Method and system for classification of an occurrence of a medical complication

Abstract

The invention relates to a computer-implemented method for classification of an occurrence of a complication caused by preeclampsia within a predetermined time period, comprising applying (S3) a second machine learning algorithm (A2) to the second dataset (DS2) of medical parameters of the patient to classify the occurrence of the complication caused by preeclampsia within the predetermined time period, and outputting (S4) a class representing the occurrence of the complication caused by preeclampsia within the predetermined time period. The invention further relates to a system (1) for classification of an occurrence of a complication caused by preeclampsia within a predetermined time period.

Description

[0001] Description

[0002] Title

[0003] Method and system for classi fication of an occurrence of a medical complication

[0004] The present invention relates to a computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period .

[0005] The present invention further relates to a system for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period .

[0006] Moreover, the invention relates to a computer program with program code to execute the inventive method, as well as a computer-readable medium with program code of a computer program to execute at least parts of the inventive method when the computer program is executed on a computer .

[0007] State of the Art

[0008] Preeclampsia is a multisystem disease in pregnancy . With an incidence of 3-5% , it is one of the leading causes of maternal and fetal morbidity and mortality . Preeclampsia is defined as an increase in blood pressure during pregnancy in combination with the new onset of maternal organ symptoms such as proteinuria, liver dys function, neurological symptoms , and others . The prediction of preeclampsia is currently conducted according to valid national and international guidelines through regular measurement of maternal blood pressure and determination of proteinuria.

[0009] However, it is a clinical dilemma that these diagnostic criteria are too imprecise to predict severe courses or complications of preeclampsia. Due to the discrepancy between nonspecific symptoms and life-threatening complications, accurate prediction is crucial to prevent these .

[0010] An improvement in the prediction of preeclampsia was achieved with the establishment of angiogenic and antiangiogenic factors. It has been shown that the circulating serum concentration of the antiangiogenic factor soluble fms-like tyrosine kinase 1 (sFlt-1) as well as that of the angiogenic factor placental growth factor (P1GF) in the serum of women is altered who will develop preeclampsia.

[0011] In Zeisler H, Llurba E, Chantraine F, Vatish M, Staff AC, Sennstrdm M, et al., "Predictive Value of the sFlt-l:PlGF Ratio in Women with Suspected Preeclampsia, " N Engl J Med. 2016;374 (l) : 13-22, it was demonstrated that using the sFlt-1 / PlGF ratio, a disease exclusion can be achieved for women presenting with clinical symptoms. Inclusion was limited due to a moderate positive predictive value.

[0012] Thus, high prediction accuracy is desirable to reduce morbidity and mortality as well as to avoid unnecessary hospitali zations , thereby alleviating the burden on the healthcare system .

[0013] It is therefore the obj ect of the invention to provide an improved method that enables more accurate determination of an occurrence of a complication caused by preeclampsia during pregnancy .

[0014] Disclosure of the Invention

[0015] The obj ect is achieved according to the invention by a computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period with the features of claim 1 .

[0016] The obj ect is further achieved according to the invention by a system for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period with the features of claim 11 . The obj ect is also achieved according to the invention by a computer program with program code to execute the inventive method, with the features of claim 14 .

[0017] Additionally, the obj ect is achieved by a computer- readable medium with program code of a computer program to execute at least parts of the inventive method when the computer program is executed on a computer, with the features of claim 15 .

[0018] The invention relates to a computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period .

[0019] The method comprises providing a pre-recorded first dataset of medical parameters of a patient .

[0020] Furthermore , the method comprises at least partially trans forming the first dataset of medical parameters of the patient using a first algorithm, in particular a multivariate data analysis method, into a reduced second dataset of medical parameters of the patient .

[0021] The method further comprises applying a second machine learning algorithm to the second dataset of medical parameters of the patient to classi fy the occurrence of the complication caused by preeclampsia within the predetermined time period, and outputting a class representing the occurrence of the complication caused by preeclampsia within the predetermined time period .

[0022] The invention further relates to a system for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period .

[0023] The system comprises at least one input device for providing a pre-recorded first dataset of medical parameters of a patient .

