Log in
E-mail
Password
Remember
Forgot password ?
Become a member for free
Sign up
Sign up
Settings
Settings
Dynamic quotes 
OFFON

MarketScreener Homepage  >  Equities  >  Nyse  >  International Business Machines Corporation    IBM

INTERNATIONAL BUSINESS MACHINES CORPORAT

(IBM)
  Report  
SummaryQuotesChartsNewsRatingsCalendarCompanyFinancialsConsensusRevisions 
News SummaryMost relevantAll newsOfficial PublicationsSector newsAnalyst Recommendations

Patent Application Titled “Evaluating Drug-Adverse Event Causality Based On An Integration Of Heterogeneous Drug Safety Causality Models” Published Online (USPTO 20190228864): International Business Machines Corporation

share with twitter share with LinkedIn share with facebook
share via e-mail
0
08/14/2019 | 05:52pm EDT

2019 AUG 14 (NewsRx) -- By a News Reporter-Staff News Editor at Disease Prevention Daily -- According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Dey, Sanjoy (White Plains, NY); Fokoue-Nkoutche, Achille B. (White Plains, NY); Shen, Katherine (New York, NY); Zhang, Ping (White Plains, NY), filed on January 24, 2018, was made available online on July 25, 2019.

The assignee for this patent application is International Business Machines Corporation (Armonk, New York, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “The present application relates generally to an improved data processing apparatus and method and more specifically to mechanisms for evaluating drug-adverse event causality based on an integration of heterogenous drug safety causality models.

“Adverse drug reactions, or ADRs, are injuries caused to a patient because of the patient taking a medication. An adverse event (AE), or adverse drug event (ADE), refers to any injury occurring at the time the patient is taking a drug, whether or not the drug itself is identified as the cause of the injury. Thus, an ADR is a special type of AE in which a causative relationship can be shown between the drug and the adverse reaction.

“ADRs may occur following a single dose of the medication (drug) or due to a prolonged administration of a drug, and may even be caused by the interaction of a combination of two or more drugs that the patient may be taking. This is different from a ‘side effect’ in that a ‘side effect’ may comprise beneficial effects whereas ADRs are universally negative. The study of ADRs is the concern of the field known as pharmacovigilance.

“Currently, the evaluation of a case, i.e. a combination of a patient’s electronic medical records from one or more electronic medical record source computing systems, for identifying adverse drug reactions, i.e. the causality of an adverse reaction with a particular drug being taken, is a highly manual process in which a human subject matter expert (SME) reviews the case and comes to a decision as to whether there is a causal relationship between a drug and an adverse reaction. However, this decision requires an evaluation of a large number of criteria and, being a manual process, is both time consuming and error prone.”

In addition to obtaining background information on this patent application, NewsRx editors also obtained the inventors’ summary information for this patent application: “This Summary is provided to introduce a selection of concepts in a simplified form that are further described herein in the Detailed Description. This Summary is not intended to identify key factors or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

“In one illustrative embodiment, a method is provided, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions that are executed by the at least one processor to cause the at least one processor to be configured to implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE). The method comprises processing, by the plurality of heterogenous causality models, drug information for the drug to generate a plurality of risk predictions for a drug and AE pair. The risk predictions include at least one of a risk score or a risk label indicating a probability of the AE occurring with use of the drug. The method further comprises providing, by the plurality of heterogenous causality models, the risk predictions, associated with the drug and AE pair, to a metaclassifier and generating, by the metaclassifier, a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models. In addition, the method comprises outputting, by the metaclassifier, the single causality score value in association with information identifying the drug and AE pair.

“In other illustrative embodiments, a computer program product comprising a computer useable or readable medium having a computer readable program is provided. The computer readable program, when executed on a computing device, causes the computing device to perform various ones of, and combinations of, the operations outlined above with regard to the method illustrative embodiment.

“In yet another illustrative embodiment, a system/apparatus is provided. The system/apparatus may comprise one or more processors and a memory coupled to the one or more processors. The memory may comprise instructions which, when executed by the one or more processors, cause the one or more processors to perform various ones of, and combinations of, the operations outlined above with regard to the method illustrative embodiment.

“These and other features and advantages of the present invention will be described in, or will become apparent to those of ordinary skill in the art in view of, the following detailed description of the example embodiments of the present invention.”

The claims supplied by the inventors are:

“1. A method, in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions that are executed by the at least one processor to cause the at least one processor to be configured to implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE), the method comprising: processing, by the plurality of heterogenous causality models, drug information for the drug to generate a plurality of risk predictions for a drug and AE pair, wherein the risk predictions include at least one of a risk score or a risk label indicating a probability of the AE occurring with use of the drug; providing, by the plurality of heterogenous causality models, the risk predictions, associated with the drug and AE pair, to a metaclassifier; generating, by the metaclassifier, a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models; and outputting, by the metaclassifier, the single causality score value in association with information identifying the drug and AE pair.

“2. The method of claim 1, wherein outputting the single score comprises outputting detailed causal features via feature selection technology and statistics tests.

