SE2150124A1 - Method and computing apparatus for healthcare quality assessment - Google Patents

Abstract

A method and a computing apparatus (110) for evaluating care quality and/or assessing patient safety. The computing apparatus (110) obtains an episode of care (EOC) for treating a medical condition of one or more patients, referred to as “a patient”. The EOC comprises a plurality of diagnostic events related to the treatment of the medical condition. The computing apparatus (110) collects, from at least one healthcare institution, information associated with said diagnostic events for the patient. The computing apparatus (110) obtains quality test results for at least two of the plurality of diagnostic events, referred to as “two diagnostic events”. Said two diagnostic events in the episode of care are associated with two standardized quality tests, respectively. Said two standardized tests are provided and monitored by a control organ. The computing apparatus (110) generates, for the EOC, at least one score based on the collected information and the quality test results. The computing apparatus (110) provides information indicative of said at least one score for use as evaluation and/or decision support for the treatment of the medical condition. A corresponding computer program and computer program carrier are also disclosed.

Description

METHOD AND COMPUTING APPARATUSFOR HEALTHCARE QUALITY ASSESS|\/IENT TECHNICAL FIELD Embodiments herein relate to healthcare quality assessment and the like. lnparticular, a method and a computing apparatus for evaluating care quality and/orassessing patient safety are disclosed. A corresponding computer program and a computer program carrier are also disclosed.

BACKGROUND Test results from hospital laboratories as well as studies in radiology, pathologyand clinical physiology form a central part of the investigation, diagnostics and follow-upof treatment results for various diseases. The test results, obtained from e.g. analysis ofa blood sample from an individual patient, of diagnostic examinations form the basis forseveral clinical decisions that, often under time pressure, must be taken for the individualpatient. lf the patient test results of the diagnostic analyses are incorrect, it hasconsequences for the patient in terms of delays, incorrect diagnosis and/or treatment. Anincorrect result also leads to an increase in the economic cost, in addition to sufferingcaused to the patient.

A problem may hence be how to evaluate quality of the care for a specific patientand/or group of patients.

Within healthcare, the term "episode of care" (EOC) is commonly used to refer tosteps, or events, that a patient are subjected to during care. The events may includemedical events, such as hospitalization (check-in), treatment, different tests of e.g. bloodfor purposes of diagnose, establishment of diagnosis, follow-up, discharge from hospital(check-out) or the like.

US20200251204 discloses a healthcare performance assessment apparatus thatincludes at least one processor programmed to collect information associated withmedically-related events from a plurality of databases, and group the collectedinformation associated with medically-related events into episode of care (EOC) datastructures. Each EOC data structure contains the collected information for a single EOC treating a medical condition or providing a medical procedure for a single patient.

Moreover, the processor is programmed to store the EOC data structures in an EOCrepository. The processor is further programmed to group EOC data structures having achosen commonality into at least one cohort, and to calculate at least one keyperformance indicators (KPls) for the cohorts. A display is configured to display the KPlsfor at least one selected cohort. ln this manner, KPls for the selected cohort is obtained.A disadvantage with this healthcare performance assessment apparatus may be that theKPls may be inaccurate and/or misleading, at least in some scenarios and/or for certain purposes.

SUMMARYAn object may be to reduce, or even eliminate, one or more of theabovementioned problems and/or disadvantages.

This object is achieved by the independent claims set forth herein. Further features are defined by the dependent claims.

According to an embodiment of the present invention, an episode of care (EOC)for treating a medical condition of a patent may be evaluated. The episode of careincludes a plurality of diagnostic events. A diagnostic event may be associated with adiagnostic result obtained by analysis of a sample relating to the patient. ln someexamples, the diagnostic result may be a numeric result, such as a measurement valueobtained from a technical analysis of the sample, such as a blood sample or the like,from the patient. Further, the diagnostic result may be a result indicating that apathologic condition is identified or not identified based on analysis of the sample, suchas a histopathological-, radiologic- or ultra-sound examination.