[0024] Moreover, the system comprises a first computing device configured to trans form the first dataset of medical parameters of the patient using a first algorithm, in particular a multivariate data analysis method, into a reduced second dataset of medical parameters of the patient at least partially .

[0025] The system further comprises a second computing device configured to apply a second machine learning algorithm to the second dataset of medical parameters of the patient to classi fy the occurrence of the complication caused by preeclampsia within the predetermined time period, and an output device configured to output a class representing the occurrence of the complication caused by preeclampsia within a predetermined time period .

[0026] The invention also relates to a computer program with program code to execute a method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period when the computer program is executed on a computer, as well as a computer- readable medium with program code of a computer program to execute at least parts of the inventive method when the computer program is executed on a computer .

[0027] Machine learning algorithms are based on the use of statistical methods to train a data processing system to perform a speci fic task without being explicitly programmed for it initially . The goal of machine learning is to construct algorithms that can learn from data and make predictions . These algorithms create mathematical models that can, for example , classi fy data .

[0028] The first algorithm, in particular the multivariate data analysis method, performs the trans formation of the first dataset of medical parameters of the patient into the reduced second dataset of medical parameters of the patient by feature selection and feature processing . Relevant features are selected from the dataset and trans formed into a format that can be used by the second machine learning algorithm . This can comprise feature extraction, feature scaling, and feature normali zation .

[0029] An idea of the present invention is to use a machine learning algorithm in the field of risk prediction for pregnant women with high risk for preeclampsia .

[0030] In case of a prediction of a possible complication, it may be recommended, for example , to terminate the pregnancy . This can eliminate the risk of the complication . The prediction can be performed throughout the course of pregnancy, preferably after the 24th week of pregnancy, or whenever a high-risk patient presents hersel f .

[0031] The machine learning algorithm is particularly applied to a reduced dataset of medical parameters of the patient . Overall , the machine learning model functions by learning from data, identi fying patterns and relationships between variables , and making predictions or decisions based on them . The accuracy of the model depends on the quality and quantity of the data, the algorithm used, and the hyperparameter settings .

[0032] Feature selection and engineering are critical steps in creating machine learning models , as they aim to select the most important features from the dataset and convert them into a format that the machine learning algorithm can use . During feature selection, a subset of relevant features is selected to be used in the model . The goal of feature selection is to reduce the dimensionality of the data and remove all redundant or irrelevant features that could negatively impact the model ' s performance .

[0033] The classi fication of the occurrence of the complication caused by preeclampsia within the predetermined time period can, for example , be provided by a binary classi fication distinguishing only between a prediction of the occurrence of a complication and a non-occurrence of a complication .

[0034] Alternatively, the classi fication can, for example , output a percentage probability of the occurrence of a complication, expressed as a numerical value between 0 and 1 .

[0035] Additionally, a platform is created that integrates a physician-side decision support tool with a patient-side home monitoring application .

[0036] Further embodiments of the present invention are the subj ect of the additional claims and the following description with reference to the figures .

[0037] According to a preferred embodiment of the invention, it is provided that the first dataset comprises a first set of medical parameters of the patient recorded through a user interface of a medical practitioner, comprising protein levels in urine , systolic blood pressure , diastolic blood pressure , an sFlt- 1 value , a P1GF value , a classi fication of thrombocytopenia, and a classi fication of elevated liver enzymes .

[0038] Part of the features comprised by the first dataset can thus advantageously be provided by the medical practitioner through the user interface .

[0039] According to another preferred embodiment of the invention, it is provided that the first dataset comprises a second set of medical parameters of the patient recorded through a patient app and / or the user interface of the medical practitioner, comprising the patient ' s age , weight before the current pregnancy, height , a classi fication of hypertension before the current pregnancy, a classi fication of new onset hypertension during the current pregnancy, and gestational age , particularly in days .

[0040] Another part of the features comprised by the first dataset can thus advantageously be provided by the patient through the patient app .

[0041] According to another preferred embodiment of the invention, it is provided that the second machine learning algorithm performs a further classi fication of the occurrence of the complication caused by preeclampsia within the predetermined time period based on the reprovision of medical parameters of the patient recorded by the patient app .