“3. The method of claim 1, wherein generating the single causality score value comprises: weighting, by the metaclassifier, each of the risk predictions from the plurality of heterogenous causality models; and aggregating, by the metaclassifier, the weighted risk predictions to generate the single causality score value, wherein the metaclassifier applies different weight values to different risk predictions from different causality models in the plurality of heterogeneous causality models.

“4. The method of claim 1, wherein the plurality of heterogeneous causality models comprise at least one of a chemical structure properties risk prediction model, a drug-drug interaction properties risk prediction model, a protein structure properties risk prediction model, a drug-food interaction risk prediction model, a drug-disease interaction risk prediction model, a temporal cues risk prediction model, or a dechallenge/rechallenge characteristics risk prediction model.

“5. The method of claim 1, further comprising: comparing, by the metaclassifier, the single causality score value to at least one threshold indicating a minimum causality score value required to identify a valid causality link between the drug and the adverse event; and outputting, by the metaclassifier, an output indicating whether or not there is a valid causality link between the drug and the adverse event based on results of the comparison.

“6. The method of claim 1, further comprising: analyzing a patient electronic medical record (EMR) to identify a listing of drugs being taken by the patient, wherein the drug in the drug and AE pairing is a drug selected from the listing of drugs, and wherein the AE in the drug and AE pairing is one of a plurality of possible AEs for which the patient is being evaluated.

“7. The method of claim 1, further comprising: analyzing a patient electronic medical record (EMR) to identify a listing of AEs associated with the patient, wherein the AE in the drug and AE pairing is an AE selected from the listing of AEs, and wherein the drug in the drug and AE pairing is one of a plurality of potential drugs that may cause the AE as identified from at least one drug data source.

“8. The method of claim 1, wherein the method is performed for each of a plurality of drugs and for each of a plurality of AEs, and wherein each combination of a drug in the plurality of drugs with an AE in the plurality of AEs provides a pairing of the drug with the AE that is evaluated using the method.

“9. The method of claim 1, wherein outputting, by the metaclassifier, the single causality score value comprises outputting the single causality score value to a cognitive system to perform a cognitive operation based on the single causality score, and wherein the cognitive operation comprises at least one of providing decision support for diagnosing a medical condition of a patient, wherein the medical condition is associated with the AE in the drug and AE pair, or providing decision support for providing a treatment recommendation that comprises the drug in the drug and AE pair.

“10. The method of claim 1, wherein outputting, by the metaclassifier, the single causality score value comprises transmitting a notification message to a computing system associated with a provider of the drug in the drug and AE pair, indicating a probability that the drug causes the AE, in response to the single causality score value meeting or exceeding a predetermined threshold value.

“11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a data processing system, causes the data processing system to implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE), and further causes the data processing system to: process, by the plurality of heterogenous causality models, drug information for the drug to generate a plurality of risk predictions for a drug and AE pair, wherein the risk predictions include at least one of a risk score or a risk label indicating a probability of the AE occurring with use of the drug; provide, by the plurality of heterogenous causality models, the risk predictions, associated with the drug and AE pair, to a metaclassifier; generate, by the metaclassifier, a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models; and output, by the metaclassifier, the single causality score value in association with information identifying the drug and AE pair.

“12. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to output the single score at least by outputting detailed causal features via feature selection technology and statistics tests.

“13. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to generate the single causality score value at least by: weighting, by the metaclassifier, each of the risk predictions from the plurality of heterogenous causality models; and aggregating, by the metaclassifier, the weighted risk predictions to generate the single causality score value, wherein the metaclassifier applies different weight values to different risk predictions from different causality models in the plurality of heterogeneous causality models.

“14. The computer program product of claim 11, wherein the plurality of heterogeneous causality models comprise at least one of a chemical structure properties risk prediction model, a drug-drug interaction properties risk prediction model, a protein structure properties risk prediction model, a drug-food interaction risk prediction model, a drug-disease interaction risk prediction model, a temporal cues risk prediction model, or a dechallenge/rechallenge characteristics risk prediction model.

“15. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to: compare, by the metaclassifier, the single causality score value to at least one threshold indicating a minimum causality score value required to identify a valid causality link between the drug and the adverse event; and output, by the metaclassifier, an output indicating whether or not there is a valid causality link between the drug and the adverse event based on results of the comparison.

“16. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to: analyze a patient electronic medical record (EMR) to identify a listing of drugs being taken by the patient, wherein the drug in the drug and AE pairing is a drug selected from the listing of drugs, and wherein the AE in the drug and AE pairing is one of a plurality of possible AEs for which the patient is being evaluated.

“17. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to: analyze a patient electronic medical record (EMR) to identify a listing of AEs associated with the patient, wherein the AE in the drug and AE pairing is an AE selected from the listing of AEs, and wherein the drug in the drug and AE pairing is one of a plurality of potential drugs that may cause the AE as identified from at least one drug data source.

“18. The computer program product of claim 11, wherein the operation of the data processing system is performed for each of a plurality of drugs and for each of a plurality of AEs, and wherein each combination of a drug in the plurality of drugs with an AE in the plurality of AEs provides a pairing of the drug with the AE that is evaluated by the operation of the data processing system.

