WO2016077059A1

WO2016077059A1 - Automated scheduling to optimize patient flows

Info

Publication number: WO2016077059A1
Application number: PCT/US2015/057219
Authority: WO
Inventors: Sauleh SIDDIQUI; Scott Levin
Original assignee: The Johns Hopkins University
Priority date: 2014-11-10
Filing date: 2015-10-23
Publication date: 2016-05-19

Abstract

Disclosed are techniques for efficient automated scheduling of certified, registered nurse anesthetists (CRNA). The techniques may include: obtaining computer readable historical patient, data, the historical patient data including, for each of a plurality of patients, patient age, type of surgical procedure, time of patient entry to operating room, time of patient exit of operating room, and whether a CRNA was involved; obtaining computer readable CRNA availability data, the CRNA availability data including a number of available CRNA; obtaining computer readable shift data, the shift data including permissible shift start, times, permissible shift lengths, and break length; applying a multi-objective mixed integer programming to input data including the computer readable historical patient data, the computer readable CRNA availability data, and the computer readable shift data to obtain output data; generating a CRNA schedule from the output data; and outputting the CRNA schedule.

Description

AUTOMATED SCHEDULING TO OPTIMIZE PATIENT FLOWS

Related Application

[0001] The present application claims priority to, and the benefit of, U.S. Provisional Patent Application No. 62/077,814, entitled, "Automated Scheduling to Optimize Patient Flows", filed November 10, 2015, which is hereby incorporated by reference in its entirety.

Background

[0002] Staffing hospital operating rooms (OR) requires scheduling certified registered nurse anesthetists (CRNA). Due to uncertainty in patient demand, creating an efficient schedule is not straightforward, and typically involves balancing surgical caseload, staff satisfaction, and costs.

Summary

[0003] According to various embodiment, a method for efficient automated scheduling of certified registered nurse anesthetists (CRNA) is disclosed. The method include obtaining computer readable historical patient data, the historical patient data including, for each of a plurality of patients, patient age, type of surgical procedure, time of patient entry to operating room, time of patient exit of operating room, and whether a CRNA was involved; obtaining computer readable CRNA availability data, the CRNA availability data including a number of available CRNA; obtaining computer readable shift data, the shift data including permissible shift start times, permissible shift lengths, and break length; applying a multi- objective mixed integer programming to input data including the computer readable historical patient data, the computer readable CRNA availability data, and the computer readable shift data to obtain output data; generating a CRNA schedule from the output data; and outputting the CRNA schedule.

[0004] Various optional features of the above embodiments include the following. The historical patient data may further include, for each of the plurality of patients, at least two of: time of patient entry to operating preparation room, time of patient exit of operating preparation room, time of patient entry to recovery room, or time of patient exit of recovery room. The CRNA availability data may further include, for each of a plurality of CRNA, an indication of permissible types of procedures. The shift data may further include at least one of: a maximal number of shifts of a given length per day, a minimum CRNA presence at a specified time, or cost per shift of a specified length. The method may include obtaining computer readable preference data, the preference data including a preferred shift length, where the input data further includes the computer readable preference data. The outputting may include displaying. The method may include obtaining a percentile value, where the obtaining output data further includes applying the multi-objective mixed integer programming to a schedule defined by the percentile value applied to the input data. The method may include staffing CRNA in a healthcare setting according to the CRNA schedule. The obtaining computer readable CRNA availability data may include: providing an input device to a plurality of CRNA; and obtaining, at the input device, the computer readable CRNA availability data from a plurality of CRNA. The method may include electronically sending individual CRNA schedules to mobile devices of each of a plurality of CRNA.

[0005] According to various embodiments, a system for efficient automated scheduling of certified registered nurse anesthetists (CRNA) is disclosed. The system includes at least one hardware electronic processor; and a memory containing instructions for execution by the at least one processor, such that the instructions cause the processor to perform a method for automated scheduling of CRNA, the method including: obtaining computer readable historical patient data, the historical patient data including, for each of a plurality of patients, patient age, type of surgical procedure, time of patient entry to operating room, time of patient exit of operating room, and whether a CRNA was involved; obtaining computer readable CRNA availability data, the CRNA availability data including a number of available CRNA; obtaining computer readable shift data, the shift data including permissible shift start times, permissible shift lengths, and break length; applying a multi-objective mixed integer programming to input data including the computer readable historical patient data, the computer readable CRNA availability data, and the computer readable shift data to obtain output data; generating a CRNA schedule from the output data; and outputting the CRNA schedule.