An EOC, defined as a number of medical events done in temporal order, oftenincluded diagnostic events as described. According to the embodiment presentlydescribed, at least two diagnostic events are observed in the EOC. The results from saidat least two diagnostic events may have impact on subsequent step(s) in the EOC,initially referred to as consequences for the patient.

Within healthcare, so called external quality assessment (EQA) programs areoften employed to evaluate quality of diagnostic results, such as accuracy, performanceand/or measurement accuracy. A random diagnostic result is evaluated in relation to a standardized quality test result, typically provided by and monitored by a certified institution. The standardized quality test result is thus provided for purposes ofevaluating and/or measuring quality of the diagnostic result associated with a diagnosticevent. The outcome of the standardized quality test is a quality test result, known asEQA result, or proficiency test result, in related literature. The quality test result may thusprovide a measure of error in the diagnostic result, such as a measurement error of atechnical analysis of a sample, or examination errors in a histopathological-, radiologic-or ultra-sound examination or the like.

With the present embodiment, a respective quality test result is thus obtained foreach of said at least two diagnostic events. Consequently, at least two quality testresults, including the respective quality test result for each of said at least two diagnosticevents, are obtained.

Moreover, information associated with said at least two diagnostic events for thepatient is collected. This information may include the patient's actual test results, such ashemoglobin level etc., for said at least two diagnostic events.

Next, at least one score is generated based on the collected information and therespective quality test result for each one of the two diagnostic events. Accordingly, thecollected information may in this manner be used in combination with said at least twoquality test results for evaluation of the EOC for the patient, while a single quality resultis according to the inventors' knowledge known to be used for evaluation of a singlediagnostic result.

Subsequently, said at least one score is provided, such as displayed, for use asevaluation and/or decision support for the treatment of the medical condition. ln this manner, at least two quality test results are combined for use asevaluation and/or decision support for the treatment of the medical condition in theobserved EOC.

An advantage is hence that at least portion of an EOC may be evaluated, during or after completion of the entire EOC, to improve quality of care for one or more patients.

According to an aspect, the object is thus achieved by a method, performed by acomputing apparatus, for evaluating care quality and/or assessing patient safety.

The computing apparatus obtains an episode of care for treating a medicalcondition of one or more patients, referred to as "a patient". The EOC comprises aplurality of diagnostic events related to the treatment of the medical condition.

The computing apparatus collects, from at least one healthcare institution,information associated with at least two of the plurality of diagnostic events, referred toas "two diagnostic events", for the patient.

The computing apparatus obtains quality test results for the two diagnosticevents. Said two diagnostic events in the episode of care are associated with twostandardized quality tests, respectively. Said two standardized tests are provided andmonitored by a control organ.

The computing apparatus generates, for the EOC, at least one score based onthe collected information and the quality test results.

The computing apparatus provides information indicative of said at least onescore for use as evaluation and/or decision support for the treatment of the medicalcondition.

According to another aspect, the object is achieved by a computing apparatusconfigured for evaluating care quality and/or assessing patient safety. The computingapparatus is configured for obtaining an episode of care for treating a medical conditionof one or more patients, referred to as "a patient". The EOC comprises a plurality ofdiagnostic events related to the treatment of the medical condition.

The computing apparatus is configured for collecting, from at least onehealthcare institution, information associated with at least two of the plurality ofdiagnostic events, referred to as "two diagnostic events", for the patient.

Moreover, the computing apparatus is configured for obtaining quality test resultsfor the two diagnostic events. Said two diagnostic events in the episode of care areassociated with two standardized quality tests, respectively. Said two standardized testsare provided and monitored by a control organ. The computing apparatus is configuredfor generating, for the EOC, at least one score based on the collected information andthe quality test results.

Furthermore, the computing apparatus is configured for providing informationindicative of said at least one score for use as evaluation and/or decision support for thetreatment of the medical condition.

BRIEF DESCRIPTION OF THE DRAWINGS The various aspects of embodiments disclosed herein, including particularfeatures and advantages thereof, will be readily understood from the following detaileddescription and the accompanying drawings, which are briefly described in the following.

Figure 1 is a schematic overview of an exemplifying network in whichembodiments herein may be implemented.

