Prediction of response to neoadjuvant chemo-immunotherapy in patients with esophageal squamous cell carcinoma by a rapid breath test.

BACKGROUND: Neoadjuvant chemo-immunotherapy combination has shown remarkable advances in the management of esophageal squamous cell carcinoma (ESCC). However, the identification of a reliable biomarker for predicting the response to this chemo-immunotherapy regimen remains elusive. While computed tomography (CT) is widely utilized for response evaluation, its inherent limitations in terms of accuracy are well recognized. Therefore, in this study, we present a novel technique to predict the response of ESCC patients before receiving chemo-immunotherapy by testing volatile organic compounds (VOCs) in exhaled breath. METHODS: This study employed a prospective-specimen-collection, retrospective-blinded-evaluation design. Patients' baseline breath samples were collected and analyzed using high-pressure photon ionization time-of-flight mass spectrometry (HPPI-TOFMS). Subsequently, patients were categorized as responders or non-responders based on the evaluation of therapeutic response using pathology (for patients who underwent surgery) or CT images (for patients who did not receive surgery). RESULTS: A total of 133 patients were included in this study, with 91 responders who achieved either a complete response (CR) or a partial response (PR), and 42 non-responders who had stable disease (SD) or progressive disease (PD). Among 83 participants who underwent both evaluations with CT and pathology, the paired t-test revealed significant differences between the two methods (p < 0.05). For the breath test prediction model using breath test data from all participants, the validation set demonstrated mean area under the curve (AUC) of 0.86 ± 0.06. For 83 patients with pathological reports, the breath test achieved mean AUC of 0.845 ± 0.123. CONCLUSIONS: Since CT has inherent weakness in hollow organ assessment and no other ideal biomarker has been found, our study provided a noninvasive, feasible, and inexpensive tool that could precisely predict ESCC patients' response to neoadjuvant chemo-immunotherapy combination using breath test based on HPPI-TOFMS.

Adaptively leverage multiple real-world data sources for treatment effect estimation based on similarity.

The incorporation of real-world data (RWD) into medical product development and evaluation has exhibited consistent growth. However, there is no universally adopted method of how much information to borrow from external data. This paper proposes a study design methodology called Tree-based Monte Carlo (TMC) that dynamically integrates patients from various RWD sources to calculate the treatment effect based on the similarity between clinical trial and RWD. Initially, a propensity score is developed to gauge the resemblance between clinical trial data and each real-world dataset. Utilizing this similarity metric, we construct a hierarchical clustering tree that delineates varying degrees of similarity between each RWD source and the clinical trial data. Ultimately, a Gaussian process methodology is employed across this hierarchical clustering framework to synthesize the projected treatment effects of the external group. Simulation result shows that our clustering tree could successfully identify similarity. Data sources exhibiting greater similarity with clinical trial are accorded higher weights in treatment estimation process, while less congruent sources receive comparatively lower emphasis. Compared with another Bayesian method, meta-analytic predictive prior (MAP), our proposed method's estimator is closer to the true value and has smaller bias.

A bidirectional interpretable compound-protein interaction prediction framework based on cross attention.

The identification of compound-protein interactions (CPIs) plays a vital role in drug discovery. However, the huge cost and labor-intensive nature in vitro and vivo experiments make it urgent for researchers to develop novel CPI prediction methods. Despite emerging deep learning methods have achieved promising performance in CPI prediction, they also face ongoing challenges: (i) providing bidirectional interpretability from both the chemical and biological perspective for the prediction results; (ii) comprehensively evaluating model generalization performance; (iii) demonstrating the practical applicability of these models. To overcome the challenges posed by current deep learning methods, we propose a cross multi-head attention oriented bidirectional interpretable CPI prediction model (CmhAttCPI). First, CmhAttCPI takes molecular graphs and protein sequences as inputs, utilizing the GCW module to learn atom features and the CNN module to learn residue features, respectively. Second, the model applies cross multi-head attention module to compute attention weights for atoms and residues. Finally, CmhAttCPI employs a fully connected neural network to predict scores for CPIs. We evaluated the performance of CmhAttCPI on balanced datasets and imbalanced datasets. The results consistently show that CmhAttCPI outperforms multiple state-of-the-art methods. We constructed three scenarios based on compound and protein clustering and comprehensively evaluated the model generalization ability within these scenarios. The results demonstrate that the generalization ability of CmhAttCPI surpasses that of other models. Besides, the visualizations of attention weights reveal that CmhAttCPI provides chemical and biological interpretation for CPI prediction. Moreover, case studies confirm the practical applicability of CmhAttCPI in discovering anticancer candidates.

Improving the classification of multiple sclerosis and cerebral small vessel disease with interpretable transfer attention neural network.

As an autoimmune-mediated inflammatory demyelinating disease of the central nervous system, multiple sclerosis (MS) is often confused with cerebral small vessel disease (cSVD), which is a regional pathological change in brain tissue with unknown pathogenesis. This is due to their similar clinical presentations and imaging manifestations. That misdiagnosis can significantly increase the occurrence of adverse events. Delayed or incorrect treatment is one of the most important causes of MS progression. Therefore, the development of a practical diagnostic imaging aid could significantly reduce the risk of misdiagnosis and improve patient prognosis. We propose an interpretable deep learning (DL) model that differentiates MS and cSVD using T2-weighted fluid-attenuated inversion recovery (FLAIR) images. Transfer learning (TL) was utilized to extract features from the ImageNet dataset. This pioneering model marks the first of its kind in neuroimaging, showing great potential in enhancing differential diagnostic capabilities within the field of neurological disorders. Our model extracts the texture features of the images and achieves more robust feature learning through two attention modules. The attention maps provided by the attention modules provide model interpretation to validate model learning and reveal more information to physicians. Finally, the proposed model is trained end-to-end using focal loss to reduce the influence of class imbalance. The model was validated using clinically diagnosed MS (n=112) and cSVD (n=321) patients from the Beijing Tiantan Hospital. The performance of the proposed model was better than that of two commonly used DL approaches, with a mean balanced accuracy of 86.06 % and a mean area under the receiver operating characteristic curve of 98.78 %. Moreover, the generated attention heat maps showed that the proposed model could focus on the lesion signatures in the image. The proposed model provides a practical diagnostic imaging aid for the use of routinely available imaging techniques such as magnetic resonance imaging to classify MS and cSVD by linking DL to human brain disease. We anticipate a substantial improvement in accurately distinguishing between various neurological conditions through this novel model.