[0006] Various optional features of the above embodiments include the following. The historical patient data may further include, for each of the plurality of patients, at least two of: time of patient entry to operating preparation room, time of patient exit of operating preparation room, time of patient entry to recovery room, or time of patient exit of recovery room. The CRNA availability data may further include, for each of a plurality of CRNA, an indication of permissible types of procedures. The shift data may further include at least one of: a maximal number of shifts of a given length per day, a minimum CRNA presence at a specified time, or cost per shift of a specified length. The instructions may further cause the processor to perform obtaining computer readable preference data, the preference data including a preferred shift length, where the input data further includes the computer readable preference data. The system may further include an electronic display electronically coupled to the processor, where the instructions further cause the processor to perform the outputting by displaying on the electronic display. The instructions may further cause the processor to perform obtaining a percentile value, where the obtaining output data further includes applying the multi-objective mixed integer programming to a schedule defined by the percentile value applied to the input data. The instructions may further cause the processor to perform providing the CRNA schedule to a plurality of CRNA via email. The system may further include an input device accessible to a plurality of CRNA and configured to obtain the computer readable CRNA availability data from a plurality of CRNA. The system may further include an interface configured to electronically send individual CRNA schedules to mobile devices of each of a plurality of CRNA.

[0007] The foregoing summary is presented merely to introduce some of the aspects of the disclosure, which are described in greater detail below. Accordingly, the present summary is not intended to be limiting.

Brief Description of the Drawings

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings.

[0009] Fig. 1 illustrates of a graph including percentile curves for patient census data acquired during a study conducted by the inventors.

[0010] Fig. 2 illustrates a graph of percentile curves for CRNA staffing.

[0011] Fig. 3 provides two pie charts depicting the cohort for cases that CRNA were involved in by procedure type and OR

[0012] Fig. 4 illustrates a graph depicting hourly scheduling blocks overlaid on to the percentile curves for CRNA staffing of Fig. 2.

[0013] Fig. 5 is a graph showing the proposed schedule and the number of CRNA scheduled to be working at a given time as determined by the mixed-integer multiobjective optimization model.

[0014] Fig. 6 is a graph illustrating the results of implementing a preference by the OR pre- intervention of the study, which was having forty CRNA in the morning.

[0015] Fig. 7 is a flowchart depicting a method according to some embodiments. [0016] Fig. 8 illustrates a schematic view of such a computing or processor system according to some embodiments.

Detailed Description

[0017] The following detailed description refers to the accompanying drawings. Wherever convenient, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several embodiments and features of the present disclosure are described herein, modifications, adaptations, and other implementations are possible, without departing from the spirit and scope of the present disclosure.

I. Introduction

[0018] In general, two-thirds of hospital-based costs, which are rising along with overall healthcare costs at a higher rate than anticipated by recent studies, are attributed to labor. Operating rooms (OR) have certified resident nurse anesthetists (referred to herein as "CRNA", either singular or plural as the context dictates) to assist in numerous procedures. Scheduling CRNA at optimal cost while maximizing patient care is a complex problem, given high levels of uncertainty from patient demand and restrictions on individual staff availability. Inefficiently staffed ORs may result in compromised patient safety, operating room holds (delays) or surgical cancellations, and nurse burn-out. Numerous large-scale studies have demonstrated the general relationship between inadequate nurse staffing levels, decreased quality of care, and increased patient morality. Conversely, an over-staffed postanesthesia care unit (PACU) creates excessive nurse idle time and associated labor costs not viable given economic pressures in healthcare. Because of the high variability of daily surgical caseloads (e.g., some may often swing 50% on the same day of the week) and patients' changing condition, it is not straightforward to develop an optimal staffing schedule for CRNA.

[0019] Through conduction a real-world study, described in detail here, the inventors have developed an improved CRNA staffing schedule for the Johns Hopkins Hospital OR through the use of multiobjective mixed-integer programming. As inputs, the optimization uses information pertaining to duration and type of surgery, CRNA work hours, and scheduling constraints (e.g., lunch breaks, types of shifts, staff preferences, shift start and end times). According to some embodiments, the process minimizes total costs while meeting these constraints, and provides a weekly schedule of CRNA staffing, including details about shift length, type, and number. This method of optimizing CRNA staffing levels is applicable across other health care settings.

