Oncological Applications of Quantum Machine Learning.

Background: Cancer is a leading cause of death worldwide. Machine learning (ML) and quantum computers (QCs) have recently advanced significantly. Numerous studies have examined the application of quantum machine learning (QML) in healthcare and validated its superiority over classical ML algorithms. Objectives: This review investigates and reports the oncological applications of QML. Methods: In March 2023, an electronic investigation of PubMed, Scopus, Web of Science, IEEE, and Cochrane databases was performed. The articles were screened based on titles and abstracts, and their full texts were examined. Results: Initially, a total of 207 articles were retrieved. Thereafter, 9 articles were included in the study, most of which were published from 2020 onwards. The results indicated the implementation of various QML techniques in different aspects of oncology, such as reducing mammography image noise, edge detection of breast cancer, clinical decision support in radiotherapy treatment, and cancer classification. Conclusion: These studies revealed that integrating quantum science with ML can significantly improve patient care and clinical outcomes. Future studies should explore the integration of QC and ML and the development of novel algorithms to enhance cancer prognosis, diagnosis, and treatment planning.

Effective connectivity between deep brain stimulation targets in individuals with treatment-resistant depression.

The therapeutic effect of deep brain stimulation on patients with treatment-resistant depression is strongly dependent on the connectivity of the stimulation region with other regions associated with depression. The aims of this study are to characterize the effective connectivity between the brain regions playing important roles in depression and further investigate the underlying pathophysiological mechanisms of treatment-resistant depression and the mechanisms involving deep brain stimulation. Thirty-three individuals with treatment-resistant depression and 29 healthy control subjects were examined. All subjects underwent resting-state functional MRI scanning. The coupling parameters reflecting the causal interactions among deep brain stimulation targets and medial prefrontal cortex were estimated using spectral dynamic causal modelling. Our results showed that compared to the healthy control subjects, in the left hemisphere of treatment-resistant depression patients, the nucleus accumbens was inhibited by the inferior thalamic peduncle and excited the ventral caudate and the subcallosal cingulate gyrus, which in turn excited the lateral habenula. In the right hemisphere, the lateral habenula inhibited the ventral caudate and the nucleus accumbens, both of which inhibited the inferior thalamic peduncle, which in turn inhibited the cingulate gyrus. The ventral caudate excited the lateral habenula and the cingulate gyrus, which excited the medial prefrontal cortex. Furthermore, these effective connectivity links varied between males and females, and the left and right hemispheres. Our findings suggest that intrinsic excitatory/inhibitory connections between deep brain stimulation targets are impaired in treatment-resistant depression patients, and that these connections are sex dependent and hemispherically lateralized. This knowledge can help to better understand the underlying mechanisms of treatment-resistant depression, and along with tractography, structural imaging, and other relevant clinical information, may assist to determine the appropriate region for deep brain stimulation therapy in each treatment-resistant depression patient.

Cervical cancer survival prediction by machine learning algorithms: a systematic review.

BACKGROUND: Cervical cancer is a common malignant tumor of the female reproductive system and is considered a leading cause of mortality in women worldwide. The analysis of time to event, which is crucial for any clinical research, can be well done with the method of survival prediction. This study aims to systematically investigate the use of machine learning to predict survival in patients with cervical cancer. METHOD: An electronic search of the PubMed, Scopus, and Web of Science databases was performed on October 1, 2022. All articles extracted from the databases were collected in an Excel file and duplicate articles were removed. The articles were screened twice based on the title and the abstract and checked again with the inclusion and exclusion criteria. The main inclusion criterion was machine learning algorithms for predicting cervical cancer survival. The information extracted from the articles included authors, publication year, dataset details, survival type, evaluation criteria, machine learning models, and the algorithm execution method. RESULTS: A total of 13 articles were included in this study, most of which were published from 2018 onwards. The most common machine learning models were random forest (6 articles, 46%), logistic regression (4 articles, 30%), support vector machines (3 articles, 23%), ensemble and hybrid learning (3 articles, 23%), and Deep Learning (3 articles, 23%). The number of sample datasets in the study varied between 85 and 14946 patients, and the models were internally validated except for two articles. The area under the curve (AUC) range for overall survival (0.40 to 0.99), disease-free survival (0.56 to 0.88), and progression-free survival (0.67 to 0.81), respectively from (lowest to highest) received. Finally, 15 variables with an effective role in predicting cervical cancer survival were identified. CONCLUSION: Combining heterogeneous multidimensional data with machine learning techniques can play a very influential role in predicting cervical cancer survival. Despite the benefits of machine learning, the problem of interpretability, explainability, and imbalanced datasets is still one of the biggest challenges. Providing machine learning algorithms for survival prediction as a standard requires further studies.

Effective connectivity between emotional and motor brain regions in people with psychogenic nonepileptic seizures (PNES).

OBJECTIVE: To characterize the effective connectivity (EC) between the emotion and motor brain regions in patients with psychogenic nonepileptic seizures (PNES), based on resting-state spectral dynamic causal modeling (spDCM). METHODS: Twenty-three patients with PNES and twenty-five healthy control (HC) subjects underwent resting-state fMRI scanning. The coupling parameters indicating the causal interactions between eight brain regions associated with emotion, executive control, and motion were estimated for both groups, using resting-state fMRI spDCM. RESULTS: Compared to the HC subjects, in patients with PNES: (i) the left insula (INS) and left and right inferior frontal gyri (IFG) are more inhibited by the amygdala (AMYG), anterior cingulate cortex (ACC), and precentral gyrus (PCG); (ii) the left AMYG has greater inhibitory effects on the INS, IFG, dorsolateral prefrontal cortex (DLPFC), PCG, and supplementary motor area (SMA); (iii) the left ACC has more inhibitory effects on the INS and IFG; (iv) the right ACC is more inhibited by the INS and IFG, and has a less inhibitory effect on the SMA and PCG; and (v) the left caudate (CAU) had increased inhibitory effects on the AMYG and IFG and a more excitatory effect on the SMA. CONCLUSION: Our results suggest that in patients with PNES, the emotion-processing regions have inhibitory effects on the executive control areas and motor regions. Our findings may provide further insight into the influence of emotional arousal on functional movements and the underlying mechanisms of involuntary movements during functional seizures. Furthermore, they may suggest that emotion regulation through cognitive behavioral psychotherapies can be a potentially effective treatment modality.