[0042] Thus , the risk of the occurrence of the complication caused by preeclampsia can advantageously be continuously re-determined based on updated medical parameters provided by the patient app .

[0043] According to another preferred embodiment of the invention, it is provided that the trans formed second dataset comprises the patient ' s age , body mass index before pregnancy, multiples of the median of sFlt- 1 , multiples of the median of P1GF, multiples of the median of the sFIt- l / PIGF ratio , a deviation from the mean systolic blood pressure , and a deviation from the mean diastolic blood pressure .

[0044] The trans formed second dataset thus advantageously contains relevant features and a format that can be used by the second machine learning algorithm .

[0045] According to another preferred embodiment of the invention, it is provided that the second machine learning algorithm and / or a third machine learning algorithm applied to the second dataset of medical parameters of the patient outputs a classi fication of a delivery caused by preeclampsia within a predetermined time period . This prediction advantageously provides an improved basis for decision-making regarding any necessary medical interventions .

[0046] According to another preferred embodiment of the invention, it is provided that the second machine learning algorithm and / or the third machine learning algorithm applied to the second dataset of medical parameters of the patient outputs the classi fication of a delivery caused by preeclampsia within the next 14 days for patients before the 34th week of pregnancy and the classi fication of a delivery caused by preeclampsia within the next 7 days for patients after the 34th week of pregnancy .

[0047] Based on this determination, the physician can make a better decision about whether the patient is at high risk and needs to be treated in a hospital , whether the patient should be delivered immediately or very soon, or whether, despite symptoms , the patient can be sent home with a higher level of certainty than previously possible .

[0048] According to another preferred embodiment of the invention, it is provided that the second machine learning algorithm and / or a fourth machine learning algorithm applied to the second dataset of medical parameters of the patient outputs a classi fication of an occurrence of preeclampsia .

[0049] The prediction of the occurrence of preeclampsia advantageously provides the physician with additional information required for treatment . For example , the occurrence of preeclampsia and simultaneously the nonoccurrence of a complication caused by preeclampsia can be predicted . This enables improved decision-making for a possible treatment of the patient .

[0050] According to another preferred embodiment of the invention, a computer-implemented method is provided, further comprising the provision of the classi fication generated by the second machine learning algorithm, the third machine learning algorithm, and / or the fourth machine learning algorithm .

[0051] The provided classi fication result can then, for example , be transmitted to the user interface of the medical practitioner and / or the patient app .

[0052] According to another preferred embodiment of the invention, it is provided that the classi fication of the occurrence of the complication caused by preeclampsia within the predetermined time period comprises a first class , which represents a prediction of the occurrence of the complication caused by preeclampsia within the predetermined time period, and a second class of the classi fication represents a prediction of the nonoccurrence of the complication caused by preeclampsia within the predetermined time period .

[0053] The binary classi fication thus allows a concrete statement regarding the occurrence or non-occurrence of the complication caused by preeclampsia within the predetermined time period .

[0054] According to another preferred embodiment of the invention, it is provided that the at least one input device comprises a user interface of a medical practitioner configured to provide a first set of medical parameters of the patient recorded by the medical practitioner, comprising protein levels in urine , systolic blood pressure , diastolic blood pressure , an sFlt- 1 value , a P1GF value , a classi fication of thrombocytopenia, and a classi fication of elevated liver enzymes .

[0055] Part of the features comprised by the first dataset can thus advantageously be provided by the medical practitioner through the user interface .

[0056] According to another preferred embodiment of the invention, it is provided that the at least one input device comprises a patient app configured to provide a second set of medical parameters recorded by the patient , comprising the patient ' s age , weight before the current pregnancy, height , a classi fication of hypertension before the current pregnancy, a classi fication of new onset hypertension during the current pregnancy, and gestational age , particularly in days .

[0057] Another part of the features comprised by the first dataset can thus advantageously be provided by the patient through the patient app .

[0058] The features described herein of the computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period are also applicable to the system for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period and vice versa .

[0059] Brief Description of the Drawings For a better understanding of the present invention and its advantages , reference is now made to the following description in conj unction with the accompanying drawings .

[0060] The invention will now be explained in more detail by way of exemplary embodiments indicated in the schematic illustrations of the drawings .

