Operation and Method for Prediction and Management of the Validity of Subject Reported 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
exact text as granted — not AI-modified1 - 52 . (canceled)
53 . A computer implemented method for improving clinical trial data quality, comprising:
obtaining compliance information from a subject in said clinical trial on a portable electronic device, wherein said compliance information comprises data on timeliness in answering a question or responding to a prompt; and determining automatically on an electronic device, based at least on an application of a decision rule to said compliance information, that an action should be taken, thereby improving clinical trial data quality.
54 . The computer implemented method of claim 53 , wherein said clinical trial is a drug trial involving humans.
55 . The computer implemented method of claim 53 , wherein said portable electronic device is a handheld computer provided with a display and a data input feature or a cell phone.
56 . The computer implemented method of claim 54 , wherein said compliance information further comprises completeness.
57 . The computer implemented method of claim 54 , wherein said action is communicated over a wireless network.
58 . The computer implemented method of claim 53 , further comprising applying said decision rule to said compliance information.
59 . The computer implemented method of claim 53 , wherein said decision rule is a reformatted algorithm.
60 . The computer implemented method of claim 59 , wherein said algorithm is representative of said compliance information.
61 . The computer implemented method of claim 59 , wherein said algorithm is generated by quantitative analysis of said compliance information.
62 . The computer implemented method of claim 53 , wherein said decision rule determines a threshold of compliance or a threshold of noncompliance.
63 . The computer implemented method of claim 53 , wherein said application of said decision rule to said compliance information identifies noncompliance within a spectrum of noncompliance.
64 . The computer implemented method of claim 63 , wherein said noncompliance is minor noncompliance.
65 . The computer implemented method of claim 64 , wherein said action is a corrective feedback.
66 . The computer implemented method of claim 63 , wherein said noncompliance is a significant noncompliance.
67 . The computer implemented method of claim 66 , wherein said action is to drop said subject from said clinical trial.
68 . The computer implemented method of claim 53 , wherein said action comprises corrective feedback, calling said subject, or dropping said subject from said clinical trial.
69 . The computer implemented method of claim 53 , further comprising communicating said action to said subject, a research site, a sponsor or a clinical trial staff, thereby improving clinical trial data quality.
70 . The computer implemented method of claim 69 , wherein said communicating said action comprises displaying said action on an electronic device.
71 . The computer implemented method of claim 70 , wherein said electronic device is a portable electronic device.
72 . A non-transitory computer-readable medium suitable for use in an electronic device, said medium comprising instructions that, when executed by said electronic device, cause said electronic device to perform:
receiving compliance information from a subject in a clinical trial, wherein said compliance information comprises data on timeliness in answering a question or responding to a prompt; and determining automatically, based at least on an application of a decision rule to said compliance information, that an action should be taken, thereby improving clinical trial data quality.
73 . The medium of claim 72 , wherein said clinical trial is a drug trial involving humans.
74 . The medium of claim 72 , wherein said compliance information further comprises completeness.
75 . The medium of claim 72 , further comprising applying said decision rule to said compliance information.
76 . The medium of claim 72 , wherein said decision rule is a reformatted algorithm.
77 . The medium of claim 76 , wherein said algorithm is representative of said compliance information.
78 . The medium of claim 72 , wherein said decision rule determines a threshold of compliance or a threshold of noncompliance.
79 . The medium of claim 72 , wherein said action comprises at least one of corrective feedback, calling said subject, or dropping said subject from said clinical trial.
80 . The medium of claim 72 , wherein said application of said decision rule to said compliance information identifies noncompliance within a spectrum of noncompliance.
81 . The medium of claim 80 , wherein said noncompliance is minor noncompliance.
82 . The medium of claim 81 , wherein said action is a corrective feedback.
83 . The medium of claim 80 , wherein said noncompliance is a significant noncompliance.
84 . The medium of claim 83 , wherein said action is to drop said subject from said clinical trial.
85 . A computer system comprising an electronic device, wherein said electronic device comprises a non-transitory computer-readable medium comprising instructions that, when executed by said computer system, cause said computer system to perform:
receiving compliance information from a subject in a clinical trial, wherein said compliance information comprises data on timeliness in answering a question or responding to a prompt; and determining automatically, based at least on an application of a decision rule to said compliance information, that an action should be taken, thereby improving clinical trial data quality.
86 . The system of claim 85 , wherein said clinical trial is a drug trial involving humans.
87 . The system of claim 85 , wherein said compliance information further comprises completeness.
88 . The system of claim 83 , further comprising applying said decision rule to said compliance information.
89 . The system of claim 85 , wherein said decision rule is a reformatted algorithm.
90 . The system of claim 89 , wherein said algorithm is representative of said compliance information.
91 . The system of claim 89 , wherein said algorithm is generated by quantitative analysis of said compliance information.
92 . The system of claim 85 , wherein said decision rule determines a threshold of compliance or a threshold of noncompliance.
93 . The system of claim 85 , wherein said action comprises at least one of corrective feedback, calling said subject, or dropping said subject from said clinical trial.
94 . The system of claim 85 , wherein said application of said decision rule to said compliance information identifies noncompliance within a spectrum of noncompliance.
95 . The system of claim 94 , wherein said noncompliance is minor noncompliance.
96 . The system of claim 95 , wherein said action is a corrective feedback.
97 . The system of claim 94 , wherein said noncompliance is a significant noncompliance.
98 . The system of claim 97 , wherein said action is to drop said subject from said clinical trial.Join the waitlist — get patent alerts
Track US2018150523A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.