Building Flexible, Scalable, and Machine Learning-Ready Multimodal Oncology Datasets.

The advancements in data acquisition, storage, and processing techniques have resulted in the rapid growth of heterogeneous medical data. Integrating radiological scans, histopathology images, and molecular information with clinical data is essential for developing a holistic understanding of the disease and optimizing treatment. The need for integrating data from multiple sources is further pronounced in complex diseases such as cancer for enabling precision medicine and personalized treatments. This work proposes Multimodal Integration of Oncology Data System (MINDS)-a flexible, scalable, and cost-effective metadata framework for efficiently fusing disparate data from public sources such as the Cancer Research Data Commons (CRDC) into an interconnected, patient-centric framework. MINDS consolidates over 41,000 cases from across repositories while achieving a high compression ratio relative to the 3.78 PB source data size. It offers sub-5-s query response times for interactive exploration. MINDS offers an interface for exploring relationships across data types and building cohorts for developing large-scale multimodal machine learning models. By harmonizing multimodal data, MINDS aims to potentially empower researchers with greater analytical ability to uncover diagnostic and prognostic insights and enable evidence-based personalized care. MINDS tracks granular end-to-end data provenance, ensuring reproducibility and transparency. The cloud-native architecture of MINDS can handle exponential data growth in a secure, cost-optimized manner while ensuring substantial storage optimization, replication avoidance, and dynamic access capabilities. Auto-scaling, access controls, and other mechanisms guarantee pipelines' scalability and security. MINDS overcomes the limitations of existing biomedical data silos via an interoperable metadata-driven approach that represents a pivotal step toward the future of oncology data integration.

Seizure treatment with olfactory training: a preliminary trial.

OBJECTIVE: Epilepsy is a chronic condition characterized by recurrent seizures. Despite miscellaneous antiseizure medications, resistance to treatment is still approximately 30%. This resistance brings forward the multidisciplinary approach and complementary treatments. In this study, we aimed to investigate the effect of olfactory training on epileptic seizures with special aromas having antiseizure effects in patients diagnosed with drug-resistant epilepsy. METHODS: A total of 24 patients (14 pediatric and 10 adults) with drug-resistant epilepsy were recruited for the study. Participants were asked to inhale the standardized bottle filled with lavender aroma (Lavandula Angustifolia) twice a day (morning and evening) for 30-45 s (2 cm in front of nose; 10-15 s to right and left nostril and 10-15 s to both nostrils) for 3 months. The type, frequency, duration of seizures, the quality of life (SF-36 and PedsQL 4.0), and olfactory functions (Sniffin' Sticks Test and Pediatric Smell Wheel) were re-assessed. RESULTS: Statistical analysis showed that olfactory training decreased the seizure frequency (p < 0.001) and the seizure duration (p = 0.02). A global 50% seizure reduction was seen among patients. Moreover, olfactory training increased the quality of life (p = 0.003) and improved the olfactory function in both the pediatric and adult groups (p = 0.017, p = 0.05, respectively). There was no adverse reaction and no increase in seizure frequency. SIGNIFICANCE: The observations of the present investigation suggest that olfactory training is a successful complementary therapy with no adverse reaction in patients with drug-resistant epilepsy. Large cohort studies and longer follow-up periods are needed for providing olfactory training as a therapy modality in patients with epilepsy.

Transcranial Doppler ultrasonography in patients with hemoglobinopathy: An experience from a tertiary center.

OBJECTIVE: Patients with hemoglobinopathy are prone to cerebrovascular event. Our aim was to screen the peak systolic flow velocity (PSV) using transcranial Doppler ultrasonography (TCD) in terms of cerebrovascular event risk in patients with beta thalassemia (ß-thal) and sickle cell anemia (SCA). METHODS: PSV and resistive index (RI) values were determined at internal carotid artery (ICA) and middle cerebral artery (MCA)-from both temporal regions using TCD. RESULTS: A total of 55 participants (40 patients and 15 healthy people) were included in the study. Thirty-three (60%) of the participants were female. Among 40 patients, 12 patients (30%) had NTDT, 14 patients (35%) had SCA, and 14 patients (35%) had TDT diagnosis. Bilateral ICA and MCA were open in all patients and had a normal flow pattern. PSV and RI were not significantly different between study and control groups in right and left MCA and ICA. Patients with high platelet level (>450.000/mm3) had significantly higher PSV values in right MCA (96 vs.70 cm/s, p=0.05). Among patients with TDT, age of starting iron chelation and right ICA PSV values was significantly negatively correlated (r=-0.56; p=0.04). Clinical symptoms (headache and pain crisis), hydroxyurea, and chelation therapy did not effect PSV values. CONCLUSION: Platelet level and age of starting iron chelation might be an influencing factor for PSV. Regular follow-up of patients, appropriate therapy and lack of other factors causing cerebrovascular events might be possible reason for these acceptable results.

Magnetic resonance imaging during management of patients with transfusion-dependent thalassemia: a single-center experience.

BACKGROUND: Cardiac and hepatic magnetic resonance imaging evaluation during treatment can tailor physicians' chelation therapy titrations. AIM: The aim of the study was to assess the relationship of cardiac and hepatic T2* values with chelation therapy in patients with transfusion-dependent thalassemia (TDT). METHODS: A total of 106 patients with TDT who were followed up in Istanbul Medical Faculty Thalassemia Center were evaluated for the study. Forty-eight (45%) patients with TDT had more than one consecutive MRI examination. The patients were divided into three subgroups according to the cardiac T2* values as the high-risk group (T2* MRI < 10 ms), medium-risk group (T2* MRI 10-20 ms), and the low-risk group (T2* MRI > 20 ms). RESULTS: The majority of patients used DFX (deferasirox) (79%) and deferiprone (DFP) (17%). Approximately 80% of patients according to cardiac T2* value and 40% of patients according to hepatic T2* value were initially in the low-risk group. Patients with follow-up MRI examinations exhibited significant improvement in liver iron concentration, which correlated with an increase in hepatic T2* values. The decrease of liver iron concentration was prominent in the DFX group (p < 0.01). The serum ferritin level was significantly correlated with liver iron concentrations (rs = 0.65, p < 0.001), hepatic T2* value (rs = - 0.62, p < 0.001), but not with cardiac T2* value (rs = - 0.20, p = 0.07). CONCLUSION: Cardiovascular and hepatic MRI is a useful follow-up tool during the assessment of risk groups and chelation therapy of patients with TDT. Consecutive MRI tests showed good monitoring of cardiac and liver iron overload.