Jerrold H. May

Surgical subspecialty block utilization and capacity planning: a minimal cost analysis model.

BACKGROUND Operational inefficiencies in the use of operating rooms (ORs) are hidden by traditional measures of OR utilization. To better detect these inefficiencies, the authors defined two new terms, underutilization and overutilization, and illustrated how these measures might be used to evaluate the use of surgical subspecialty ORs. The authors also described capacity planning (optimizing surgical subspecialty block time allotments) using a minimal cost analysis (MCA) model. METHODS The authors evaluated post hoc all surgeries performed over 6 yr at a large teaching hospital. To prepare utilization estimates, surgical records were categorized relative to budgeted OR block time for each subspecialty. Surgical cases beginning and ending during budgeted OR block time were categorized as budgeted utilization, budgeted time not used for surgery was underutilization, and cases beginning before/after budgeted block time were classified as overutilization. Cases that overlapped budgeted and nonbudgeted OR block time were parsed and the portions were assigned appropriately. Probability distributions were fitted to the historical patterns of surgical demand, and MCA block time budgets were estimated that minimized the costs of underutilization and overutilization for each subspecialty. To illustrate the potential savings if these MCA budgets were implemented, the authors compared actual operational costs to the estimated MCA budget costs and expressed the savings as a percentage of actual costs. RESULTS The authors analyzed data from 58,251 surgical cases and 10 surgical subspecialty blocks. Classic utilization for each block-day by surgical subspecialty ranged from 44-113%. Average daily block-specific underutilization ranged from 16 to 60%, whereas overutilization ranged from 4 to 49%. CONCLUSIONS Underutilization and overutilization are important measures because they may be used to evaluate the quality of OR schedules and the efficiency of OR utilization. Overutilization and underutilization also allow capacity planning using an MCA model This study indicated that the potential savings, if the MCA budgets were to be implemented, would be significant.

Modeling the uncertainty of surgical procedure times: comparison of log-normal and normal models.

Background: Medical institutions are under increased economic pressure to schedule elective surgeries efficiently to contain the costs of surgical services. Surgical scheduling is complicated by variability inherent in the duration of surgical procedures. Modeling that variability, in turn, provides a mechanism to generate accurate time estimates. Accurate time estimates are important operationally to improve operating room utilization and strategically to identify surgeons, procedures, or patients whose duration of surgeries differ from what might be expected. Methods: The authors retrospectively studied 40,076 surgical cases (1,580 Current Procedural Terminology–anesthesia combinations, each with a case frequency of five or more) from a large teaching hospital, and attempted to determine whether the distribution of surgical procedure times more closely fit a normal or a log-normal distribution. The authors tested goodness-of-fit to these data for both models using the Shapiro–Wilk test. Reasons, in practice, the Shapiro–Wilk test may reject the fit of a log-normal model when in fact it should be retained were also evaluated. Results: The Shapiro–Wilk test indicates that the log-normal model is superior to the normal model for a large and diverse set of surgeries. Goodness-of-fit tests may falsely reject the log-normal model during certain conditions that include rounding errors in procedure times, large sample sizes, untrimmed outliers, and heterogeneous mixed populations of surgical procedure times. Conclusions: The authors recommend use of the log-normal model for predicting surgical procedure times for Current Procedural Terminology–anesthesia combinations. The results help to legitimize the use of log transforms to normalize surgical procedure times before hypothesis testing using linear statistical models or other parametric statistical tests to investigate factors affecting the duration of surgeries.

Surgeon and type of anesthesia predict variability in surgical procedure times

Background Variability in surgical procedure times increases the cost of healthcare delivery by increasing both the underutilization and overutilization of expensive surgical resources. To reduce variability in surgical procedure times, we must identify and study its sources. Methods Our data set consisted of all surgeries performed over a 7-yr period at a large teaching hospital, resulting in 46,322 surgical cases. To study factors associated with variability in surgical procedure times, data mining techniques were used to segment and focus the data so that the analyses would be both technically and intellectually feasible. The data were subdivided into 40 representative segments of manageable size and variability based on headers adopted from the common procedural terminology classification. Each data segment was then analyzed using a main-effects linear model to identify and quantify specific sources of variability in surgical procedure times. Results The single most important source of variability in surgical procedure times was surgeon effect. Type of anesthesia, age, gender, and American Society of Anesthesiologists risk class were additional sources of variability. Intrinsic case-specific variability, unexplained by any of the preceding factors, was found to be highest for shorter surgeries relative to longer procedures. Variability in procedure times among surgeons was a multiplicative function (proportionate to time) of surgical time and total procedure time, such that as procedure times increased, variability in surgeons’ surgical time increased proportionately. Conclusions Surgeon-specific variability should be considered when building scheduling heuristics for longer surgeries. Results concerning variability in surgical procedure times due to factors such as type of anesthesia, age, gender, and American Society of Anesthesiologists risk class may be extrapolated to scheduling in other institutions, although specifics on individual surgeons may not. This research identifies factors associated with variability in surgical procedure times, knowledge of which may ultimately be used to improve surgical scheduling and operating room utilization.