[0061] In the drawings :

[0062] Fig . l shows a flowchart of a computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period; and

[0063] Fig . 2 shows a schematic representation of a system for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period .

[0064] Unless otherwise indicated, identical reference numerals designate identical elements in the drawings .

[0065] Detailed Description of the Embodiments

[0066] The computer-implemented method for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period shown in Fig . 1 comprises providing S I a pre-recorded first dataset DS 1 of medical parameters of a patient . Furthermore , the method comprises at least partially trans forming S2 the first dataset DS 1 of medical parameters of the patient using a first algorithm Al , in particular a multivariate data analysis method, into a reduced second dataset DS2 of medical parameters of the patient .

[0067] The method further comprises applying S3 a second machine learning algorithm A2 to the second dataset DS2 of medical parameters of the patient to classi fy the occurrence of the complication caused by preeclampsia within the predetermined time period .

[0068] Moreover, the method comprises outputting S4 a class KI , K2 representing the occurrence of the complication caused by preeclampsia within a predetermined time period .

[0069] The first dataset DS 1 comprises a first set of medical parameters of the patient recorded via a user interface 10 of a medical practitioner, comprising protein levels in urine , systolic blood pressure , diastolic blood pressure , an sFlt- 1 value , a P1GF value , a classi fication of thrombocytopenia, and a classi fication of elevated liver enzymes .

[0070] The first dataset DS 1 further comprises a second set of medical parameters of the patient recorded via a patient app 12 and / or the user interface 10 of the medical practitioner, comprising the patient ' s age , weight before the current pregnancy, height , a classi fication of hypertension before the current pregnancy, a classi fication of new onset hypertension during the current pregnancy, and gestational age , in particular in days .

[0071] The second machine learning algorithm A2 performs a further classi fication of the occurrence of the complication caused by preeclampsia within the predetermined time period based on the re-provision of medical parameters of the patient recorded via the patient app 12 .

[0072] The trans formed second dataset DS2 comprises the patient ' s age , body mass index before pregnancy, multiples of the median of sFlt- 1 , multiples of the median of P1GF, multiples of the median of the sFlt- 1 / P1GF ratio , a deviation from the mean systolic blood pressure , and a deviation from the mean diastolic blood pressure .

[0073] The second machine learning algorithm A2 and / or a third machine learning algorithm A3 applied to the second dataset DS2 of medical parameters of the patient further outputs a classi fication of a delivery caused by preeclampsia within a predetermined time period . Furthermore , the second machine learning algorithm A2 and / or the third machine learning algorithm A3 applied to the second dataset DS2 of medical parameters of the patient outputs the classi fication of a delivery caused by preeclampsia within the next 14 days for patients before the 34th week of pregnancy and the classi fication of a delivery caused by preeclampsia within the next 7 days for patients after the 34th week of pregnancy . The second machine learning algorithm A2 and / or a fourth machine learning algorithm A4 applied to the second dataset DS2 of medical parameters of the patient further outputs a classi fication of an occurrence of preeclampsia .

[0074] Furthermore , the method comprises providing the classi fication generated by the second machine learning algorithm A2 , the third machine learning algorithm A3 , and / or the fourth machine learning algorithm A4 .

[0075] The classi fication of the occurrence of the complication caused by preeclampsia within the predetermined time period comprises a first class KI , which represents a prediction of the occurrence of the complication caused by preeclampsia within the predetermined time period .

[0076] Furthermore , the classi fication comprises a second class K2 , which represents a prediction of the non-occurrence of the complication caused by preeclampsia within the predetermined time period .

[0077] Alternatively, the classi fication may, for example , output a percentage probability of the occurrence of a complication, expressed as a numerical value between 0 and 1 .

[0078] Fig . 2 shows a schematic representation of a system 1 for classi fication of an occurrence of a complication caused by preeclampsia within a predetermined time period . The system 1 comprises at least one input device 14 for providing a pre-recorded first dataset DS 1 of medical parameters of a patient .

[0079] Furthermore , the system 1 comprises a first computing device 16 , which is configured to at least partially trans form the first dataset of medical parameters of the patient using a first algorithm Al , in particular a multivariate data analysis method, into a reduced second dataset DS2 of medical parameters of the patient .