“19. The computer program product of claim 11, wherein the computer readable program further causes the data processing system to output, by the metaclassifier, the single causality score value at least by outputting the single causality score value to a cognitive system to perform a cognitive operation based on the single causality score, and wherein the cognitive operation comprises at least one of providing decision support for diagnosing a medical condition of a patient, wherein the medical condition is associated with the AE in the drug and AE pair, or providing decision support for providing a treatment recommendation that comprises the drug in the drug and AE pair.

“20. A data processing system comprising: at least one processor; and at least one memory coupled to the at least one processor, wherein the at least one memory comprises instructions which, when executed by the at least one processor, cause the at least one processor to implement a plurality of heterogeneous causality models and a metaclassifier for predicting a likelihood of causality between a drug and an adverse event (AE), and further cause the at least one processor to: process, by the plurality of heterogenous causality models, drug information for the drug to generate a plurality of risk predictions for a drug and AE pair, wherein the risk predictions include at least one of a risk score or a risk label indicating a probability of the AE occurring with use of the drug; provide, by the plurality of heterogenous causality models, the risk predictions, associated with the drug and AE pair, to a metaclassifier; generate, by the metaclassifier, a single causality score value indicative of a probability of causality between the drug and the AE, of the drug and AE pair, based on an aggregation of the risk predictions from the plurality of heterogenous causality models; and output, by the metaclassifier, the single causality score value in association with information identifying the drug and AE pair.”

For more information, see this patent application: Dey, Sanjoy; Fokoue-Nkoutche, Achille B.; Shen, Katherine; Zhang, Ping. Evaluating Drug-Adverse Event Causality Based On An Integration Of Heterogeneous Drug Safety Causality Models. Filed January 24, 2018 and posted July 25, 2019. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220190228864%22.PGNR.&OS=DN/20190228864&RS=DN/20190228864

(Our reports deliver fact-based news of research and discoveries from around the world.)

Copyright © 2019 NewsRx LLC, Disease Prevention Daily, source Health Newsletters

share with twitter share with LinkedIn share with facebook
share via e-mail
0
Latest news on INTERNATIONAL BUSINESS MAC
09:59aINTERNATIONAL BUSINESS MACHINES : IHL Group Names IBM Order Management as a Lead..
PR
08/16INTERNATIONAL BUSINESS MACHINES : IBM looking for more opportunities for transfo..
AQ
08/152022 Business Analytics & Enterprise Software Market Growth, Forecasts and Ke..
AQ
08/14INTERNATIONAL BUSINESS MACHINES : IBM looking for more opportunities for transfo..
AQ
08/14Stocks: Dividends in Spotlight as Bond Yields Drop -- WSJ
DJ
08/12INTERNATIONAL BUSINESS MACHINES : IBM files patent for blockchain web browser
AQ
08/12INTERNATIONAL BUSINESS MACHINES : Frost and Sullivan-Automated Software Testing ..
AQ
08/08INTERNATIONAL BUSINESS MACHINES : ISM Canada Appoints Hasnain Versi as New Presi..
AQ
08/08INTERNATIONAL BUSINESS MACHINES CORP : Ex-dividend day for
FA
08/07NEWS HIGHLIGHTS : Top Company News of the Day
DJ
More news
Financials (USD)
Sales 2019 77 842 M
EBIT 2019 12 712 M
Net income 2019 10 433 M
Debt 2019 39 695 M
Yield 2019 4,75%
P/E ratio 2019 11,7x
P/E ratio 2020 10,9x
EV / Sales2019 2,05x
EV / Sales2020 1,89x
Capitalization 120 B
Chart INTERNATIONAL BUSINESS MACHINES CORPORATION
Duration : Period :
International Business Machines Corporation Technical Analysis Chart | MarketScreener
Full-screen chart
Technical analysis trends INTERNATIONAL BUSINESS MAC
Short TermMid-TermLong Term
TrendsBearishNeutralBullish
Income Statement Evolution
Consensus
Sell
Buy
Mean consensus HOLD
Number of Analysts 23
Average target price 155,47  $
Last Close Price 135,04  $
Spread / Highest target 29,6%
Spread / Average Target 15,1%
Spread / Lowest Target -11,1%
EPS Revisions
Managers
NameTitle
Virginia M. Rometty Chairman, President & Chief Executive Officer
James J. Kavanaugh Chief Financial Officer & Senior Vice President
John E. Kelly Senior VP-Cognitive Solutions & Research
Martin Jetter SVP-Global Technology Services
Sidney Taurel Independent Director
Sector and Competitors
1st jan.Capitalization (M$)
INTERNATIONAL BUSINESS MACHINES CORPORATION18.80%119 629
ACCENTURE38.42%124 357
TATA CONSULTANCY SERVICES14.37%113 467
AUTOMATIC DATA PROCESSING28.86%73 319
VMWARE, INC.5.14%59 000
INFOSYS LTD17.54%46 111