Figure 2 is a flowchart illustrating embodiments of the method in the computingapparatus.

Figure 3 is an illustration of a schematic and simplified information indicative of atleast one score for a first example.

Figure 4 is an illustration of a schematic and simplified information indicative of atleast one score for a second example.

Figure 5 is a flowchart illustrating an exemplifying episode of care.

Figure 6 is a block diagram illustrating an exemplifying computing apparatus according to the embodiments herein.

DETAILED DESCRIPTION Throughout the following description, similar reference numerals have been usedto denote similar features, such as nodes, actions, modules, circuits, parts, items,elements, units or the like, when applicable. ln the Figures, features that appear in some embodiments are indicated by dashed lines.

Figure 1 depicts an exemplifying system 100 in which embodiments herein may be implemented.

The system 100 comprises a computing apparatus 110, such as a computer, asoftware component executing on a virtual or physical server or the like. The computingapparatus 110 may be operated, direct or indirectly e.g. via a so called client device (notshown), such as a Personal Computer, smartphone or the like, by a user 140. The user140, such as a doctor or the like, may view information relating to a particular patient150, a group of patients, a particular healthcare provider, a group of healthcare providers or the like.

As an example, the system 100 may also comprise one or more databases, suchas a first database 120 comprising standardized quality test results, a second database130 comprising results from diagnostic events relating to one or more patients 150,and/or other similar databases the like. ln some examples, the first and second data bases 120, 130 form parts of acommon database. This may mean the first database 120 is the same as the seconddatabase 130. ln some other examples, the first database is separate, e.g. differentfrom, i.e. not the same as, the second database 130.

Throughout the present disclosure one or more of the following terms orexpression may be used.

"Episode of care", "course of care" or the like may refer to a sequence of eventsfor the treatment of a medical condition of one or more patients. The treatment mayinclude investigation, diagnose and follow-up concerning the medical condition of thepatient.

"Diagnostic event" - an event in the episode of care that is associated with adiagnostic result originating from a diagnostic analysis. The diagnostic result may forexample be: 1) numeric, such as one or more scalar measurement values, or 2) boolean or binary, such as true/false, yes/no, identified/not identified etc.. 3) ordinal results, such as a diagnosis grade I out of e.g. three grades, where the ordinal result can be sorted in a defined order, and 4) nominal or unsortable results, such as diagnosis A out of four possible diagnosis A, B, C and D, bacteria species A out of a plurality of possiblebacteria species. These diagnosis results cannot be sorted in a scale basedon amount/size etc..

The diagnostic analysis may be performed by a technical measurement device.ln this case, the diagnostic event may be a measurement event resulting in ameasurement result, such as said one or more scalar measurement values.Alternatively, the diagnostic analysis may be performed by a human expert, whichtypically provides a boolean diagnostic result.

Examples of diagnostic analyses that are performed by a technical measurement device include, but are not limited to, measurement of: o concentration of hemoglobin (Hb) in blood using a point-of-care device o concentration of Hb, number concentration of reticulocytes, Mean corpuscularvolume and mean corpuscular hemoglobin of erythrocytes measured on acell-counter o concentration of ferritin in blood plasma, o concentration of iron in blood plasma and the total iron-binding capacity(TIBC) in blood plasma using laboratory equipment at central hospitallaboratories o concentration of C-reactive protein (CRP) in blood plasma at the point of careand/or using automized laboratory equipment and o the like.

Examples of diagnostic analyses, or procedures, that are performed by a humanexpert include, but are not limited to: o echocardiography, heart function variables as measured by ultra sound technique. o pathological anatomical diagnosis based on investigation of tissue samplesfrom the patient's body, such as colon, rectum or the like or other part, and o the like. "decision limit" refers to one or more numerical threshold values which whenexceeded and/or undercut by a numeric diagnostic result, such as a measurementresult, indicates a pathologic condition of the patient under observation. ln someexamples, a range may be defined by two numerical threshold values. The range maytypically be associated with a normal condition of the patent. However, it may also be thecase that the range is associated with a pathological condition of the patient. ln thismanner, the diagnostic result is achieved by applying the decision limit(s) to themeasurement result.