[0080] The system 1 further comprises a second computing device 18 , which is configured to apply a second machine learning algorithm A2 to the second dataset DS2 of medical parameters of the patient to classi fy the occurrence of the complication caused by preeclampsia within the predetermined time period .

[0081] In addition, the system 1 comprises an output device 20 , which is configured to output a class representing the occurrence of the complication caused by preeclampsia within a predetermined time period .

[0082] The at least one input device 14 comprises a user interface 10 of a medical practitioner, which is configured to provide a first set of medical parameters of the patient recorded by the medical practitioner, comprising protein levels in urine , systolic blood pressure , diastolic blood pressure , an sFlt- 1 value , a P1GF value , a classi fication of thrombocytopenia, and a classi fication of elevated liver enzymes . Furthermore , the at least one input device 14 comprises a patient app 12 , which is configured to provide a second set of medical parameters recorded by the patient , comprising the patient ' s age , weight before the current pregnancy, height , a classi fication of hypertension before the current pregnancy, a classi fication of new onset hypertension during the current pregnancy, and gestational age , particularly in days .

[0083] The user interface 10 of the medical practitioner and the patient app 12 are configured to communicate with a backend app 22 . The backend app 22 is in turn connected to a model-serving app 24 , wherein the provided medical parameters are transmitted from the backend app 22 to the model-serving app 24 .

[0084] The classi fication generated by the corresponding machine learning model is then transmitted from the model-serving app 24 back to the backend app 22 , which the user interface 10 of the medical practitioner and / or the patient app 12 can access .

[0085] The patient app 12 and / or the user interface 10 of the medical practitioner can be provided, for example , as a desktop app and / or smartphone app .

[0086] Although speci fic embodiments have been illustrated and described herein, it is understood by those skilled in the art that numerous alternative and / or equivalent implementations exist . It should be noted that the exemplary embodiment or exemplary embodiments are merely examples and are not intended to limit the scope , applicability, or configuration in any way .

[0087] Rather, the aforementioned summary and detailed description provide those skilled in the art with a convenient guide for implementing at least one exemplary embodiment , with the understanding that various changes in function and arrangement of elements may be made without departing from the scope of the appended claims and their legal equivalents .

[0088] In general , this application is intended to cover modi fications , adj ustments , or variations of the embodiments presented herein . For example , the order of the method steps may be altered . The method may also be performed at least partially sequentially or in parallel .

[0089] List of reference signs

[0090] 1 System

[0091] 10 User interface of a medical practitioner

[0092] 12 Patient app

[0093] 14 Input device

[0094] 16 First computing device

[0095] 18 Second computing device

[0096] 20 Output device

[0097] 22 Backend app

[0098] 24 Model-serving app

[0099] Al First algorithm

[0100] A2 Second machine learning algorithm

[0101] A3 Third machine learning algorithm

[0102] A4 Fourth machine learning algorithm

[0103] DS 1 First dataset

[0104] DS2 Second dataset

[0105] KI First class

[0106] K2 Second class

[0107] S 1-S4 Method steps

Claims

Claims1. Computer-implemented method for classification of an occurrence of a complication caused by preeclampsia within a predetermined time period, comprising : providing (SI) a pre-recorded first dataset (DS1) of medical parameters of a patient; at least partially transforming (S2) the first dataset (DS1) of medical parameters of the patient using a first algorithm (Al) , in particular a multivariate data analysis method, into a reduced second dataset (DS2) of medical parameters of the patient ; applying (S3) a second machine learning algorithm (A2) to the second dataset (DS2) of medical parameters of the patient to classify the occurrence of the complication caused by preeclampsia within the predetermined time period; and outputting (S4) a class (KI, K2 ) representing the occurrence of the complication caused by preeclampsia within the predetermined time period.

2. Computer-implemented method according to claim 1, wherein the first dataset (DS1) comprises a first set of medical parameters of the patient recorded by a user interface (10) of a medical practitioner, comprising protein levels in urine, systolic blood pressure, diastolic blood pressure, an sFlt-1 value, a P1GF value, a classification ofthrombocytopenia, and a classification of elevated liver enzymes.