[0020] Thus, in general, this disclosure presents a multiobjective optimization technique that takes, among other things, operating room patient flow data as input and creates a CRNA schedule as output.

II. Case Study and Experimental Results

[0021] As a case study, the inventors implemented a technique at the operating rooms of Johns Hopkins Hospital, where a new schedule was adopted with fewer CRNA. As described herein, the inventors conclude that multiobjective optimization tools can provide an efficient way to schedule CRNA and other staff with the help of patient data.

[0022] The data for the inventors' study was collected from Centricity Perioperative Manager (ORMIS) supported by the Johns Hopkins Hospital Anesthesiology department for procedures from July 1 to December 31 during year of the experiment. A total of 83675 procedures were input into this model, of which CRNA were involved in 53,965 cases (64%). Weekends and procedures outside the time period of 7:00 am to 1 1 :00 pm were excluded. Study data included patient demographics such as age, gender, and if they were an inpatient or outpatient, as well as when patients entered and left the OR, when patients entered and left the OR, the type of surgery performed, and if a CRNA was part of the procedure.

[0023] Fig. 1 illustrates of a graph 100 including percentile curves for the patient census data acquired during the inventors' study. In particular, Fig. 1 illustrates median rates, approximately equal to the mean. The x-axis of graph 100 corresponds to averages for each of five work week days, with each hash mark representing four hours time. The >>-axis of graph 100 represents quantity of patients served. Curve 102 represents the 95^th percentile; curve 104 represents the 75^th percentile, and curve 106 represents the median.

[0024] Fig. 2 illustrates a graph 200 of percentile curves for CRNA staffing. Thus, graph 200 of Fig. 2 represents staffing for the patients represented by graph 100 of Fig. 1. Note that the fifth group of curves, representing_. Thursdays, have slightly greater amplitudes than the other groups of curves, representing Teaching Thursdays at Johns Hopkins. Fig. 2 illustrates median rates, approximately equal to the mean. The x-axis of graph 200 corresponds to averages for each of five work week days, with each hash mark representing four hours time. The y-axis of graph 200 represents quantity of CRNA. Curve 202 represents the 95^th percentile; curve 204 represents the 75^th percentile, and curve 206 represents the median. [0025] Fig. 3 provides two pie charts 300, 301 depicting the cohort for cases that CRNA were involved in by procedure type and OR. In pie chart 300, the following abbreviations are used: G.I. corresponds to gastroenterology; OPH corresponds to ophthalmology; OLHN corresponds to otolaryngology head and neck; UROL corresponds to urology ONC corresponds to oncology; NEUR corresponds to neurology; PLAS corresponds to plastic surgery; RAD corresponds to radiology; PULM corresponds to pulmonology; ORTH corresponds to orthopedics; PEDS corresponds to pediatrics; PSY corresponds to psychiatry; and GYN corresponds to gynecology. In chart 301, the terms JHO, REM, WCC, WOR, ZB3, ZB4, and ZB5 correspond to various operating rooms at the facility under study.

[0026] Fig. 4 illustrates a graph 400 depicting hourly scheduling blocks overlaid on to the percentile curves for CRNA staffing of Fig. 2. That is, graph 400 depicts block scheduling times that cover the observed staffing of Fig. 2. In particular, blocks 402 represent staffing coverage for the 95^th percentile of observed CRNA staffing 202 of Fig. 2; blocks 404 represent staffing coverage for the 75^th percentile of observed CRNA staffing 204 of Fig. 2; and blocks 406 represent staffing coverage for the median of observed CRNA staffing 206 of Fig. 2. Fig. 4 is described further below.

