EP3844775A1 - Selbstlernender eingabefilter für medizingeräte - Google Patents
Selbstlernender eingabefilter für medizingeräteInfo
- Publication number
- EP3844775A1 EP3844775A1 EP19761856.4A EP19761856A EP3844775A1 EP 3844775 A1 EP3844775 A1 EP 3844775A1 EP 19761856 A EP19761856 A EP 19761856A EP 3844775 A1 EP3844775 A1 EP 3844775A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- probability
- density
- input
- database
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analogue processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/008—Reliability or availability analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2365—Ensuring data consistency and integrity
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
Definitions
- the present invention relates to a method for monitoring the reliability of an input in a medical device according to claim 1 and to the field of medical devices, in particular to a device for
- the alarm fatigue is a desensitization especially of the clinical
- Reasons for irrelevant alarms are, for example, the main preparation or measures on the patient, the alarm limits not being adapted to the patient or the clinical situation, the use of sensors with insufficient quality and service life, inadequate threshold logic, "overmonitoring", proactive monitoring and / or faulty alarm transmission.
- At least one value is entered into the medical device in step S1.
- step S9 the at least one value with data from the database 1 (DERS)
- step S9 If the result in step S9 is positive (yes), the process proceeds to step S12 and it is output that the value is “OK”. If the result in step S9 is negative (no), the process moves to step S11 and an error message is output Such an error message is followed by step S14, in which the user is asked whether the entered value from step S1 should be overwritten. In step S13, the user decides not to enter again, that is to say against
- step S15 Overwriting the previous value, the algorithm is stopped. If the user makes a new entry in step S13, the previous value which has been assessed as incorrect is overwritten and then output as “OK”. Thereafter, the algorithm is ended / stopped until a new entry (step S15).
- the object of the present invention is to avoid the aforementioned disadvantages and problems and to provide a method and a device for reducing the false alarms, as a result of which the safety of medical devices is increased.
- This object is achieved by a method for monitoring the reliability of an input in a medical device with the features of claim 1 and by a device for monitoring the reliability of an input in a medical device with the features of claim 9.
- the present invention relates to a method for monitoring the
- a first step at least one value is entered into the medical device. After the input, a probability of occurrence density of the at least one value is calculated based on an input history. The input history provides historical data which are stored in a first database. Then, in a further step, an error probability of the input from an a priori error probability density and the previously calculated one
- Error probability density is stored in the first database and is in front of the Calculation of the probability of errors loaded from the database.
- An a priori error probability density is a discrete or absolutely continuous density function with the associated probability distribution, that is, the a priori probability distribution.
- Probability of error of the input this is output in the input treatment for further use, such as for dynamic and independent adjustment of alarm limits when checking the correctness of the at least one entered value.
- the workload of the clinic staff and the stress of the patients are reduced.
- inputs are evaluated and processed with the help of a self-learning - using artificial intelligence - flexible and adaptable system.
- the present invention thus offers a method which, depending on values and experiences, alarm limits dynamically and independently adapts to situations.
- a probability distribution based on a recursive Bayesian filter it is preferred to use a probability distribution based on a recursive Bayesian filter to calculate the probability of error.
- all the inputs are stored in the first database in the medical device.
- the entered numerical values are with the related / correlated inputs, such as alarms, alarm acknowledgments,
- a (input) filter like a Bayesian filter calculates how
- the a priori probability distribution from these values Every new entry is offset against this probability.
- the input is evaluated by the algorithm and the input is declared / confirmed or an alarm is issued if the input has been declared / invalid.
- the Bayesian filter or the Bayesian estimation method differs from other estimation methods of classic statistics in that they include the
- a probability distribution over the resulting parameter space must be specified a priori. This makes it possible to include preliminary information, such as, in this case, already known results of various entries up to the time of the new entry.
- preliminary information such as, in this case, already known results of various entries up to the time of the new entry.
- values / data are used to move from the a priori distribution to the a posteriori distribution, on which the estimates are based.
