Surgical scheduling via optimization and machine learning with long-tailed data : Health care management science, in press

Using data from cardiovascular surgery patients with long and highly variable post-surgical lengths of stay (LOS), we develop a modeling framework to reduce recovery unit congestion. We estimate the LOS and its probability distribution using machine learning models, schedule procedures on a rolling basis using a variety of optimization models, and estimate performance with simulation. The machine learning models achieved only modest LOS prediction accuracy, despite access to a very rich set of patient characteristics. Compared to the current paper-based system used in the hospital, most optimization models failed to reduce congestion without increasing wait times for surgery. A conservative stochastic optimization with sufficient sampling to capture the long tail of the LOS distribution outperformed the current manual process and other stochastic and robust optimization approaches. These results highlight the perils of using oversimplified distributional models of LOS for scheduling procedures and the importance of using optimization methods well-suited to dealing with long-tailed behavior.

Serum immunoglobulin E and immunoglobulin G reactivity to Agaricus bisporus proteins in mushroom cultivation workers

BACKGROUND AND PURPOSE

Although molds are regarded as the main fungal allergen sources, evidence indicates that spores of Basidiomycota including Agaricus bisporus (A. bisporus) can be also found at high concentrations in the environment and may cause as many respiratory allergies as molds. The aim of the present study was to evaluate specific immunoglobulin E (IgE) and immunoglobulin G (IgG) antibodies against A. bisporus via immunoblotting technique in individuals working at mushroom cultivation centers.

MATERIALS AND METHODS

In this study, 72 workers involved in the cultivation and harvest of button mushrooms were enrolled. For the analysis of serum IgE and IgG, A. bisporus grown in Sabouraud dextrose broth was harvested and ruptured by liquid nitrogen and glass beads. The obtained sample was centrifuged and the supernatant was collected as "crude extract" (CE). CE was separated via Sodium Dodecyl Sulfate-Polyacrylamide Gel Electrophoresis (SDS-PAGE). The separated proteins were transferred to a nitrocellulose filter and the bands responsive to IgE and IgG were identified by anti-human conjugated antibodies. All participants were screened in terms of total IgE level.

RESULTS

Among 72 workers, 18 (25%) had a total IgE level higher than 188 IU/mL. In SDS-PAGE, the CE of A. bisporus showed 23 different protein bands with a molecular weight range of 13-80 kDa. The sera of 23.6% and 55.5% of participants showed positive response, with specific IgE and IgG antibodies against A. bisporus in the blot, respectively. The bands with molecular weights of 62 and 68 kDa were the most reactive protein components of A. bisporus to specific IgE antibodies. Moreover, bands with molecular weights of 57 and 62 kDa showed the highest reactivity to IgG, respectively. Also, 62 and 68 kDa components were the most reactive bands with both specific IgG and IgE antibodies.

CONCLUSION

The obtained findings revealed that A. bisporus has different allergens and antigens, which contribute to its potential as an aeroallergen in hypersensitivity-related reactions of the lungs.