Development, External Validation, and Visualization of Machine Learning Models for Predicting Occurrence of Acute Kidney Injury after Cardiac Surgery.

Background: Cardiac surgery-associated acute kidney injury (CSA-AKI) is a major complication that results in short- and long-term mortality among patients. Here, we adopted machine learning algorithms to build prediction models with the overarching goal of identifying patients who are at a high risk of such unfavorable kidney outcomes. Methods: A total of 1686 patients (development cohort) and 422 patients (validation cohort), with 126 pre- and intra-operative variables, were recruited from the First Medical Centre and the Sixth Medical Centre of Chinese PLA General Hospital in Beijing, China, respectively. Analyses were performed using six machine learning techniques, namely K-nearest neighbor, logistic regression, decision tree, random forest (RF), support vector machine, and neural network, and the APPROACH score, a previously established risk score for CSA-AKI. For model tuning, optimal hyperparameter was achieved by using GridSearch with 5-fold cross-validation from the scikit-learn library. Model performance was externally assessed via the receiver operating characteristic (ROC) and decision curve analysis (DCA). Explainable machine learning was performed using the Python SHapley Additive exPlanation (SHAP) package and Seaborn library, which allow the calculation of marginal contributory SHAP value. Results: 637 patients (30.2%) developed CSA-AKI within seven days after surgery. In the external validation, the RF classifier exhibited the best performance among the six machine learning techniques, as shown by the ROC curve and DCA, while the traditional APPROACH risk score showed a relatively poor performance. Further analysis found no specific causative factor contributing to the development of CSA-AKI; rather, the development of CSA-AKI appeared to be a complex process resulting from a complex interplay of multiple risk factors. The SHAP summary plot illustrated the positive or negative contribution of RF-top 20 variables and extrapolated risk of developing CSA-AKI at individual levels. The Seaborn library showed the effect of each single feature on the model output of the RF prediction. Conclusions: Efficient machine learning approaches were successfully established to predict patients with a high probability of developing acute kidney injury after cardiac surgery. These findings are expected to help clinicians to optimize treatment strategies and minimize postoperative complications. Clinical Trial Registration: The study protocol was registered at the ClinicalTrials Registration System (https://www.clinicaltrials.gov/, #NCT04966598) on July 26, 2021.

Morphology changes in the cochlea of impulse noise-induced hidden hearing loss.

BACKGROUND: This study was focused on impulse noise induces hidden hearing loss. OBJECTIVES: This study was designed to determine the morphology changes of noise-induced hidden hearing loss (NIHHL). METHOD: Fifteen guinea pigs were divided into three groups: noise-induced hidden hearing loss (NIHHL) group, noise-induced hearing loss (NIHL) group, and normal control group. For the NIHHL group, guinea pigs were exposed to 15 times of impulse noise with peak intensity of 163 dB SPL at one time. For the NIHL group, animals were exposed to two rounds of 100 times impulse noise, and the time interval is 24 h. Auditory brain response (ABR) was tested before, immediately, 24 h, one week, and one month after noise exposure to evaluate cochlear physiology changes. One month after noise exposure, all guinea pigs in three groups were sacrificed, and basement membranes were carefully dissected immediately after ABR tests. The cochlea samples were observed by transmission electron microscopy (TEM) to find out the morphology changes. RESULT: The ABR results showed that 15 times of impulse noise exposure could cause NIHHL in guinea pigs and 200 times could cause completely hearing loss. Impulse noise exposure could cause a dramatic increase of mitochondria in the inner hair cell. The structures of ribbon synapse and heminode were also obviously impaired compared to the normal group. The nerve fiber and myelin sheath remained intact after impulse noise exposure. CONCLUSION: This research revealed that impulse noise could cause hidden hearing loss, and the changes in inner hair cells, ribbon synapse, and heminode all played a vital role in the pathogenesis of hidden hearing loss.

Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer.

Objective: To develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients. Methods: Clinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians. Results: A total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/. Conclusion: The results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level.

Automatic Recognition of Auditory Brainstem Response Characteristic Waveform Based on Bidirectional Long Short-Term Memory.

Background: Auditory brainstem response (ABR) testing is an invasive electrophysiological auditory function test. Its waveforms and threshold can reflect auditory functional changes in the auditory centers in the brainstem and are widely used in the clinic to diagnose dysfunction in hearing. However, identifying its waveforms and threshold is mainly dependent on manual recognition by experimental persons, which could be primarily influenced by individual experiences. This is also a heavy job in clinical practice. Methods: In this work, human ABR was recorded. First, binarization is created to mark 1,024 sampling points accordingly. The selected characteristic area of ABR data is 0-8 ms. The marking area is enlarged to expand feature information and reduce marking error. Second, a bidirectional long short-term memory (BiLSTM) network structure is established to improve relevance of sampling points, and an ABR sampling point classifier is obtained by training. Finally, mark points are obtained through thresholding. Results: The specific structure, related parameters, recognition effect, and noise resistance of the network were explored in 614 sets of ABR clinical data. The results show that the average detection time for each data was 0.05 s, and recognition accuracy reached 92.91%. Discussion: The study proposed an automatic recognition of ABR waveforms by using the BiLSTM-based machine learning technique. The results demonstrated that the proposed methods could reduce recording time and help doctors in making diagnosis, suggesting that the proposed method has the potential to be used in the clinic in the future.