"Healthcare provider" may include one particular hospital or one or morehospitals, healthcare institutions or the like. Said one or more hospitals or the like maybe organized into an administrative unit, region, area or the like.

"Certified institution" may refer to a quality assessment organization setting up,providing and/or monitoring one or more standardized quality tests for controlling qualityof one or more diagnostic analyses.

"Standardized quality test" may refer to the procedure and/or test basis providedby the certified institution. There may be a respective standardized quality test for each of one or more of the diagnostic analyses. Accordingly, a diagnostic analysis may beassociated with a corresponding standardized quality test.See section "standardized quality test" for further description."Quality test result" is an outcome of a standardized quality test. ln Figure 2, a schematic flowchart of an exemplifying method in the computingapparatus 110 is shown. Accordingly, the computing apparatus 110 may perform thecomputer-implemented method as defined by the appended independent claim. ln a first example, the method may be used for evaluating at least a portion of anEOC for a particular patient. For reasons of simplicity, the EOC comprises a firstdiagnostic event and a second diagnostic event. ln other examples, the EOC mayinclude any suitable number of diagnostic events, all associated with the observed EOC.However, it is of course not ruled out that any particular diagnostic event is associatedwith several different EOCs. An EOC could be exemplified by the process starting with apatient seeking professional opinion regarding a symptom leading to an investigation,leading to a diagnosis, leading to a treatment leading to a follow up scheme, all stepsoften including different kinds of diagnostic events. ln a second example, the method may be used for evaluating quality of care forat least one EOC at a particular healthcare provider. For reasons of simplicity, one EOCfor treatment of a particular medical condition will be considered in the following. Theembodiments herein may in some examples apply to one or more EOC at one or morehealthcare providers. Said one or more healthcare providers, forming a set of healthcareproviders, may be selected based on any desired commonality, such as region, area,number of patients treated, number of inhabitants in the region etc..

One or more of the following actions may be performed in any suitable order.

Action A010 The computing apparatus 110 obtains an episode of care EOC for treating amedical condition of one or more patients, referred to as "a patient". The EOC comprisesa plurality of diagnostic events related to the treatment of the medical condition. ln this manner, the computing apparatus 110 is beneficially provided withinformation about the EOC and the plurality of diagnostic events that are included in theEOC. This may be done in several manners. The computing apparatus 110 may e.g.fetch this information from a database or a combination of databases, such as the firstdatabase 120, the second database 130 or the like. Additionally or alternatively, thecomputing apparatus 110 may be configured with the information about the EOC and thediagnostic event associated therewith. Moreover, also or as an alternative, the user 140may input this information into the computing apparatus 110, e.g. directly or indirectly viathe client device.

With the first example, the EOC may typically include diagnostic events that thepatient has experienced, such as been exposed to, endured, passed through or the like.The outcome provided in action A050 below may or may not be used to determine whichof one or more optional diagnostic events may be included in the EOC for the patient.See also Figure 5.

With the second example, the EOC may include at least a portion of an EOC,preferably a complete EOC, for the treatment of a medical condition that a plurality ofpatients has experienced at the selected set of healthcare institutions.

Action A020 ln order to obtain information about the patient(s), the computing apparatus 110collects, from at least one healthcare institution, information associated with at least twoof the plurality of diagnostic events, referred to as "two diagnostic events", for thepatient(s).

The collected information may thus include test results, or patient test results todistinguish from quality test results, from the diagnostic event, such as a measurementvalue or the like as exemplified below.

With the first example, the first diagnostic event for the patient may be Hbmeasurement by primary care. The collected information may then include a firstmeasurement value of the Hb measurement for the observed patient. The seconddiagnostic event may be CRP measurement and the collected information may include asecond measurement value of the CRP for the observed patient. ln this manner, thecomputing apparatus 110 collects information, such as measurement results ofdiagnostic analyses in the EOC for the patient, i.e. the observed patient or the particularpatient.

