age was found for total area of the tibia or radius (as appropriate) (mm2) at all sites, trabecular bone area (mm2) at 4% sites, and total bone area (both long bones) (mm2) at 66% sites. A negative association with age was found for cortical density (mg/cm3) and cortical thickness (mm) at both radial and tibial 66% sites, but total density (mg/cm3) at the 66% radial site and total cortical density of both long bones (mg/cm3) at the 66% tibial site only.ConclusionThis study presents normative data for pQCT-derived bone parameters and describes age related associations in a number of these variables. Broadly, parameters of bone area were positively associated with age, whereas parameters associated with bone density and structure were negatively associated with age. These data have the potential to be used in clinical settings when assessing age-related decline in bone health.Mini abstractNormative data for pQCT parameters in Australian men are presented, adjusted for age, height and weight.

Project description:BackgroundThyroid nodules (TNs) cytologically defined as category Bethesda III and IV pose a major diagnostic challenge before surgery, demanding new methods to reduce unnecessary diagnostic thyroid lobectomies for patients with benign TNs. This study aimed to assess whether a model combining dual-energy computed tomography (DECT) quantitative parameters with morphologic features could reliably differentiate between benign and malignant lesions in Bethesda III and IV TNs.MethodsData from 77 patients scheduled for thyroid surgery for Bethesda III and IV TNs (malignant =48; benign =29) who underwent DECT scans were reviewed. DECT quantitative parameters including normalized iodine concentration (NIC), attenuation on the slope of spectral Hounsfield unit (HU) curve, and normalized effective atomic number (Zeff) were measured in the arterial phase (AP) and venous phase (VP). DECT quantitative parameters and morphologic features were compared between the malignant and benign cohorts. The receiver operating characteristic curve was performed to compare the performances of significant DECT quantitative parameters, morphologic features, or the models combining the DECT parameters, respectively, with morphologic features. A nomogram was constructed from the optimal performance model, and the performance was evaluated via the calibration curve and decision curve analysis.ResultsThe areas under the receiver operating characteristic curve with 95% confidence interval (CI) of the NIC in the AP (AP-NIC), slope of spectral HU curve in the AP, and NZeff in the AP were 0.749 (95% CI: 0.641-0.857), 0.654 (95% CI: 0.530-0.778), and 0.722 (95% CI: 0.602-0.842), respectively. The model combining AP-NIC with enhanced blurring showed the highest diagnostic performance, with an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.808, 0.854, and 0.655, respectively; it was then used to construct a nomogram. The calibration curve showed that the discrepancy between the prediction of the nomogram and actual observations was less than 5%. The decision curve analysis indicated the nomogram had a positive net benefit in threshold risk ranges of 14% to 58% or 60% to 91% for malignant Bethesda III and IV TNs.ConclusionsThe model combining AP-NIC with enhanced blurring could reliably differentiate between benign and malignant lesions in Bethesda III and IV TNs.

Project description:ObjectivesTo explore the association between lower extremity muscle features from CTA and peripheral arterial disease (PAD) severity using digital subtraction angiography (DSA) as reference standard.MethodsInformed consent was waived for this Institutional Review Board approved retrospective study. PAD patients were recruited from July 2016 to September 2020. Two radiologists evaluated PAD severity on DSA and CTA using runoff score. The patients were divided into two groups: mild PAD (DSA score ≤ 7) vs. severe PAD (DSA score > 7). After segmenting lower extremity muscles from CTA, 95 features were extracted for univariable analysis, logistic regression model (LRM) analysis, and sub-dataset analysis (PAD prediction based on only part of the images). AUC of CTA score and LRMs for PAD prediction were calculated. Features were analyzed using Student's t test and chi-squared test. p < 0.05 was considered statistically significant.ResultsA total of 56 patients (69 ± 11 years; 38 men) with 56 lower legs were enrolled in this study. The lower leg muscles of mild PAD group (36 patients) showed higher CT values (44.6 vs. 39.5, p < 0.001) with smaller dispersion (35.6 vs. 41.0, p < 0.001) than the severe group (20 patients). The AUC of CTA score, LRM-I (constructed with muscle features), and LRM-II (constructed with muscle features and CTA score) for PAD severity prediction were 0.81, 0.84, and 0.89, respectively. The highest predictive performance was observed in the image subset of the middle and inferior segments of lower extremity (LRM-I, 0.83; LRM-II, 0.90).ConclusionsLower extremity muscle features are associated with PAD severity and can be used for PAD prediction.Critical relevance statementQuantitative image features of lower extremity muscles are associated with the degree of lower leg arterial stenosis/occlusion and can be a beneficial supplement to the current imaging methods of vascular stenosis evaluation for the prediction of peripheral arterial disease severity.Key points• Compared with severe PAD, lower leg muscles of mild PAD showed higher CT values (39.5 vs. 44.6, p < 0.001). • Models developed with muscle CT features had AUC = 0.89 for predicting PAD. • PAD severity prediction can be realized through the middle and inferior segment of images (AUC = 0.90).

Dataset Information

Prediction models for respiratory outcomes in patients with COVID-19: integration of quantitative computed tomography parameters, demographics, and laboratory features.

Background

Methods

Results

Conclusions

Publications

Prediction models for respiratory outcomes in patients with COVID-19: integration of quantitative computed tomography parameters, demographics, and laboratory features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets