Operation and Method for Prediction and Management of the Validity of Subject Reported Data

• US 20110082827A1
• Filed: 12/10/2010
• Published: 04/07/2011
• Est. Priority Date: 04/02/2001
• Status: Active Grant

• Current Assignee: eResearchTechnology, Inc. (Explorer Holdings, Inc.)
• Original Assignee: Invivodata Incorporated (Explorer Holdings, Inc.)
• Inventors: SHIFFMAN, Saul, Engfer, Douglas R., Paty, Jean
• Granted Patent: US 9,129,215 B2
• Time in Patent Office: Days
• US Class Current: 706/47
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/025 Extracting rules from data

Abstract

A system for developing and implementing empirically derived algorithms to generate decision rules to predict invalidity of subject reported data and fraud with research protocols in surveys allows for the identification of complex patterns of variables that detect or predict subject invalidity of subject reported data and fraud with the research protocol in the survey. The present invention may also be used to monitor invalidity of subject reported data within a research protocol to determine preferred actions to be performed. Optionally, the invention may provide a spectrum of invalidity, from minor invalidity needing only corrective feedback, to significant invalidity requiring subject removal from the survey. The algorithms and decision rules can also be domain-specific, such as detecting invalidity or fraud among subjects in a workplace satisfaction survey, or demographically specific, such as taking into account gender or age. The algorithms and decision rules may be optimized for the specific sample of subjects being studied.

Claims

1-52. -52. (canceled)

53. A computer implemented method for predicting the invalidity of subject reported data, comprising:

analyzing one or more validity markers;

generating at least one predictive algorithm for predicting the invalidity of subject reported data by quantitative analysis of the validity markers; and

translating the at least one predictive algorithm into at least one prediction rule for use with a clinical trial.

54. The method of claim 53, further comprising comparing the one or more validity markers to the at least one prediction rule to determine if action is needed.

55. The method of claim 54, further comprising determining an appropriate action if the step of comparing indicates that action is needed.

56. The method of claim 54, wherein the analyzing comprises employing a portable electronic device capable of displaying information and receiving and storing input from a user.

57. The method of claim 54, further composing creating an evaluabitity database adapted to store data related to the validity of subject reported data.

58. The method of claim 57, wherein the evaluability database is tailored to a condition affecting the subject.

59. The method of claim 53, wherein the analyzing further comprises analyzing historical protocol data and wherein the generating comprises quantitative analysis of the historical protocol data.

60. The method of claim 53, wherein the analyzing comprises analyzing at least one database containing at least one set of data from the group consisting of historical validity markers and historical protocol data.

61. The method of claim 53, wherein the one or more validity markers are historical validity markers, from more than one event.

62. The method of claim 53, wherein the one or more validity markers are from at least one event.

63. A computer implemented method for determining the validity of subject reported data and determining if corrective action is needed, comprising:

analyzing at least one set of data from the group consisting of historical validity markers and historical protocol data;

generating at least one algorithm reflective of the at least one set of data by quantitative analysis of the at least one set of data;

translating the at least one algorithm into at least one decision rule for analyzing information on the validity of subject reported data;

obtaining validity markers for at least one event; and

analyzing the validity markers with the at least one decision rule to determine if corrective action is needed.

64. The method of claim 63, further comprising determining an appropriate corrective action if the step of analyzing indicates that corrective action is needed.

65. The method of claim 63, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

66. The method of claim 63, wherein the generating employs at least one of the group of multiple linear regression, discriminant function analysis, logistic regression, neural networks, classification trees and regression trees.

67. The method of claim 63, wherein the analyzing comprises, analyzing at least one database containing at least one data set selected from the group consisting of historical validity markers and historical protocol data.

68. A computer implemented method for determining the validity of subject reported data, comprising:

analyzing historical validity markers and historical protocol data;

generating a spectrum of invalidity representative of the historical validity markers not compliant with the historical protocol data by quantitative analysis of the historical validity markers and the historical protocol data;

obtaining one or more validity markers for at least one event; and

comparing the spectrum of invalidity to the historical validity markers to determine if corrective action is needed.

69. The method of claim 68, further comprising determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

70. The method of claim 69, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

71. A computer implemented method for detecting subject fraud, comprising:

analyzing historical validity markers and historical protocol data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the historical validity markers and the historical protocol data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule for use with a clinical trial.

72. A computer implemented method of detecting subject fraud, comprising:

analyzing information on the validity of subject reported data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the information on the validity of subject reported data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule for use with a clinical trial.

73. The method of claim 72, further comprising:

comparing the validity markers to the at least one fraud detection rule to determine if action is needed.

74. The method of claim 73, further comprising determining an appropriate action if the step of comparing indicates that action is needed.

75. The method of claim 73, wherein the analyzing comprises the use of a portable electronic device capable of displaying information and receiving and storing input from a user.

76. The method of claim 73, further comprising the step of creating an evaluability database adapted to store data related to subject fraud.

77. The method of claim 76, wherein the evaluability database is tailored to a condition affecting the subject.

78. The method of claim 73, wherein the analyzing employs at Least one database containing at least one data set selected from the group consisting of historical validity markers and historical protocol data.

79. A medium suitable for use in an electronic device, comprising instructions for execution by the electronic device, the instructions comprising:

analyzing at least one data set selected from the of the group consisting of validity markers and protocol data;

generating at least one predictive algorithm for predicting invalid subject reported data by quantitative analysis of the at feast one data set translating the at least one predictive algorithm into at least one prediction rule for use with a clinical trial.

80. The medium of claim 79 wherein said instructions further comprise comparing validity markers to at least one prediction rule to determine if an action is needed.

81. The medium of claim 79, wherein the data set is obtained using a portable electronic device capable of displaying information and receiving and storing input from a user.

82. The medium of claim 79 wherein said instructions further comprise creating an evaluability database adapted to store data related to information on the validity of subject reported data.

83. The medium of claim 79, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

84. The medium of claim 79, wherein the validity markers are from at least one event.

85. The medium of claim 79, wherein the protocol data is historical protocol data from more than one clinical trial.

86. The medium of claim 79, wherein the protocol data is from at least one clinical trial.

87. A medium suitable for use in an electronic device, comprising instructions for execution by the electronic device, the instructions comprising:

analyzing at least one data set selected from the group consisting of validity markers and historical protocol data;

generating at least one algorithm reflective of the at least one data set by quantitative analysis of the at least one data set;

translating the at least one algorithm into at least one decision rule for analyzing information on the validity of subject response data;

obtaining validity markers for at least one event; and

analyzing the validity markers with the at least one decision rule to determine if corrective action is needed.

88. The medium of claim 87 wherein the instructions further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

89. The medium of claim 87, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

90. The medium, of claim 87, wherein the generating employs at least one of the group of multiple linear regression, discriminant function analysis, logistic regression, neural networks, classification trees and regression trees.

91. A medium suitable for use in an electronic device, comprising instructions for execution by the electronic device, the instructions comprising:

analyzing historical validity markers and historical protocol data;

generating a spectrum of invalidity representative of the historical validity markers not compliant with the historical protocol data by quantitative analysis of the historical validity markers and the historical protocol data;

obtaining validity markers for at least one event; and

comparing the spectrum of invalidity to the validity markers to determine if corrective action is needed.

92. The medium of claim 91 wherein the instructions further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

93. The medium of claim 92, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

94. A medium suitable for use in an electronic device, comprising instructions for execution by the electronic device, the instructions comprising:

analyzing validity markers and protocol data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the validity markers and the protocol data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule.

95. The medium of claim 94 wherein the instructions, further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

96. The medium of claim 94, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

97. The medium of claim 94, wherein the generating employs at least one of the group of multiple linear regression, discriminant function analysis, logistic regression, neural networks, classification trees and regression trees.

98. The medium of claim 94, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

99. The medium of claim 94, wherein the validity markers are from at least one event.

100. The medium of claim 94, wherein the protocol data is historical protocol data from more than one clinical trial.

101. The method of claim 94, wherein the protocol data is from at least one clinical trial.

102. A medium suitable for use in an electronic device, comprising instructions for execution by the electronic device, the instructions comprising:

analyzing information on the validity of subject reported data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the information on the validity of subject reported data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule for use.

103. The medium of claim 102, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

104. The medium of claim 102, wherein the validity markers are from at least one event.

105. The medium of claim 102, wherein the electronic device is a portable electronic device.

106. A computer system suitable comprising an electronic device, wherein the electronic device comprises instructions for execution by the electronic device, the instructions comprising:

analyzing at least one data set selected from the of the group consisting of validity markers and protocol data;

generating at least one predictive algorithm for predicting invalid subject reported data by quantitative analysis of the at feast one data set translating the at least one predictive algorithm into at least one prediction rule for use with a clinical trial.

107. The computer system of claim 106 wherein said instructions further comprise comparing validity markers to at least one prediction rule to determine if an action is needed.

108. The computer system of claim 106, wherein the data set is obtained using a portable electronic device capable of displaying information and receiving and storing input from a user.

109. The computer system of claim 106 wherein said instructions further comprise creating an evaluability database adapted to store data related to information on the validity of subject reported data.

110. The computer system of claim 106, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

111. The computer system of claim 106, wherein the validity markers are from at least one event.

112. The computer system of claim 106, wherein the protocol data is historical protocol data from more than one clinical trial.

113. The computer system of claim 106, wherein the protocol data is from at least one clinical trial.

114. A computer system comprising an electronic device, wherein the electronic device comprises instructions for execution by the electronic device, the instructions comprising:

analyzing at least one data set selected from the group consisting of validity markers and historical protocol data;

generating at least one algorithm reflective of the at least one data set by quantitative analysis of the at least one data set;

translating the at least one algorithm into at least one decision rule for analyzing information on the validity of subject response data;

obtaining validity markers for at least one event; and

analyzing the validity markers with the at least one decision rule to determine if corrective action is needed.

115. The computer system of claim 114 wherein the instructions further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

116. The computer system of claim 114, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

117. The computer system, of claim 114, wherein the generating employs at least one of the group of multiple linear regression, discriminant function analysis, logistic regression, neural networks, classification trees and regression trees.

118. A computer system suitable comprising an electronic device, wherein the electronic device comprises instructions for execution by the electronic device, the instructions comprising:

analyzing historical validity markers and historical protocol data;

generating a spectrum of invalidity representative of the historical validity markers not compliant with the historical protocol data by quantitative analysis of the historical validity markers and the historical protocol data;

obtaining validity markers for at least one event; and

comparing the spectrum of invalidity to the validity markers to determine if corrective action is needed.

119. The computer system of claim 118 wherein the instructions further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

120. The computer system of claim 119, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

121. A computer system suitable for use in an electronic device, wherein the electronic device comprises instructions for execution by the electronic device, the instructions comprising:

analyzing validity markers and protocol data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the validity markers and the protocol data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule.

122. The computer system of claim 121 wherein the instructions, further comprise determining an appropriate corrective action if the step of comparing indicates that corrective action is needed.

123. The computer system of claim 121, wherein the obtaining comprises using a portable electronic device capable of displaying information and receiving and storing input from a user.

124. The computer system of claim 121, wherein the generating employs at least one of the group of multiple linear regression, discriminant function analysis, logistic regression, neural networks, classification trees and regression trees.

125. The computer system of claim 121, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

126. The computer system of claim 121, wherein the validity markers are from at least one event.

127. The computer system of claim 121, wherein the protocol data is historical protocol data from more than one clinical trial.

128. The method of claim 121, wherein the protocol data is from at least one clinical trial.

129. A computer system suitable comprising an electronic device, wherein the electronic device comprises instructions for execution by the electronic device, the instructions comprising:

analyzing information on the validity of subject reported data;

generating at least one fraud detection algorithm for detecting subject fraud by quantitative analysis of the information on the validity of subject reported data; and

translating the at least one fraud detection algorithm into at least one fraud detection rule for use.

130. The computer system of claim 129, wherein the validity markers are historical information on the validity of subject reported data, from more than one event.

131. The computer system of claim 129, wherein the validity markers are from at least one event.

132. The computer system of claim 129, wherein the electronic device is a portable electronic device.