Logistic regression analysis of clinical and computed tomography features of pulmonary abscesses and risk factors for pulmonary abscess-related empyema

Risk factors associated with length of hospital stay and medical expenses in pulmonary abscess patients: retrospective study

Background

Pulmonary abscess carries a high mortality and requires long-term managements. A better understanding of the risk factors associated with the prolonged hospital stay and high medical expenses in these patients can improve the management strategy in individual patient and optimize the overall healthcare resources.

Methods

We performed a retrospective study and reviewed the medical records on consecutive patients hospitalized at the Department of Respiratory Medicine of the General Hospital of Northern Theater Command, Shenyang, Liaoning, China, between January 1, 2015, and December 31, 2020. Demographics, comorbidity, clinical symptoms, laboratory tests, length of hospital stay, and medical expenses were recorded. Their relationships with the length of hospital stay and medical expenses in pulmonary abscess patients were analyzed.

Results

There were 190 patients with the pulmonary abscess and 12,189 patients without the pulmonary abscess. Compared with patients without the pulmonary abscess, patients with the pulmonary abscess had longer hospital stays (21.8 ± SD vs 12.8 ± SD, P < 0.01), In patients with the pulmonary abscess, the mean length of hospital stay was 5.3 days longer in male vs female patients (P = 0.025). Multivariate linear regression analyses showed that extrapulmonary disease and clinical symptoms were associated with the length of hospital stay and medical expenses, respectively. In addition, anemia was associated with both the length of hospital stay and medical expenses. Sex and hypoproteinemia were associated with the medical expenses.

Conclusions

The mean length of hospital stay was longer in patients with the pulmonary abscess than those without the pulmonary abscess. The length of hospital stay and medical expense were associated with sex, clinical symptoms, extrapulmonary disease, and abnormal laboratory tests in patients with the pulmonary abscess.

Machine learning models for rat multigeneration reproductive toxicity prediction

Reproductive toxicity is one of the prominent endpoints in the risk assessment of environmental and industrial chemicals. Due to the complexity of the reproductive system, traditional reproductive toxicity testing in animals, especially guideline multigeneration reproductive toxicity studies, take a long time and are expensive. Therefore, machine learning, as a promising alternative approach, should be considered when evaluating the reproductive toxicity of chemicals. We curated rat multigeneration reproductive toxicity testing data of 275 chemicals from ToxRefDB (Toxicity Reference Database) and developed predictive models using seven machine learning algorithms (decision tree, decision forest, random forest, k-nearest neighbors, support vector machine, linear discriminant analysis, and logistic regression). A consensus model was built based on the seven individual models. An external validation set was curated from the COSMOS database and the literature. The performances of individual and consensus models were evaluated using 500 iterations of 5-fold cross-validations and the external validation data set. The balanced accuracy of the models ranged from 58% to 65% in the 5-fold cross-validations and 45%–61% in the external validations. Prediction confidence analysis was conducted to provide additional information for more appropriate applications of the developed models. The impact of our findings is in increasing confidence in machine learning models. We demonstrate the importance of using consensus models for harnessing the benefits of multiple machine learning models (i.e., using redundant systems to check validity of outcomes). While we continue to build upon the models to better characterize weak toxicants, there is current utility in saving resources by being able to screen out strong reproductive toxicants before investing in vivo testing. The modeling approach (machine learning models) is offered for assessing the rat multigeneration reproductive toxicity of chemicals. Our results suggest that machine learning may be a promising alternative approach to evaluate the potential reproductive toxicity of chemicals.

Logistic Regression for Machine Learning in Process Tomography

The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images.