Background: Malignant Mesothelioma (MM) is a rare but aggressive tumor that arises in the lungs. Commonly, costly imaging and laboratory resources, i.e., X-ray imaging, magnetic resonance imaging (MRI), positron emission tomography (PET) scans, biopsies, and blood tests, have already been utilized for the diagnosis of MM. Even though these diagnostic measures are expensive and unavailable in distant areas, some of these diagnostic methods are also very painful for the patient, including biopsy and cytology of pleural fluid. Objective: In this study, we proposed a diagnostic model for early identification of MM via machine learning techniques. We explored the health records of 324 Turkish patients, which showed the symptoms related to MM. The data of patients included socio-economic, geographical, and clinical features. Methods: Different feature selection methods have been employed for the selection of significant features. To overcome the data imbalance problem, various data-level resampling techniques have been utilized to obtain efficient results. The gradient boosted decision tree (GBDT) method has been used to develop the diagnostic model. The performance of the GBDT model is also compared with traditional machine learning algorithms. Results and Conclusion: Our model's results outperformed other models, both on balance and imbalance data. The results clearly show that undersampling techniques outperformed imbalanced data without resampling based on accuracy and receiving operating characteristic (ROC) value. Conversely, it has also been observed that oversampling techniques outperformed undersampling and imbalanced data based on accuracy and ROC. All classifiers employed in this study achieved efficient results utilizing feature selection-based methods (OneR, information gain, and Relief-F), but the other two methods (gain ratio and correlation) results were not entirely promising. Finally, when the combination of Synthetic Minority Oversampling Technique (SMOTE) and OneR was applied with GBDT, it gave the most favorable results based on accuracy, F-measure, and ROC. The diagnosis model has also been deployed to assist doctors, patients, medical practitioners, and other healthcare professionals for early diagnosis and better treatment of MM.

Clinical Scenario During routine staging work-up for a left breast mass, a 68-year-old woman complained of dysphagia and dysphonia. During further investigations, a left-sided lesion at the foramen magnum was observed on brain imaging. Both lesions were biopsied and showed a classical chordoma. ManagementThe skull-base lesion and the breast lesion were surgically resected, and adjuvant radiotherapy was given.Summary Chordoma is a rare primary central nervous system tumour that seldom metastasizes. The lung is the most common site of metastasis. Synchronous breast metastasis from a skull-base chordoma is very rare, and a safe management option includes a maximum resection followed by adjuvant radiotherapy.

No abstract

The fully-automated planning sequences took w15 minutes of optimization time. As shown in Table 1, the resulting clinically-deliverable automated plans were selected by the physician subjects 70% of the time (HOT: 57%, COLD: 13%, Clinical: 30%). Within the 30% of cases where the manually-planned treatments were selected, in 19 out of 43 instances the reviewing physician deemed the differences between the clinical plan and the closest automated plan to be clinically insignificant. In the 24 cases where the manually-planned treatments were preferred, 21 plans were selected because of more aggressive OAR sparing (brainstem, cochlea, or optic nerve) and 3 plans were selected because the manual plans better spared a nearby volume that received prior radiation therapy. Conclusion: In a clear majority (120/144 Z 83%) of cases, automated SRS planning demonstrated superior or equivalent plan quality to existing manual planning processes. Further refinement of algorithms to balance the complex clinical tradeoffs for high-priority OARs and to account for instances of retreatment will likely improve performance even further.