With the second example, the computing apparatus 119 collects, e.g. from thesecond database 130 associated with the selected set of healthcare institutions, theinformation associated with said diagnostic events for patients treated at the set ofhealthcare institutions. ln this manner, an assessment of the quality of care for the EOC, or a portion thereof, at the set of healthcare institutions may be provided.

Action A030 The computing apparatus 110 obtains, such as receives from the first database120, quality test results for the two diagnostic events. Said two diagnostic events in theepisode of care are associated with two standardized quality tests, respectively. Said twostandardized tests are provided and monitored by a certified institution.

Said two diagnostic events may comprise at least one of a result from a technicalanalysis of a sample associated with the patient, a result from a diagnostic analysis of agraphical representation, obtained using a medical imaging technology. The graphicalrepresentation is associated with at least a portion of the patient. Examples of medicalimaging technologies include, but are not limited to, magnetic resonance imaging (MRI),X-ray, mammography, ultrasound, electrocardiogram (ECG or EKG), computed tomography (CT), and the like.

With the first example, a first quality test result, associated with the firstdiagnostic event and with the healthcare institution that handled the first diagnosticevent, is obtained, e.g. from the first database 120. Similarly, a second quality test result,associated with the second diagnostic event and with the healthcare institution thathandled the second diagnostic event, is obtained, e.g. from the first database 120. lnmore detail as non-limiting real-life example, the first quality test result may be an EQAresult for Hb for the healthcare institution. Further, in more detail as non-limiting real-lifeexample, the second quality test result may be an EQA result for CRP for the healthcareinstitution.

This similarly also applies for the second example when considering a plurality ofpatients treated in the observed EOC and by the healthcare institution.

Generally, each quality test result may comprise one or more of a mean, astandard deviation, a coefficient of variation (cv) for a set of measurement results on agiven sample, such a blood sample, urine sample, an image of the patient or the like, and a bias (or bias value) expressed in terms of an absolute value or percentage. The 11 bias, depending on whether it is a positive or negative value, is an indication of that thediagnostic result is consistently under or over a true value (as determined by e.g. thecontrol organ). As a result, the quality test result provides information aboutmeasurement accuracy at the healthcare institution, a laboratory or the like.

Action A040 The computing apparatus 110 generates, for the EOC, at least one score basedon the collected information and the quality test results.

Accordingly, the computing apparatus 110 may calculate, based on themeasurement accuracy at the healthcare institution obtained as quality test results usingthe standardized quality tests and the collected information, a probability of that thediagnostic result is a true positive result and/or a true negative result. ln the following, a more elaborated example will be described.

Terms used: Hb (Hemoglobin concentration in blood) value less than a cut off value, or threshold,measured from a person indicates anemia and/or inflammation CRP, concentration of C-reactive protein in blood plasma, value higher than a cut offvalue indicates an inflammatory process.

Prev, Prevalence, number of disease cases present in a particular population at a giventime. A known reference value from statistics on e.g. a reference population.

Patient test results, the measured value from a person, in this example Hb and CRPBias, the difference (generally unknown) between a laboratory's average value (overtime) for a test item and the average that would be achieved by the reference laboratoryif it undertook the same measurements on the same test item. Typically, the quality testresult for a particular diagnostic test comprises the bias, e.g. as a bias value.

SD, The SD (standard deviation) is calculated es the square foot of verience by determinihg each data points deviation teiative to the nteeh. Typically, the quality testresult for a particular diagnostic test comprises the SD, e.g. as a SD value.

PPV, positive predictive value, is the probahiiity thet subjects with a positive screeningtest, si" patient test, resuits outside e decision iimit, truiy have the ttiseese.

Cut-ett vetue, are the dividing point on meesurihg scaies tlvitete the patient test resuitsare divided into different categories; typiceiiy eesitive (indicating semeehe hes the 12 condition of interest), or negative (indicating someone does not has the condition ofinterest.

Reference popiiiation, a ciafiriad subset of a target poputatiari that serves as a standardagainst which specific: findings ara evaitiated.

Diagnsstio sensitivity (sensitivity or sans for short herein), or Trtia Positiva rate,rneasores the proportion of positives (ie. being pathoiogio) that are correctiy identified(ia. tha proportion of tiiosa vvno have serna condition (affactad) who ara corracttyidentified as having the pathoiogic condition).

Diagnostie speoifioity (spacificity or spar: for short iierein), or True Negativa rate,rriaasuras the proportion of riagativas (heaithyfriorrnai) that ara corractiy identified (ie.the proportion of those who do not have the condition (unaffectaci) who are aorrectiyidentified as not having tna condition, being heaithylnarniai).

Exarnpie with reference to Figure 3, A i-ih vaioe of Qtšgfi. and a CRP of 'iâüniglL isrriaasurad in raatierit A tvvo days aftar a surgicai procedura as for patient X1.

The cut-off values of interest are 134g/L for Hb and 150 mg/L for CRP.

The prevalence of a complication causing an inflammatory response aftersurgery is 10%.

The results from two different EQA schemes (one for Hb and one for CRP)shows that the instruments used for analysing Hb and CRP in the blood from patient Ado have a bias of -1 and SD of 2 for Hb and a bias of -10 and SD of 10 for CRP.

Patient X2 and X3 are merely shown as illustrative examples.

Calculation - example of action A040.

Step 1 The cut-off value, the patient test result, bias and SD is used to calculate theprobability that the real (unknown) test result truly would be lower than the cut-off(pathologic). This probability is the sensitivity (Sens). The patient test result is thus astatistic outcome (or sample) representing the real (unknown) test result.

As an example, the so called probability density function, often referred to as thebell-curve in related literature, for a normal distribution may be used to calculate theprobability that a number falls at or below a given value. The given value is the cut-offvalue and a mean for the distribution is represented by the patient test result after 13 adjustment with the bias (i.e. reduced or increased according to the bias value). Hence,it can then by use of the probability density function be determined with which probabilitythe real patient test result would be higher or lower than the cut-off value. The cut-offmay be a lower threshold or an upper threshold depending on what is normal/healthy fora patient. Similar examples may be made for other distributions with other probabilitydensity functions.

Accordingly, the sensitivity, expressed as a probability, may be determined, suchas calculated, based on cut-off value, patient test result as mean after adjustmentaccording to bias, the SD and using the probability density function. ln this example, i.e. for this patient result, the sensitivity is 1 (afterrounding/approximation).

Step 2 The cut-off value, mean value and SD of Hb and CRP for the referencepopulation is used to calculate the probability that the real (unknown) test result trulywould be higher than the cut-off (normal). This probability is the specificity (spec). ln a similar fashion to the sensitivity, albeit with differences as in the following,the specificity may be determined, such as calculated, based on a mean and a SD for areference population and the patient result.

Using quasi-programming language using functions whose name depend on thesoftware used, the specificity may be calculated as: Spec= (1-Dist_Norm(PR,MeanRef,SDref))/(1-Dist_Norm(PR,MeanRef,SDref)+P3) PR= the patient test result.

MeanRef is the mean of the reference population.

SDref is the standard deviation for the reference population.

P3 is calculated as a probability in the same manner as the sensitivity using thecut-off, the mean and the SD for the reference population.

The Dist_Norm-function gives the probability that a number falls at or below agiven value of a normal distribution.

Step 3 PPV is calculated using the formula PPV= (Sens x Prev)/(Spec x Prev+(1-Spec) x (1-Prev)) 14 Prev= 10% e.g. according to epidemiologic research available through e.g. look-up in related literature, databases or the like. The value may also differ for differentcountries, regions etc.

For each and one of the included diagnostic analyses, the PPVs are calculated,i.e. PPVHb and PPVCRP, respectively. ln this example, the PPVHb for Hb is 85% andthe PPVCRP for CRP is 71%.

As the last step the combined PPV for this EoC is calculated as PPVHb x PPVCRP = PPVtotal, which yields: 0.85 x 0.71 = 0.60, i.e. shown as total in Figure 3. ln the example above, PPV has been used. However, in other examples thecollected information and the quality test results may be used to calculate otherintermediate results in the process of generating said at least one score. ln further examples, the calculations above may be performed on the basis of ordinal diagnostic results.

