Improving the Accuracy of Physics-Based Hydration-Free Energy Predictions by Machine Learning the Remaining Error Relative to the Experiment.

The accuracy of computational models of water is key to atomistic simulations of biomolecules. We propose a computationally efficient way to improve the accuracy of the prediction of hydration-free energies (HFEs) of small molecules: the remaining errors of the physics-based models relative to the experiment are predicted and mitigated by machine learning (ML) as a postprocessing step. Specifically, the trained graph convolutional neural network attempts to identify the "blind spots" in the physics-based model predictions, where the complex physics of aqueous solvation is poorly accounted for, and partially corrects for them. The strategy is explored for five classical solvent models representing various accuracy/speed trade-offs, from the fast analytical generalized Born (GB) to the popular TIP3P explicit solvent model; experimental HFEs of small neutral molecules from the FreeSolv set are used for the training and testing. For all of the models, the ML correction reduces the resulting root-mean-square error relative to the experiment for HFEs of small molecules, without significant overfitting and with negligible computational overhead. For example, on the test set, the relative accuracy improvement is 47% for the fast analytical GB, making it, after the ML correction, almost as accurate as uncorrected TIP3P. For the TIP3P model, the accuracy improvement is about 39%, bringing the ML-corrected model's accuracy below the 1 kcal/mol threshold. In general, the relative benefit of the ML corrections is smaller for more accurate physics-based models, reaching the lower limit of about 20% relative accuracy gain compared with that of the physics-based treatment alone. The proposed strategy of using ML to learn the remaining error of physics-based models offers a distinct advantage over training ML alone directly on reference HFEs: it preserves the correct overall trend, even well outside of the training set.

2011 Recommendations for the diagnosis and management of gout and hyperuricemia.

Gout is a major health problem in the United States; it affects 8.3 million people, which is approximately 4% of the adult population. Gout is most often diagnosed and managed in primary care physician practices. Primary care physicians have a significant opportunity to diagnose and manage patients with gout and improve patient outcomes. Following publication of the 2006 European League Against Rheumatism (EULAR) gout guidelines, significant evidence on gout has accumulated and new treatments for patients with gout have become available. It is the objective of these 2011 recommendations for the diagnosis and management of gout and hyperuricemia to update the 2006 EULAR guidelines, paying special attention to the needs of primary care physicians, who manage most patients with gout. The revised 2011 recommendations are based on the Grading of Recommendations Assessment, Development, and Evaluation approach as an evidence-based strategy for rating quality of evidence and grading strength of recommendation in clinical practice. A total of 26 key recommendations for diagnosis (n = 10) and management (n = 16) were evaluated. Presence of tophus (proven or suspected) and response to colchicine had the highest clinical diagnostic value (likelihood ratio [LR], 15.56 [95% CI, 2.11-114.71] and LR, 4.33 [95% CI, 1.16-16.16], respectively). The key aspect of effective management of an acute gout attack is initiation of treatment within hours of onset of first symptoms. Low-dose colchicine is better tolerated than and is as effective as high-dose colchicine (number needed to treat [NNT], 5 [95% CI, 3-13] and NNT, 6 [95% CI, 3-72], respectively). For urate-lowering therapy, allopurinol in combination with probenecid was shown to be more effective than either agent alone (effect size [ES], 5.51 for combination; ES, 4.46 for probenecid; and ES, 2.80 for allopurinol). Febuxostat, also a xanthine oxidase inhibitor, has a slightly different mechanism of action and can be prescribed at unchanged doses for patients with mild-to-moderate renal or hepatic impairment. Febuxostat 40 mg versus 80 mg (NNT, 6 [95% CI, 4-11]) and 120 mg (NNT, 6 [95% CI, 3-26]) both demonstrated long-term efficacy. The target of urate-lowering therapy should be a serum uric acid level of ≤ 6 mg/dL. For patients with refractory and tophaceous gout, intravenous pegloticase is a new treatment option.

Multiple primary cancers including mesothelioma of the tunica vaginalis: case report and literature review with primary care focus.

The development of multiple primary malignancies in an individual is rare and unfortunate, and the care of such a patient presents specific challenges. We report the diagnosis and progression of 3 histologically different primary cancers in 1 patient over the course of 15 years. At age 50 years, the patient received a diagnosis of transitional cell carcinoma of the bladder; treatment was successful. When the patient was 64 years old, mesothelioma of the tunica vaginalis was diagnosed, and computed tomography performed for staging purposes revealed a lung lesion, which was later diagnosed as adenocarcinoma. Treatment for the adenocarcinoma was also successful, but the patient continues to have recurrence of mesothelioma. To our knowledge, the present report is the first description of a case of 3 primary cancers that includes a mesothelioma of the tunica vaginalis. Because mesothelioma of the tunica vaginalis is rare, we reviewed the literature on its prevalence, presentation, management, and prognosis.

2011 recommendations for the diagnosis and management of gout and hyperuricemia.

Gout is a major health problem in the United States; it affects 8.3 million people, which is approximately 4% of the adult population. Gout is most often diagnosed and managed in primary care practices; thus, primary care physicians have a significant opportunity to improve patient outcomes. Following publication of the 2006 European League Against Rheumatism (EULAR) gout guidelines, significant new evidence has accumulated, and new treatments for patients with gout have become available. It is the objective of these 2011 recommendations to update the 2006 EULAR guidelines, paying special attention to the needs of primary care physicians. The revised 2011 recommendations are based on the Grading of Recommendations Assessment, Development, and Evaluation approach as an evidence-based strategy for rating quality of evidence and grading the strength of recommendation formulated for use in clinical practice. A total of 26 key recommendations, 10 for diagnosis and 16 for management, of patients with gout were evaluated, resulting in important updates for patient care. The presence of monosodium urate crystals and/or tophus and response to colchicine have the highest clinical diagnostic value. The key aspect of effective management of an acute gout attack is initiation of treatment within hours of symptom onset. Low-dose colchicine is better tolerated and is as effective as a high dose. When urate-lowering therapy (ULT) is indicated, the xanthine oxidase inhibitors allopurinol and febuxostat are the options of choice. Febuxostat can be prescribed at unchanged doses for patients with mild-to-moderate renal or hepatic impairment. The target of ULT should be a serum uric acid level that is ≤ 6 mg/dL. For patients with refractory and tophaceous gout, intravenous pegloticase is a new treatment option. This article is a summary of the 2011 clinical guidelines published in Postgraduate Medicine. This article provides a streamlined, accessible overview intended for quick review by primary care physicians, with the full guidelines being a resource for those seeking additional background information and expanded discussion.