- Occurrence probability density is calculated, from which the filter described above calculates a valid value of the input.
- the filter works as a recursive Bayes filter type.
- the a posteriori filter density can be determined recursively using Bayesian estimation theory. Based on the Bayes theorem, the a posteriori filter density can first be expanded and then factored into a recursive one
- the variables X k , y k describe a value at time k, the variables Xk, Y k a sequence of all values up to time k and the variable p a probability.
- the denominator of the equation is a normalization constant, so that the integral results in 1 over the distribution function. So only those in the counter of
- Prediction or a priori distribution density P ⁇ - IL ) and the probability of occurrence distribution density p (y k l x k ) are determined.
- the a priori distribution density is calculated from the historical input data.
- the filter adapts to the input behavior of its user and is flexible in relation to its changing behavior.
- the filter can learn permanently and will continue to filter out new types of incorrect entries independently.
- Probability of occurrence to a predetermined probability distribution use in particular a Gaussian distribution based on the data of a second database, provided there is no sufficient input history or input history. This is particularly advantageous at the beginning when the first database does not yet have any historical data.
- the second database contains data from the previous dose error reduction system (DERS for short) according to FIG. 3.
- training is carried out with test data until a certain threshold value, which preferably corresponds to a work profile of the user, is reached when the probability of error is calculated.
- the filter is trained with the test data using this "Train-Until-No-Error principle" (short: TUNE) until it reaches a certain threshold when evaluating the entries and thus corresponds to the work profile of the user. But even during use, the filter at TUNE can be trained with this incorrectly rated message in the event of an error.
- TUNE Train-Until-No-Error principle
- the invention further relates to a device for monitoring the reliability of an input in a medical device, with a means for entering at least one value into the medical device, a means for calculating a probability of occurrence density of the at least one value based on an input history, a means for calculating an error probability of the input from a database stored in a first and from the first
- Database loaded a priori error probability density and the calculated Probability of occurrence density and a means for outputting the probability of error for further use in the input treatment.
- the device described above is designed to carry out all of the steps described above.
- 1 shows the sequence of the method for monitoring the reliability of an input in the form of a flow chart.
- the user enters at least one value in the step S1
- step S2 The occurrence probability density of the at least one value is then calculated in step S3 on the basis of historical data.
- the historical data are stored in the first database 3.
- step S4 the a-priori error probability density is loaded from the first database 3. This loaded a-priori error probability density and the probability of occurrence density calculated in step S3 become in one step S5
- Calculation device 2 calculates the error probability of the input.
- Step S6 outputs the error probability calculated in step S5 for further use in the input treatment.
- the a-priori error probability density is recalculated and loaded into the first database 3 in step S8. In other words, a new data point is added to the first database 3.
- a step S1 at least one value is entered into the medical device by a user, which is stored in a step S2 in the first database 3 and processed in the calculation device 2, which carries out the algorithm, in accordance with the flowchart from FIG.
- the validity value of the input is determined in step S9 as to whether the input value is assessed as positive / correct (yes) or negative / incorrect (no).
- step S12 it is output that the value is “OK” and the algorithm is ended.
- step S11 which outputs an error.
- step S13 the user must finally
- step S14 decides whether he wants to make a new entry so as to overwrite the value in a step S14 or whether he does not want to make any new entries.
- the process then goes to step S12 and again an “OK” is output and the algorithm is ended.