[0027] A description of an example procedure that was followed for the analysis follows. First, OR start time was designated as when the patient entered the OR and end time was designated when the patient left the OR. Second, patients with inconsistent data (missing start and end times, start time after end time, no patient or procedure identification number) were removed from the data. This was less than 1% of the data. Third, the procedures which involved CRNA were extracted from the data and percentile curves were generated as shown in Fig. 2. Fourth, scheduling occurs in hourly blocks, so these were overlaid on the percentile curves as shown in Fig. 4. Fifth, a percentile level was selected in conversation with CRNA, surgeons, anesthesiologists, and hospital administrators. For this analysis, the inventors chose the 75th percentile, but the method may work for alternate choices. Sixth, the 75th percentile block schedule from Fig. 4 was put into an optimization model described herein. This model had the objective of minimizing number of hours worked by CRNA with respect to meeting the block schedule constraints. An hour of break (30 minute lunch plus two 15 minute coffee breaks) was added into each shift along with other constraints detailed herein. The model chose between 14 hour, 12 hour, and 10 hour shifts, with allowable start times: 7:00 am, 9:00 am, 1 1 :00 am and allowable end times: 5:00 pm, 7:00 pm, 9:00 pm,l 1 :00 pm. Seventh, the optimization routine returns a number of different options for scheduling along with details about number of shifts and what time these shifts are supposed to start. An example is shown below in Table 1.

Table 1: Sample Week Schedule Given as Optimization Model Output

[0028] As illustrated by Table 1, the mixed-integer multiobjective optimization model thus provides a weekly schedule for CRNA and staff census for each minute of the day.

[0029] Fig. 5 is a graph 500 showing the output schedule 502 of the optimization process and the number of CRNA scheduled to be working at a given time as determined by the mixed-integer multiobjective optimization model. In addition, graph 500 shows the 75^th percentile curve for CRNA staffing 506 overlaid on to the block scheduling times 504 that cover the observed staffing, i.e., curve 204 of Fig. 2 and blocks 404 of Fig. 4, respectively. Proposed schedule 502 shows the effect of having fixed start and end times as well as a total hour-long break in each shift. Fig. 5 also provides insight into the working of the OR. Every morning, procedures start at a given time (typically 8:00 am) and then are consistently at a high number, until early afternoon when a number of CRNA go on break. The procedures pick up again, and peak late afternoon and slowly taper off. The slow tapering at the end shows how end times for procedures typically cannot be accurately predicted, and the number of delays adds up at the end of the day. [0030] The study also included a comparison scenario to illustrate the amount of cost savings possible.

[0031] Fig. 6 is a graph 600 illustrating the results of implementing a preference by the OR pre-intervention of the study, which was having forty CRNA in the morning. Thus, graph 600 shows the 75^th percentile curve for CRNA staffing 608 overlaid on to the block scheduling times 606 that cover the observed staffing, as well as the proposed schedule 502, i.e., respectively, curve 204 of Fig. 2, blocks 404 of Fig. 4, and proposed schedule 502 of Fig. 5. The inventors added this as a constraint in the model, and showed that even under the best case scenario, there is a loss of having a high number of CRNA come in the morning. Most of the uncertainty and need happens in the afternoon, which the proposed schedule showed.

[0032] The Johns Hopkins department of anesthesiology implemented the proposed schedule along with a host of other changes starting the following April. According to their financial analysis, these changes resulted in annual savings of at least $170,000 per year. The inventors obtained CRNA scheduling data from them for April to September. The results indicate a substantial savings in both CRNA time and hospital money.

III. Model Structure and Parameters

[0033] This section describes the optimization process in detail. The disclosed optimization routine may be used as part of the actions of block 708 of method 700. The optimization routine may be performed using a mixed-integer, multiobjective optimization model, for example. In the example implementation described in Section II, above, GAMS 12 was used to perform the optimization routine, although other packages may be used in the alternative.

[0034] Table 2 below illustrates example constraints used in the case study and usable in other embodiments. As shown, Table 2 indicates a discretization of time as implemented each day for scheduling purposes, as well as a example CRNA shift start times and shift lengths. Table 2 also explains a parameter that is used in the equations set forth below.

Table 2: Example Constraints

[0035] Table 3 below explains various variables that may be used in the optimization process. In particular, Table 3 indicates the intended meanings of various variables.

Table 3: Variable Descriptions

[0036] Table 4 below sets forth several parameters that may be used in the optimization process. In particular,

is an integer specifying a number of required CRNA at different hours, and is an integer setting forth the length of breaks per shift. This

later parameter was set at 1 for all cases in the case study. That is, one hour lunch breaks are built into the shifts.

Table 4: Parameter Explanations

[0037] The following objective equation may be implemented as part of the mixed-integer, multiobjective optimization model. In such an implementation, the objective equation may specify the parameter to be optimized.

[0038] The following constraint inequality for each hour of the day may be implemented as part of the mixed-integer, multiobjective optimization model. In such an implementation, the constraint inequality for each hour of the day may specify a constraint on time.

