Surgery Duration Prediction using Multitask Feature Selection.

Efficient optimization of operation room (OR) activity poses a significant challenge for hospital managers due to the complex and risky nature of the environment. The traditional "one size fits all" approach to OR scheduling is no longer practical, and personalized medicine is required to meet the diverse needs of patients, care providers, medical procedures, and system constraints within limited resources. This paper aims to introduce a scientific and practical tool for predicting surgery durations and improving OR performance for maximum benefit to patients and the hospital. Previous works used machine-learning models for surgery duration prediction based on preoperative data. The models consider covariates known to the medical staff at the time of scheduling the surgery. However, model selection becomes crucial, where the number of covariates used for prediction depend on the available sample size. Our proposed approach utilizes multitask regression to select a common subset of predicting covariates for all tasks with the same sample size while allowing the model's coefficients to vary between them. A regression task can refer to a single surgeon or operation type or the interaction between them. By considering these diverse factors, our method provides an overall more accurate estimation of the surgery durations, and the selected covariates that enter the model may help to identify the resources required for a specific surgery. We found that when the regression tasks were surgeon-based or based on the pair of operation type and surgeon, our suggested approach outperformed the compared baseline suggested in a previous study. However, our approach failed to reach the baseline for an operation type-based task. By accurately estimating surgery durations, hospital managers can provide care to a greater number of patients, optimize resource allocation and utilization, and reduce waste. This research contributes to the advancement of personalized medicine and provides a valuable tool for improving operational efficiency in the dynamic world of medicine.

Functional Benefit and Orthotic Effect of Dorsiflexion-FES in Children with Hemiplegic Cerebral Palsy.

Functional electrical stimulation of the ankle dorsiflexor (DF-FES) may have advantages over ankle foot orthoses (AFOs) in managing pediatric cerebral palsy (CP). This study assessed the functional benefit and orthotic effect of DF-FES in children with hemiplegic CP. We conducted an open-label prospective study on children with hemiplegic CP ≥ 6 years who used DF-FES for five months. The functional benefit was assessed by repeated motor function tests and the measurement of ankle biomechanical parameters. Kinematic and spatiotemporal parameters were assessed by gait analysis after one and five months. The orthotic effect was defined by dorsiflexion ≥ 0° with DF-FES at either the mid or terminal swing. Among 26 eligible patients, 15 (median age 8.2 years, range 6-15.6) completed the study. After five months of DF-FES use, the results on the Community Balance and Mobility Scale improved, and the distance in the Six-Minute Walk Test decreased (six-point median difference, 95% CI (1.89, 8.1), -30 m, 95% CI (-83.67, -2.6), respectively, p < 0.05) compared to baseline. No significant changes were seen in biomechanical and kinematic parameters. Twelve patients (80%) who showed an orthotic effect at the final gait analysis experienced more supported walking over time, with a trend toward slower walking. We conclude that the continuous use of DF-FES increases postural control and may cause slower but more controlled gait.

Head and Neck Cutaneous Squamous Cell Carcinoma Clinicopathological Risk Factors according to Age and Gender: A Population-based Study.

BACKGROUND: Clinicopathological risk factors for cutaneous squamous cell carcinoma of the head and neck (CSCCHN) are associated with local recurrence and metastasis. OBJECTIVES: To compare the incidence and risk factors of CSCCHN by age and gender in order to help refine the clinical evaluation and treatment process. METHODS: Clinical and pathological data of all patients diagnosed with CSCCHN during 2009-2011 were obtained from a central pathology laboratory in Israel. Estimated incidence rate calculation was standardized to the 2010 Israeli population. Independent risk factors for poorly differentiated CSCCHN were analyzed using logistic regression. RESULTS: CSCCHN was diagnosed in 621 patients. Mean age was 75.2 years; mean tumor horizontal diameter was 11.1 ± 6.8 mm. The overall estimated incidence rate in males was higher than in females (106.2 vs. 54.3 per 1,000,000, P 0.001). Twenty cases (3.2%) had poorly differentiated CSCCHN. Scalp and ear anatomic locations were observed more often in males than in females (22.1% vs. 6.1% and 20.3% vs. 3.3%, respectively, P < 0.001). Per 1 mm increment, tumor horizontal diameter increased the risk for poorly differentiated CSCCHN by 6.7% (95% CI 1.3-12.4%, P = 0.014). CONCLUSIONS: CSCCHN clinicopathological risk factors are not distributed evenly among different age and gender groups.

The Empirical Distribution of a Large Number of Correlated Normal Variables.

Motivated by the advent of high dimensional highly correlated data, this work studies the limit behavior of the empirical cumulative distribution function (ecdf) of standard normal random variables under arbitrary correlation. First, we provide a necessary and sufficient condition for convergence of the ecdf to the standard normal distribution. Next, under general correlation, we show that the ecdf limit is a random, possible infinite, mixture of normal distribution functions that depends on a number of latent variables and can serve as an asymptotic approximation to the ecdf in high dimensions. We provide conditions under which the dimension of the ecdf limit, defined as the smallest number of effective latent variables, is finite. Estimates of the latent variables are provided and their consistency proved. We demonstrate these methods in a real high-dimensional data example from brain imaging where it is shown that, while the study exhibits apparently strongly significant results, they can be entirely explained by correlation, as captured by the asymptotic approximation developed here.

Dose-finding designs: the role of convergence properties.

It is common for novel dose-finding designs to be presented without a study of their convergence properties. In this article we suggest that examination of convergence is a necessary quality check for dose-finding designs. We present a new convergence proof for a nonparametric family of methods called "interval designs," under certain conditions on the toxicity-frequency function F. We compare these conditions with the convergence conditions for the popular CRM one-parameter Phase I cancer design, via an innovative numerical sensitivity study generating a diverse sample of dose-toxicity scenarios. Only a small fraction of scenarios meet the Shen-O'Quigley convergence conditions for CRM. Conditions for "interval design" convergence are met more often, but still less than half the time. In the discussion, we illustrate how convergence properties and limitations help provide insight about small-sample behavior.