Surgical Suite Utilization and Capacity Planning: A Minimal Cost Analysis Model

In this paper, we are concerned with cost reduction, operating suite utilization, and capacity planning in surgical services. We studied 58,251 computerized surgical records from a teaching hospital to determine a model for measuring operating suite utilization, analyzing the quality of surgical schedules, and allocating surgical suite budgets (capacity planning). The classical definition of operating suite (OR) utilization, encountered in the literature is the ratio of the total OR time used to the total OR time allocated or budgeted. To create a better measure of utilization, we measured underutilization and overutilization providing a more complete description of the overall use of resources. Because the costs of under and overutilization of operating suites are high, they are attractive potential targets for cost minimization and the magnitude of the potential savings are such that attempts to measure and eliminate this inefficiency could be financially rewarding.

Fitting the Lognormal Distribution to Surgical Procedure Times

Minimum surgical times are positive and often large. The lognormal distribution has been proposed for modeling surgical data, and the three-parameter form of the lognormal, which includes a location parameter, should be appropriate for surgical data. We studied the goodness-of-fit performance, as measured by the Shapiro-Wilk p-value, of three estimators of the location parameter for the lognormal distribution, using a large data set of surgical times. Alternative models considered included the normal distribution and the two-parameter lognormal model, which sets the location parameter to zero. At least for samples with n > 30, data adequately fit by the normal had significantly smaller skewness than data not well fit by the normal, and data with larger relative minima (smallest order statistic divided by the mean) were better fit by a lognormal model. The rule “If the skewness of the data is greater than 0.35, use the three-parameter lognormal with the location parameter estimate proposed by Muralidhar & Zanakis (1992), otherwise, use the two-parameter model” works almost as well at specifying the lognormal model as more complex guidelines formulated by linear discriminant analysis and by tree induction.

Estimating times of surgeries with two component procedures: comparison of the lognormal and normal models.

Background Variability inherent in the duration of surgical procedures complicates surgical scheduling. Modeling the duration and variability of surgeries might improve time estimates. Accurate time estimates are important operationally to improve utilization, reduce costs, and identify surgeries that might be considered outliers. Surgeries with multiple procedures are difficult to model because they are difficult to segment into homogenous groups and because they are performed less frequently than single-procedure surgeries. Methods The authors studied, retrospectively, 10,740 surgeries each with exactly two CPTs and 46,322 surgical cases with only one CPT from a large teaching hospital to determine if the distribution of dual-procedure surgery times fit more closely a lognormal or a normal model. The authors tested model goodness of fit to their data using Shapiro-Wilk tests, studied factors affecting the variability of time estimates, and examined the impact of coding permutations (ordered combinations) on modeling. Results The Shapiro-Wilk tests indicated that the lognormal model is statistically superior to the normal model for modeling dual-procedure surgeries. Permutations of component codes did not appear to differ significantly with respect to total procedure time and surgical time. To improve individual models for infrequent dual-procedure surgeries, permutations may be reduced and estimates may be based on the longest component procedure and type of anesthesia. Conclusions The authors recommend use of the lognormal model for estimating surgical times for surgeries with two component procedures. Their results help legitimize the use of log transforms to normalize surgical procedure times prior to hypothesis testing using linear statistical models. Multiple-procedure surgeries may be modeled using the longest (statistically most important) component procedure and type of anesthesia.

Estimating Procedure Times for Surgeries by Determining Location Parameters for the Lognormal Model

We present an empirical study of methods for estimating the location parameter of the lognormal distribution. Our results identify the best order statistic to use, and indicate that using the best order statistic instead of the median may lead to less frequent incorrect rejection of the lognormal model, more accurate critical value estimates, and higher goodness-of-fit. Using simulation data, we constructed and compared two models for identifying the best order statistic, one based on conventional nonlinear regression and the other using a data mining/machine learning technique. Better surgical procedure time estimates may lead to improved surgical operations.

Choosing data-mining methods for multiple classification: representational and performance measurement implications for decision support

Data-mining techniques are designed for classification problems in which each observation is a member of one and only one category. We formulate ten data representations that could be used to extend those methods to problems in which observations may be full members of multiple categories. We propose an audit matrix methodology for evaluating the performance of three popular data-mining techniques--linear discriminant analysis, neural networks, and decision tree induction-- using the representations that each technique can accommodate. We then empirically test our approach on an actual surgical data set. Tree induction gives the lowest rate of false positive predictions, and a version of discriminant analysis yields the lowest rate of false negatives for multiple category problems, but neural networks give the best overall results for the largest multiple classification cases. There is substantial room for improvement in overall performance for all techniques.

Using data mining to profile TV viewers

Mining thousands of viewing choices and millions of patterns, advertisers and TV networks identify household characteristics, tastes, and desires to create and deliver custom targeted advertising.

A hybrid data mining/simulation approach for modelling outpatient no-shows in clinic scheduling

This paper considers the outpatient no-show problem faced by a rural free clinic located in the south-eastern United States. Using data mining and simulation techniques, we develop sequencing schemes for patients, in order to optimize a combination of performance measures used at the clinic. We utilize association rule mining (ARM) to build a model for predicting patient no-shows; and then use a set covering optimization method to derive three manageable sets of rules for patient sequencing. Simulation is used to determine the optimal number of patients and to evaluate the models. The ARM technique presented here results in significant improvements over models that do not employ rules, supporting the conjecture that, when dealing with noisy data such as in an outpatient clinic, extracting partial patterns, as is done by ARM, can be of significant value for simulation modelling.