The calculations above may be used with the first example, where the patient testresults from a specific patient are used together with quality test results from relevantEQA's to assess the uncertainty for a specific EOC for the individual patient. Likewise,the calculations above can be used with the second example, where e.g. multiple patienttest results from a particular hospital together with corresponding quality test results areused to form mean-values as a measure of the quality at the hospital. As an example,with brief reference to Figure 4, the mean of three (or any number of patients) patientsPPVHb is calculated for the first diagnostic event, DE1, and the mean of the threepatients PPVCRP is calculated for the DE2. Then, the total is the product of these values.Alternatively, the total is calculated for each of the patients and then the mean of thetotals for the patients is used as a measure of the quality of the healthcare institution. orhospital. ln the examples above, PPV has been used for purposes of illustration. ln otherexamples, said at least one score may comprise the prevalence values for eachdiagnostic event, such as PPVHb, PPVCRP. Yet, further said at least one score maycomprise the minimal and/or maximal value taken from the scores, such as prevalence, sensitivity, specificity or the like, for each diagnostic event.

Also, all individual patient test results during a specified period of time, e.g.annually, for a specific group of patients, e.g. Covid-19, Diabetes, colorectal cancer,could be entered into the calculation for quality assessment of the whole EOC in aspecific setting or for a specific health care provider.

Finally, the EQA results could be used with a simulation of patient test results.E.g., 10% deviation from the cut-off values to estimate the number of right and wrongclassified patients during a specific period of time in a specific health care setting. Theseresults could be visualized as heat maps showing the number of right classified patients for each diagnostic step (columns) within a specific EOC for healthcare providers. ln some examples, the computing apparatus 110 may generate said at least onescore by generating a respective score for each one of said two diagnostic events. A setof scores may comprise the respective score for each diagnostic result in the EOC. ln this manner, several respective scores, one or more of the respective scorescomprised in the set of scores, may be compared.

With the first example, the user 140 may, based on such comparison, decidewhich diagnostic event to follow next.

With the second example, the user 140, based on such comparison, decidewhich one or more of the diagnostic events in the EOC to improve in order to enhancequality of care.

Action A050 The computing apparatus 110 provides information indicative of said at least onescore for use as evaluation and/or decision support for the treatment of the medicalcondition. For example, said at least one score can be used as evaluation and/ordecision support for the medical condition of interest, where the decision support mayrefer to which diagnostic event to perform next and/or to how reliable the assesseddiagnostic events shall be considered to be.

Each one of said at least one score may be associated with a respective color. lnthis manner, a so called heatmap may be constructed for the representation of said at least one score.

Standardized quality test 16 Within the healthcare sector, it is of interest to measure quality of a diagnosticevent. For this purpose, various control organs, such as certified institutes, a specialdepartment within a hospital or the like, provide standardized quality tests, one for eachdiagnostic event. A control organ may be referred to as a diagnosis evaluation testprovider, i.e. a provider of standardized tests for evaluation of diagnosis reliability. Thecontrol organ may thus be a control organization for evaluation of diagnostic tests. Fordiagnosis performed by technical analysis devices, the evaluation of diagnosis reliabilitymay amount to the provision of estimates of measurement uncertainty.

A healthcare institution, typically a hospital, that participates in a standardizedquality test performs a set of diagnostic analyses on a test sample, which typically isknown and provided by the control organization. When performing the set of diagnosticanalysis on the test sample, the healthcare institution obtains a set of sample testresults, which are provided to the certified institution. Next, the certified institutionprocesses the set of sample test results to provide one or more quality test result(s),such as EQA results, as an indication of measurement accuracy at the participating healthcare institution.

To the inventors' knowledge, one diagnostic event at a time is evaluated with thestandardized quality test. With embodiments herein, an impact of measurementaccuracy for at least two diagnostic events that belong to one and the same EOC isassessed for use as evaluation and/or decision support for the treatment of the medical condition.

With reference to Figure 6, a schematic block diagram of embodiments of the computing apparatus 110 of Figure 1 is shown.