[0039] The following constraint inequality for breaks may be implemented as part of the mixed-integer, multiobjective optimization model. In such an implementation, the constraint inequality for breaks may place constraints on CRNA break times.

[0040] The following inequality limits the number of 14 hour shifts per day to four. It may be implemented as a constraint of the mixed-integer, multiobjective optimization model. This constraint is optional according to some embodiments.

[0041] The following inequality specifies that the schedule is to accommodate at least 40 CRNA starting at 7:00 am. It may be implemented as a constraint of the mixed-integer, multiobjective optimization model. This constraint is optional according to some embodiments.

[0042] In implementing the mixed-integer, multiobjective optimization model, a solution may specify any of a plurality of possible Pareto optimal solutions. That is, the model may output one or more solutions, even if many, if not infinitely many, solutions exist.

[0043] Fig. 7 is a flowchart depicting a method according to some embodiments. The method may be implemented on computer hardware such as that described in detail in Section IV, below.

[0044] At block 702, the method obtains computer readable historical patient data. The method may obtain such data by reading computer readable electronic media, by manual input, by scraping electronic patient and/or hospital electronic records, or by other techniques. In some embodiments, the historical patient data may include, for each of the plurality of patients, one or more of: time of patient entry to operating preparation room, time of patient exit of operating preparation room, time of patient entry to recovery room, or time of patient exit of recovery room

[0045] At block 704, the method obtains computer readable CRNA availability data. The ^" method may obtain such data by manual input, by scraping electronic patient and/or hospital electronic records, or by other techniques. The method may obtain such data by reading computer readable electronic media, by manual input, by scraping patient and/or hospital electronic records, or by other techniques. According to some embodiments, the CRNA availability data may include, for each of a plurality of CRNA, an indication of permissible types of procedures. According to some embodiments, the actions of this block include providing an input device {e.g., a computer or card swipe device) to a plurality of CRNA, and obtaining, at the input device, the computer readable CRNA availability data from a plurality of CRNA. [0046] At block 706, the method obtains computer readable shift data. The method may obtain such data by reading computer readable electronic media, by manual input, by scraping patient and/or hospital electronic records, or by other techniques. According to some embodiments, the shift data may include at least one of: a maximal number of shifts of a given length per day, a minimum CRNA presence at a specified time, or cost per shift of a specified length.

[0047] At block 708, the method applies a multi-objective mixed integer programming technique to the data obtained at blocks 702, 704, and 706. The technique may be configured and applied as described in detail herein. According to some embodiments, the method may include obtaining computer readable preference data that represents a preferred shift length, and the data input to the multi-objective mixed integer programming technique includes the computer readable preference data. According to some embodiments, the method also includes obtaining a percentile value, and the obtaining output data further includes applying the multi-objective mixed integer programming to a schedule defined by the percentile value applied to the input data of any, or a combination, of the data obtained at blocks 702, 704, and 706.

[0048] At block 710, the method generates a CRNA schedule based on the output of block 708. The schedule may be as illustrated by Table 1 , above, for example.

[0049] At block 712, the method outputs the CRNA schedule. The output may be by way of display on a computer monitor, a printout, or data sent to a different electronic process, such as a billing application, for example. As another example, the method may electronically send individual CRNA schedules to mobile devices of each of a plurality of CRNA individuals, e.g., by way of text message or email, for example. This optional feature provides enhances efficiency because it permits near instantaneous communication of the CRNA schedule to the CRNA staff.

[0050] Some embodiments also include staffing CRNA in a healthcare setting according to the CRNA schedule.

IV. Computer Hardware Implementation Examples

[0051] Embodiments may also include one or more systems for implementing one or more embodiments of the method of the present disclosure.

[0052] Fig. 8 illustrates a schematic view of such a computing or processor system 800, according to some embodiments. The system 800 may include one or more processors 802, possibly of varying core (including multi-core) configurations and/or clock frequencies. The one or more processors 802 may be operable to execute instructions, apply logic, etc. It will be appreciated that these functions may be provided by multiple processors or multiple cores on a single chip operating in parallel and/or communicably linked together.