- the process proceeds to step S15, which ends / stops the algorithm.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Psychiatry (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Power Engineering (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102018121349.2A DE102018121349A1 (de) | 2018-08-31 | 2018-08-31 | Selbstlernender Eingabefilter für Medizingeräte |
| PCT/EP2019/073138 WO2020043848A1 (de) | 2018-08-31 | 2019-08-29 | Selbstlernender eingabefilter für medizingeräte |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP3844775A1 true EP3844775A1 (de) | 2021-07-07 |
Family
ID=67809500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP19761856.4A Pending EP3844775A1 (de) | 2018-08-31 | 2019-08-29 | Selbstlernender eingabefilter für medizingeräte |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US12575793B2 (de) |
| EP (1) | EP3844775A1 (de) |
| JP (1) | JP7474748B2 (de) |
| CN (1) | CN112771623B (de) |
| DE (1) | DE102018121349A1 (de) |
| WO (1) | WO2020043848A1 (de) |
Family Cites Families (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5903454A (en) * | 1991-12-23 | 1999-05-11 | Hoffberg; Linda Irene | Human-factored interface corporating adaptive pattern recognition based controller apparatus |
| JP2000163404A (ja) * | 1998-11-25 | 2000-06-16 | Nec Corp | データ発生確率推定装置 |
| US8036735B2 (en) * | 2007-08-08 | 2011-10-11 | Cardiac Pacemakers, Inc. | System for evaluating performance of an implantable medical device |
| US7979363B1 (en) | 2008-03-06 | 2011-07-12 | Thomas Cecil Minter | Priori probability and probability of error estimation for adaptive bayes pattern recognition |
| RU2425394C2 (ru) * | 2009-03-10 | 2011-07-27 | Федеральное государственное образовательное учреждение высшего профессионального образования "Военный авиационный инженерный университет" (г. Воронеж) Министерства обороны Российской Федерации | Способ обнаружения искаженных импульсных сигналов |
| CN101718634B (zh) | 2009-11-20 | 2012-05-09 | 西安交通大学 | 基于多元概率模型的设备状态综合动态报警方法 |
| US20150142457A1 (en) * | 2013-11-20 | 2015-05-21 | Toshiba Medical Systems Corporation | Apparatus for, and method of, data validation |
| JP6167948B2 (ja) | 2014-03-14 | 2017-07-26 | 富士ゼロックス株式会社 | 障害予測システム、障害予測装置およびプログラム |
| WO2015164879A1 (en) * | 2014-04-25 | 2015-10-29 | The Regents Of The University Of California | Recognizing predictive patterns in the sequence of superalarm triggers for predicting patient deterioration |
| EP2960665B1 (de) | 2014-06-27 | 2017-05-24 | Secure-IC SAS | Vorrichtung und Verfahren zur Kalibrierung eines digitalen Sensors |
| CN104965996B (zh) * | 2015-07-23 | 2017-09-29 | 济南工程职业技术学院 | 一种基于贝叶斯公式的年长者生活状态监测推理方法 |
| JP6139615B2 (ja) * | 2015-09-04 | 2017-05-31 | パラマウントベッド株式会社 | 異常通報システム、異常通報方法及びプログラム |
| KR101748122B1 (ko) * | 2015-09-09 | 2017-06-16 | 삼성에스디에스 주식회사 | 경보의 오류율 계산 방법 |
| CN106407082B (zh) * | 2016-09-30 | 2019-06-14 | 国家电网公司 | 一种信息系统告警方法和装置 |
| CN107137093B (zh) * | 2017-04-20 | 2019-06-07 | 浙江大学 | 一种包含异常血糖概率报警器的连续血糖监测设备 |
| CN107246873A (zh) | 2017-07-03 | 2017-10-13 | 哈尔滨工程大学 | 一种基于改进的粒子滤波的移动机器人同时定位与地图构建的方法 |
-
2018
- 2018-08-31 DE DE102018121349.2A patent/DE102018121349A1/de active Pending
-
2019
- 2019-08-29 EP EP19761856.4A patent/EP3844775A1/de active Pending
- 2019-08-29 JP JP2021510923A patent/JP7474748B2/ja active Active
- 2019-08-29 CN CN201980061999.1A patent/CN112771623B/zh active Active
- 2019-08-29 WO PCT/EP2019/073138 patent/WO2020043848A1/de not_active Ceased
