Optimization of thermal desorption conditions of stir bar sorptive extraction facilitated by machine learning

Stir bar sorptive extraction is an effective technique for trapping odorants, but there are limited studies on the effect of varying thermal desorption conditions on desorption efficiency of odorants. Therefore, we conducted this study to explore the relationship between desorption conditions and desorption efficiency for 18 odorants with diverse physicochemical properties using instrumental analysis and mathematical modeling. We trained four types of machine learning models using a dataset comprising 864 different combinations of four desorption conditions (each three levels) and physicochemical properties. The prediction value of the selected model was validated using a validation dataset of six new odorants. The Random Forest model had the highest performance (R = 0.910). The order of feature importance using this model was as follows: cryo-focusing temperature, molecular weight, log P, boiling point, desorption temperature, desorption time, and helium flow. For testing on new odorants, the correlations between predicted and experimental data for terpene (R = 0.99), alcohol (R = 0.98), ester (R = 0.92), sulfide (R = 0.89), phenol (R = 0.88), and aldehyde (R = 0.61) were determined.

A nomogram for predicting the HER2 status in female patients with breast cancer in China: a nationwide, multicenter, 10-year epidemiological study

BACKGROUND

The concordance rate of human epidermal growth factor receptor 2 (HER2) status between core needle biopsy (CNB) and subsequent excisional biopsies of the same tumor varies from 81 to 96%, which may cause inappropriate neoadjuvant therapy that impair the potential benefit from HER2 targeted therapy for patients. This study aimed to establish a nomogram to predict the HER2 status pre-operatively as an auxiliary diagnosis to CNB assessment.

METHODS

Among 4211 breast cancer patients cataloged in the Nation-wide Multicenter 10-year Retrospective Clinical Epidemiological Study of Breast Cancer in China, 2291 patients with complete relevant information were included in this study, which were further randomized 3:1 and divided into a training set and a validation set. The nomogram was established based on independent predictors of HER2 positivity recognized by logistic regression analysis and further validated internally and externally.

RESULTS

The multivariate logistic regression analysis showed that T-stage, N-stage, estrogen receptor (ER) status, progesterone receptor (PR) status were independent predictors for HER2 status. The nomogram was thereby constructed by those independent predictors as well as histology type. The areas under the receiver operating characteristic curve (AUC) of the training set and the validation set were 0.636 and 0.681, respectively. The calibration plots demonstrated good fitness of the nomogram for HER2 status prediction. With the optimal cutoff value, the nomogram yielded 80.0% sensitivity, 43.1% specificity in the training set and 81.1% sensitivity, 49.8% specificity in the validation set.

CONCLUSIONS

The present nomogram can provide valuable information on HER2 status and combined with standard CNB assessment, clinicians could make more appropriate decision on neoadjuvant therapy of breast cancer.

Practical approach to determine sample size for building logistic prediction models using high-throughput data

An empirical method of sample size determination for building prediction models was proposed recently. Permutation method which is used in this procedure is a commonly used method to address the problem of overfitting during cross-validation while evaluating the performance of prediction models constructed from microarray data. But major drawback of such methods which include bootstrapping and full permutations is prohibitively high cost of computation required for calculating the sample size. In this paper, we propose that a single representative null distribution can be used instead of a full permutation by using both simulated and real data sets. During simulation, we have used a dataset with zero effect size and confirmed that the empirical type I error approaches to 0.05. Hence this method can be confidently applied to reduce overfitting problem during cross-validation. We have observed that pilot data set generated by random sampling from real data could be successfully used for sample size determination. We present our results using an experiment that was repeated for 300 times while producing results comparable to that of full permutation method. Since we eliminate full permutation, sample size estimation time is not a function of pilot data size. In our experiment we have observed that this process takes around 30min. With the increasing number of clinical studies, developing efficient sample size determination methods for building prediction models is critical. But empirical methods using bootstrap and permutation usually involve high computing costs. In this study, we propose a method that can reduce required computing time drastically by using representative null distribution of permutations. We use data from pilot experiments to apply this method for designing clinical studies efficiently for high throughput data.