[0053] The processor system 800 may also include a memory system, which may be or include one or more memory devices and/or computer-readable media 804 of varying physical dimensions, accessibility, storage capacities, etc. such as flash drives, hard drives, disks, random access memory, etc., for storing data, such as images, files, and program instructions for execution by the processors 802. In an embodiment, computer-readable media 804 may store instructions that, when executed by the processor 802, are configured to cause the processor system 800 to perform operations. For example, execution of such instructions may cause the processor system 800 to implement one or more portions and/or embodiments of the method(s) described above, e.g., method 700.

[0054] The processor system 800 may also include one or more network interfaces 806. Network interfaces 806 may include any hardware, applications, and/or other software. Accordingly, network interfaces 806 may include Ethernet adapters, wireless transceivers, PCI interfaces, and/or serial network components, for communicating over wired or wireless media using protocols, such as Ethernet, wireless Ethernet, etc.

[0055] As an example, the processor system 800 may be, or communicate with, a mobile device that includes one or more network interfaces for communication of information. For example, a mobile device may include a wireless network interface (e.g., operable via IEEE 802.1 1 , ETSI GSM, BLUETOOTH®, satellite, etc.). As an example, a mobile device may include components such as a main processor, memory, a display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), a SIM slot, audio/video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, a mobile device may be configured as a cell phone, a tablet, etc. As an example, a system may include one or more mobile devices. As an example, system 800 may wirelessly provide individual CRNA scheduling data to individual CRNA mobile devices, e.g., via text message, email, or other expedient.

[0056] The processor system 800 may further include one or more peripheral interfaces 808, for communication with a display screen, projector, keyboards, mice, touchpads, sensors, other types of input and/or output peripherals, and/or the like. In some implementations, the components of processor system 800 need not be enclosed within a single enclosure or even located in close proximity to one another, but in other implementations, the components and/or others may be provided in a single enclosure. As an example, a system may be a distributed environment, for example, a so-called "cloud" environment where various devices, components, etc. interact for purposes of data storage, communications, computing, etc. As an example, a method may be implemented in a distributed environment {e.g., wholly or in part as a cloud-based service).

[0057] As an example, information may be input from a display (e.g., a touchscreen), output to a display, or both. As an example, information may be output to a projector, a laser device, a printer, etc. such that the information may be viewed.

[0058] The memory device 804 may be physically or logically arranged or configured to store data on one or more storage devices 810. The storage device 810 may include one or more file systems or databases in any suitable format. The storage device 810 may also include one or more software programs 812, which may contain interpretable or executable instructions for performing one or more of the disclosed processes, e.g., method 700. When requested by the processor 802, one or more of the software programs 812, or a portion thereof, may be loaded from the storage devices 810 to the memory devices 804 for execution by the processor 802.

[0059] Peripheral interfaces 808, processors 802, network interfaces 806, memory devices 804, and storage devices 810 may be communicatively coupled to each-other, and possibly to other components of system 800, via one or more electronic busses.

[0060] Those skilled in the art will appreciate that the above-described componentry is merely one example of a hardware configuration, as the processor system 800 may include any type of hardware components, including any necessary accompanying firmware or software, for performing the disclosed implementations. The processor system 800 may also be implemented in part or in whole by electronic circuit components or processors, such as application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs).

[0061] The foregoing description of the present disclosure, along with its associated embodiments and examples, has been presented for purposes of illustration only. It is not exhaustive and does not limit the present disclosure to the precise form disclosed. Those skilled in the art will appreciate from the foregoing description that modifications and variations are possible in light of the above teachings or may be acquired from practicing the disclosed embodiments.

[0062] For example, the same techniques described herein with reference to the processor system 800 may be used to execute programs according to instructions received from another program or from another processor system altogether. Similarly, commands may be received, executed, and their output returned entirely within the processing and/or memory of the processor system 800. Accordingly, neither a visual interface command terminal nor any terminal at all is strictly necessary for performing the described embodiments.

[0063] Likewise, the steps described need not be performed in the same sequence discussed or with the same degree of separation. Various steps may be omitted, repeated, combined, or divided, as necessary to achieve the same or similar objectives or enhancements. Accordingly, the present disclosure is not limited to the above-described embodiments, but instead is defined by the appended claims in light of their full scope of equivalents. Further, in the above description and in the below claims, unless specified otherwise, the term "execute" and its variants are to be interpreted as pertaining to any operation of program code or instructions on a device, whether compiled, interpreted, or run using other techniques.

