Designing solvent systems using self-evolving solubility databases and graph neural networks.

Designing solvent systems is key to achieving the facile synthesis and separation of desired products from chemical processes, so many machine learning models have been developed to predict solubilities. However, breakthroughs are needed to address deficiencies in the model's predictive accuracy and generalizability; this can be addressed by expanding and integrating experimental and computational solubility databases. To maximize predictive accuracy, these two databases should not be trained separately, and they should not be simply combined without reconciling the discrepancies from different magnitudes of errors and uncertainties. Here, we introduce self-evolving solubility databases and graph neural networks developed through semi-supervised self-training approaches. Solubilities from quantum-mechanical calculations are referred to during semi-supervised learning, but they are not directly added to the experimental database. Dataset augmentation is performed from 11 637 experimental solubilities to >900 000 data points in the integrated database, while correcting for the discrepancies between experiment and computation. Our model was successfully applied to study solvent selection in organic reactions and separation processes. The accuracy (mean absolute error around 0.2 kcal mol-1 for the test set) is quantitatively useful in exploring Linear Free Energy Relationships between reaction rates and solvation free energies for 11 organic reactions. Our model also accurately predicted the partition coefficients of lignin-derived monomers and drug-like molecules. While there is room for expanding solubility predictions to transition states, radicals, charged species, and organometallic complexes, this approach will be attractive to predictive chemistry areas where experimental, computational, and other heterogeneous data should be combined.

Inadvertent strangulation of inflation line of the pilot balloon during submental endotracheal intubation: a rare complication.

Submental intubation is the preferred type of intubation in patients with complex maxillofacial fractures where oral or nasal intubation cannot be performed. It is also less invasive than tracheostomy in securing the airways. We report a case where an inadvertent strangulation of inflation line of the pilot balloon resulted in inadequate ventilation during submental intubation.

Breast-conserving radiotherapy with simultaneous integrated boost; field-in-field three-dimensional conformal radiotherapy versus inverse intensity-modulated radiotherapy - A dosimetric comparison: Do we need intensity-modulated radiotherapy?

BACKGROUND AND PURPOSE: To examine the feasibility of improving breast-conserving radiotherapy with simultaneous integrated boost (SIB) and analyzing the efficiency of forward versus inverse intensity-modulated radiotherapy (IMRT) techniques in providing the same. MATERIALS AND METHODS: Three-dimensional conformal radiotherapy (3DCRT) field-in-field (FIF) plans with simultaneous and sequential boost and IMRT SIB plans were generated for the datasets of 20 patients who had undergone breast-conserving surgery. The 3 plans were compared dosimetrically for efficiency in terms of planning target volume (PTV) coverage (PTV 95%), homogeneity and conformity, dose delivered to ipsilateral/contralateral lungs (I/L: V10, V20, C/L: Vmean, V5), heart and contralateral breast (Vmean, V30 for heart and Vmean, V1, V5 for C/L breast). RESULTS: The FIF 3DCRT plan with SIB (PLAN B) was more homogeneous than the classical technique with sequential boost (PLAN A). There were less hot spots in terms of Dmax (63.7 ± 1.3) versus Dmax (68.9 ± 1), P < 0.001 and boost V107%, B (0.3 ± 0.7) versus A (3.5 ± 5.99), P = 0.001. The IMRT SIB (PLAN C) did not provide any significant dosimetric advantage over the 3DCRT SIB technique. IMRT SIB plan C was associated with increased dose to contralateral lung in-terms of V5 (10.35 +/- 18.23) vs. (1.13 +/- 4.24), P = 0.04 and Vmean (2.12 ± 2.18) versus Vmean (0.595 ± 0.89), P = 0.008. There was 3-fold greater exposure in terms of Monitor Unit (MU) (1024.9 ± 298.32 versus 281.05 ± 20.23, P < 0.001) and treatment delivery time. CONCLUSIONS: FIF 3DCRT SIB provides a dosimetrically acceptable and technically feasible alternative to the classical 3DCRT plan with sequential boost for breast-conserving radiotherapy. It reduces treatment time by 2 weeks. IMRT SIB does not appear to have any dosimetric advantage; it is associated with significantly higher doses to contralateral lung and heart and radiation exposure in terms of MU.

SU-E-T-218: The IHE-RO Helper Tool: Demonstrating the Connectivity Issues Solved by IHE-RO.

PURPOSE: To develop a Web-based application (IHE-RO Helper) to allow comprehensive review of the interconnectivity and interoperability of various radiotherapy devices established through testing sanctioned by the Integrating Healthcare Enterprise-Radiation Oncology (IHE-RO). MATERIAL AND METHODS: IHE-RO is an initiative sponsored by ASTRO to improve the way computer based systems in radiation oncology share information using well-defined data exchange standards (DICOM / HL7). At the IHE-RO Connectathon events over the last 4 years, 11 vendors with 14 different products have successfully tested and identified solutions to connectivity problems in treatment planning, simulation and delivery. Because the test results are highly technical, the interconnectivity issues amongst the RT devices may get overlooked by the end users. The IHE-RO helper tool is designed to operate in simple clinical terms with queries and presentations organized based on treatment techniques and clinical features that are familiar to the practitioners. For example, if you are planning to purchase a treatment planning system capable of generating plans (e.g. Stereotactic treatments) and are concerned whether the TPS can successfully transfer such data to your treatment management system (TMS) and subsequently to your treatment delivery system (TDS), the IHE-RO Helper can identify the connectivity requirements and list vendors that have successfully passed an IHE-RO Connectathon and validated their solution to the specific requirements. RESULTS: The IHE-RO helper tool provides a graphical and textual user interface to effectively demonstrate the solved interconnectivity problems between TPS, TMS and TDS. A report is also provided that explains the interconnectivity problems and its solutions. CONCLUSIONS: The IHE-RO helper is an effective tool to clearly identify vendor products that are IHE-RO compliant, thereby encourages vendor participation in testing and validation. Such a tool will be invaluable in procurement of new equipment to ensure a priori interoperability with anticipated RT devices deployed in the clinic. This research and development project is supported by the Bankhead-Coley Cancer Research Program grant # RC1-09BW-09-26833.