- 2019-08-29 US US17/271,652 patent/US12575793B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112771623A (zh) | 2021-05-07 |
| DE102018121349A1 (de) | 2020-03-05 |
| JP7474748B2 (ja) | 2024-04-25 |
| WO2020043848A1 (de) | 2020-03-05 |
| US20210338169A1 (en) | 2021-11-04 |
| US12575793B2 (en) | 2026-03-17 |
| JP2021535505A (ja) | 2021-12-16 |
| CN112771623B (zh) | 2025-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE69209688T2 (de) | Blutpumpensystem mit Rückflusswarnung | |
| DE19940624C1 (de) | Sicherheitsvorrichtung für eine Blutbehandlungsvorrichtung und Verfahren zur Erhöhung der Sicherheit einer Blutbehandlungsvorrichtung | |
| DE69735178T2 (de) | System zum Einstellen des Schwellwertpegels eines Gebers bei einem frequenzadaptiven Herzschrittmacher | |
| DE102014102730A1 (de) | Vorrichtung und Verfahren zur Erkennung eines Fehlers im extrakorporalen Blutkreislauf | |
| WO2008037410A1 (de) | Vorrichtung und verfahren zur vorgabe einer dialysierflüssigkeitsrate oder blutflussrate für eine extrakorporale blutbehandlung | |
| EP2121417B1 (de) | Verfahren und vorrichtung zur ermittlung eines lenkwinkeloffsets | |
| EP0402508A1 (de) | Verfahren und Einrichtung zum Detektieren einer Folge von anormalen Ereignissen in einem elektrischen Signal, insbesondere dem Depolarisationssignal eines Herzens | |
| DE102014003542A1 (de) | Verfahren und Vorrichtung zur Erzeugung eines Alarms während einer maschinellen Patientenbeatmung | |
| WO2018091492A1 (de) | Konzertierte alarmbehandlung fuer einen verbund von dialysegeraeten | |
| EP3258284B1 (de) | Betrieb einer magnetresonanzvorrichtung unter berücksichtigung von implantat-trägern | |
| DE102019202514A1 (de) | Verfahren zur digitalen Subtraktionsangiographie, Röntgeneinrichtung, Computerprogramm und elektronisch lesbarer Datenträger | |
| DE102019118703A1 (de) | System und Verfahren zum kontinuierlichen Verifizieren der Bauelementzustandsintegrität | |
| EP3844775A1 (de) | Selbstlernender eingabefilter für medizingeräte | |
| DE102014019520B4 (de) | Verfahren zur Erzeugung eines Alarms bei der Überwachung eines Patienten und Vorrichtung hierfür | |
| DE3511697C2 (de) | ||
| DE102018122115A1 (de) | Verfahren zur Umgebungserfassung eines Fahrzeugs | |
| DE10114383B4 (de) | Blutdruckvorrichtung und Gerät zur extrakorporalen Blutbehandlung mit einer solchen Blutüberwachungsvorrichtung | |
| DE112012006972T5 (de) | Halbautomatisches Spülsystem für das Spülen einer Wasserleitung und entsprechendes Verfahren | |
| DE102020124395A1 (de) | Verfahren zum Identifizieren des Typs eines medizinischen Filters, und Vorrichtungen | |
| EP3206732A1 (de) | Vorrichtung zur ereignisabhängigen grenzwertüberwachung einer dialysemaschine | |
| DE102022108410A1 (de) | Vorhersage und abschwächung von speicherlecks in einem computersystem | |
| DE102022205047A1 (de) | Verfahren zum Erkennen eines Konfliktes | |
| DE112020006567T5 (de) | Diagnosemetrik für das kumulative Vorhandensein von Sogbedingungen | |
| DE102020128948A1 (de) | Vorrichtung, Verfahren und Computerprogramm zum Bereitstellen eines Vorschlags für zumindest eine angepasste Alarmbedingung für einen Nutzer in einem medizinischen System | |
| EP3129081A1 (de) | Verfahren zur abschätzung der behandlungsdauer einer peritonealdialyse-behandlung |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 17P | Request for examination filed |
Effective date: 20210302 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20240702 |