3. Computer-implemented method according to claim 2, wherein the first dataset (DS1) comprises a second set of medical parameters of the patient recorded by a patient app (12) and / or the user interface (10) of the medical practitioner, comprising the patient's age, weight before the current pregnancy, height, a classification of hypertension before the current pregnancy, a classification of new onset hypertension during the current pregnancy, and gestational age, in particular in days.

4. Computer-implemented method according to claim 3, wherein the second machine learning algorithm (A2) performs a further classification of the occurrence of the complication caused by preeclampsia within the predetermined time period based on the reprovision of medical parameters of the patient recorded by the patient app (12) .

5. Computer-implemented method according to any of the preceding claims, wherein the transformed second dataset (DS2) comprises the patient's age, body mass index before pregnancy, multiples of the median of sFlt-1, multiples of the median of P1GF, multiples of the median of the ratio of sFlt-1 and P1GF, a deviation from the mean systolic blood pressure, and a deviation from the mean diastolic blood pressure.

6. Computer-implemented method according to any of the preceding claims, wherein the second machine learning algorithm (A2) and / or a third machine learning algorithm (A3) applied to the second dataset (DS2) of medical parameters of the patient outputs a classification of a delivery caused by preeclampsia within a predetermined time period.

7. Computer-implemented method according to claim 6, wherein the second machine learning algorithm (A2) and / or the third machine learning algorithm (A3) applied to the second dataset (DS2) of medical parameters of the patient outputs the classification of a delivery caused by preeclampsia within the next 14 days for patients before the 34th week of pregnancy and the classification of a delivery caused by preeclampsia within the next 7 days for patients after the 34th week of pregnancy.

8. Computer-implemented method according to any of the preceding claims, wherein the second machine learning algorithm (A2) and / or a fourth machine learning algorithm (A4) applied to the second dataset (DS2) of medical parameters of the patient outputs a classification of an occurrence of preeclampsia .

9. Computer-implemented method according to claim 8, further comprising providing the classification generated by the second machine learning algorithm (A2) , the third machine learning algorithm (A3) , and / or the fourth machine learning algorithm (A4) .

10. Computer-implemented method according to any of the preceding claims, wherein the classification of the occurrence of the complication caused by preeclampsia within the predetermined time period comprises a first class (KI) representing a prediction of the occurrence of the complication caused by preeclampsia within the predetermined time period, and wherein a second class (K2) of the classification represents a prediction of the nonoccurrence of the complication caused by preeclampsia within the predetermined time period.

11. System (1) for classification of an occurrence of a complication caused by preeclampsia within a predetermined time period, comprising: at least one input device (14) for providing a prerecorded first dataset (DS1) of medical parameters of a patient; a first computing device (16) configured to transform the first dataset of medical parameters of the patient using a first algorithm (Al) , in particular a multivariate data analysis method, into a reduced second dataset (DS2) of medical parameters of the patient at least partially; a second computing device (18) configured to apply a second machine learning algorithm (A2) to the second dataset (DS2) of medical parameters of the patient to classify the occurrence of the complication caused by preeclampsia within the predetermined time period; andan output device (20) configured to output a class (KI, K2 ) representing the occurrence of the complication caused by preeclampsia within the predetermined time period.

12. System according to claim 11, wherein the at least one input device (14) comprises a user interface (10) of a medical practitioner configured to provide a first set of medical parameters of the patient recorded by the medical practitioner, comprising protein levels in urine, systolic blood pressure, diastolic blood pressure, an sFlt-1 value, a P1GF value, a classification of thrombocytopenia, and a classification of elevated liver enzymes.

13. System according to claim 11 or 12, wherein the at least one input device (14) comprises a patient app (12) configured to provide a second set of medical parameters recorded by the patient, comprising the patient's age, weight before the current pregnancy, height, a classification of hypertension before the current pregnancy, a classification of new onset hypertension during the current pregnancy, and gestational age, in particular in days.

14. Computer program with program code to execute at least parts of a method according to any of claims 1 to 10 when the computer program is executed on a computer .

15. Computer-readable medium with program code of a computer program to execute at least parts of amethod according to any of claims 1 to 10 when the computer program is executed on a computer .

Images