Claims

CLAIMS What is claimed is:

1. A method for efficient automated scheduling of certified registered nurse anesthetists (CRNA), the method comprising:

obtaining computer readable historical patient data, the historical patient data comprising, for each of a plurality of patients, patient age, type of surgical procedure, time of patient entry to operating room, time of patient exit of operating room, and whether a CRNA was involved;

obtaining computer readable CRNA availability data, the CRNA availability data comprising a number of available CRNA;

obtaining computer readable shift data, the shift data comprising permissible shift start times, permissible shift lengths, and break length;

applying a multi-objective mixed integer programming to input data comprising the computer readable historical patient data, the computer readable CRNA availability data, and the computer readable shift data to obtain output data;

generating a CRNA schedule from the output data; and

outputting the CRNA schedule.

2. The method of claim 1, wherein the historical patient data further comprises, for each of the plurality of patients, at least two of: time of patient entry to operating preparation room, time of patient exit of operating preparation room, time of patient entry to recovery room, or time of patient exit of recovery room.

3. The method of claim 1, wherein the CRNA availability data further comprises, for each of a plurality of CRNA, an indication of permissible types of procedures.

4. The method of claim 1, wherein the shift data further comprises at least one of: a maximal number of shifts of a given length per day, a minimum CRNA presence at a specified time, or cost per shift of a specified length.

5. The method of claim 1, further comprising obtaining computer readable preference data, the preference data comprising a preferred shift length, wherein the input data further comprises the computer readable preference data.

6. The method of claim 1 , wherein the outputting comprises displaying.

7. The method of claim 1 , further comprising obtaining a percentile value, wherein the obtaining output data further comprises applying the multi-objective mixed integer programming to a schedule defined by the percentile value applied to the input data.

8. The method of claim 1 , further comprising staffing CRNA in a healthcare setting according to the CRNA schedule.

9. The method of claim 1 , wherein the obtaining computer readable CRNA availability data comprises:

providing an input device to a plurality of CRNA; and

obtaining, at the input device, the computer readable CRNA availability data from a plurality of CRN A.

10. The method of claim 1, further comprising electronically sending individual CRNA schedules to mobile devices of each of a plurality of CRNA.

1 1 . A system for efficient automated scheduling of certified registered nurse anesthetists (CRNA), the system comprising:

at least one hardware electronic processor; and

a memory containing instructions for execution by the at least one processor, such that the instructions cause the processor to perform a method for automated scheduling of CRNA, the method comprising:

obtaining computer readable shift data, the shift data comprising permissible shift start times, permissible shift lengths, and break length; applying a multi -objective mixed integer programming to input data comprising the computer readable historical patient data, the computer readable CRNA availability data, and the computer readable shift data to obtain output data;

generating a CRNA schedule from the output data; and

outputting the CRNA schedule.

12. The system of claim 1 1 , wherein the historical patient data further comprises, for each of the plurality of patients, at least two of: time of patient entry to operating preparation room, time of patient exit of operating preparation room, time of patient entry to recovery room, or time of patient exit of recovery room.

13. The system of claim 1 1, wherein the CRNA availability data further comprises, for each of a plurality of CRNA, an indication of permissible types of procedures.

14. The system of claim 1 1 , wherein the shift data further comprises at least one of: a maxima] number of shifts of a given length per day, a minimum CRNA presence at a specified time, or cost per shift of a specified length.

15. The system of claim 1 1 , wherein the instructions further cause the processor to perform obtaining computer readable preference data, the preference data comprising a preferred shift length, wherein the input data further comprises the computer readable preference data.

16. The system of claim 1 1, further comprising an electronic display electronically coupled to the processor, wherein the instructions further cause the processor to perform the outputting by displaying on the electronic display.

17. The system of claim 1 1, wherein the instructions further cause the processor to perform obtaining a percentile value, wherein the obtaining output data further comprises applying the multi-objective mixed integer programming to a schedule defined by the percentile value applied to the input data.

18. The system of claim 1 1 , wherein the instructions further cause the processor to perform providing the CRNA schedule to a plurality of CRNA via email.

19. The system of claim 1 1 , further comprising an input device accessible to a plurality of CRNA and configured to obtain the computer readable CRNA availability data from a plurality of CRNA.

20. The system of claim 1 1, further comprising an interface configured to electronically send individual CRNA schedules to mobile devices of each of a plurality of CRNA.