System and method for assessing physician performance using robust multivariate techniques of statistical analysis

• US 5,924,073 A
• Filed: 11/14/1995
• Issued: 07/13/1999
• Est. Priority Date: 11/14/1995
• Status: Expired due to Fees

• Current Assignee: Beacon Patient Physician Association, LLC, Maillefer Instruments S.A.
• Original Assignee: Beacon Patient Physician Association, LLC
• Inventors: Tyuluman, Samuel A., Ammann, Larry P.
• Primary Examiner(s): Cosimano, Edward R.
• Application Number:
  US08/557,496
• Time in Patent Office: 1,337 Days
• Field of Search: 395/202, 395/203, 395/204, 395/207, 395/211, 705/2, 705/3, 705/4, 705/7, 705/11, 364/400, 600/300, 707/1, 707/104
• US Class Current: 705/2
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A system (10) is provided for assessing physician performance using robust multivariate techniques of statistical analysis. System (10) includes a database (14) operable to store data relating to at least one patient-physician contact. An evaluator (18) is coupled to the database (14). The evaluator (18) is operable to evaluate the data stored in the database (14) using robust multivariate techniques of statistical analysis in order to identify outliers in the data and establish a dynamic standard of care.

Claims

1. A method for assessing data associated with physician performance using robust multivariate techniques of statistical analysis comprising:

collecting data relating to a patient physician contact;

storing the data in a database;

generating a plurality of data units from the patient-physician contact, each data unit comprising information relating to a single diagnosis and the characteristics of the patient;

identifying all data units in which a diagnosis for an ailment was given;

categorizing by ailment the data units in which a diagnosis was given;

associating the data units in which a correct diagnosis was not given with one of the data units in which a correct diagnosis was given, thereby categorizing all data units by ailment; and

,

analyzing all data units relating to a particular ailment using robust multivariate techniques in order to establish a probable transition sequence comprising a plurality of diagnoses which may be given before diagnosing the ailment, the probable transition sequence defining the standard of care for the treatment of that ailment.

2. A method for assessing the ability of a physician to efficiently diagnose an ailment, comprising the steps of:

generating a plurality of transition probabilities;

generating a probable transition sequence from the transition probabilities;

generating at least one data unit from a patient- physician contact, the data unit comprising information relating to a single diagnosis and the characteristics of the patient;

from the data units generated, reconstructing an actual transition sequence of diagnoses given by the physician before diagnosing the ailment;

determining whether the actual transition sequence is the same as the probable transition sequence;

informing a physician that he is performing in accordance with the established standard of care if the actual transition sequence is the same as the probable transition sequence;

analyzing the actual transition sequence using multivariate techniques to determine whether the actual transition sequence is more efficient than the probable transition sequence;

setting the probable transition sequence to the actual transition sequence to establish a higher standard of care, if the actual transition sequence is more efficient; and

informing the physician that he is not performing in accordance with the reasonable standard of care, if the actual transition sequence is less efficient.

3. The method of claim 2, wherein the step of generating a probable transition sequence comprises the step of generating a plurality of diagnoses which may be given before diagnosing the ailment.