The computing apparatus 110 may comprise a processing unit 601, such as ameans for performing the methods described herein. The means may be embodied inthe form of one or more hardware units and/or one or more software units. The term"unit" may thus refer to a circuit, a software block or the like according to variousembodiments as described below.

The computing apparatus 110 may further comprise a memory 602. The memorymay comprise, such as contain or store, instructions, e.g. in the form of a computer program 603, which may comprise computer readable code units. 17 According to some embodiments herein, the computing apparatus 110 and/or theprocessing unit 601 comprises a processing circuit 604 as an exemplifying hardwareunit, which may comprise one or more processors. Accordingly, the processing unit 601may be embodied in the form of, or 'realized by', the processing circuit 604. Theinstructions may be executable by the processing circuit 604, whereby the computingapparatus 110 is operative to perform the methods of Figure 2. As another example, theinstructions, when executed by the computing apparatus 110 and/or the processingcircuit 604, may cause the computing apparatus 110 to perform the method according toFigure 2. ln view of the above, in one example, there is provided a computing apparatus110 for evaluating care quality and/or assessing patient safety. Again, the memory 602contains the instructions executable by said processing circuit 604 whereby thecomputing apparatus 110 is operative for: obtaining an episode of care (EOC) for treating a medical condition of one ormore patients, referred to as "a patient", wherein the EOC comprises a plurality ofdiagnostic events related to the treatment of the medical condition, collecting, from at least one healthcare institution, information associated with atleast two of the plurality of diagnostic events, referred to as "two diagnostic events", forthe patient, obtaining quality test results for the two diagnostic events, wherein said twodiagnostic events in the episode of care are associated with two standardized qualitytests, respectively, wherein said two standardized tests are provided and monitored by acontrol organ, generating, for the EOC, at least one score based on the collected informationand the quality test results, and providing information indicative of said at least one score for use as evaluation and/or decision support for the treatment of the medical condition.

Figure 6 further illustrates a carrier 605, or program carrier, which provides, suchas comprises, mediates, supplies and the like, the computer program 603 as describeddirectly above. The carrier 605 may be one of an electronic signal, an optical signal, aradio signal and a computer readable medium. 18 ln some embodiments, the computing apparatus 110 and/or the processing unit601 may comprise one or more of a unit 610, a unit 620, a unit 630, a unit 640, a unit650, a unit 660, a unit 670, a unit 680, and a unit 690 as exemplifying hardware units.The term "unit" may refer to a circuit when the term "unit" refers to a hardware unit. lnother examples, one or more of the aforementioned exemplifying hardware units may be implemented as one or more software units.

Moreover, the computing apparatus 110 and/or the processing unit 601 maycomprise an Input/Output unit 606, which may be exemplified by the receiving unit and/or the sending unit when applicable.

Accordingly, the computing apparatus 110 is configured for evaluating carequality and/or assessing patient safety.

Therefore, according to the various embodiments described above, thecomputing apparatus 110 and/or the processing unit 601 and/or the obtaining unit 610 isconfigured for obtaining an episode of care EOC for treating a medical condition of oneor more patients, referred to as "a patient". The EOC comprises a plurality of diagnosticevents related to the treatment of the medical condition.

The computing apparatus 110 and/or the processing unit 601 and/or thecollecting unit 620 is configured for collecting, from at least one healthcare institution,information associated with at least two of the plurality of diagnostic events, referred toas "two diagnostic events", for the patient.

The computing apparatus 110 and/or the processing unit 601 and/or theobtaining unit 610, or another obtaining unit (not shown), is configured for obtainingquality test results for the two diagnostic events. Said two diagnostic events in theepisode of care are associated with two standardized quality tests, respectively. Said twostandardized tests are provided and monitored by a control organ.

The computing apparatus 110 and/or the processing unit 601 and/or thegenerating unit 630 is configured for generating, for the EOC, at least one score basedon the collected information and the quality test results.

The computing apparatus 110 and/or the processing unit 601 and/or theproviding unit 640 is configured for providing information indicative of said at least onescore for use as evaluation and/or decision support for the treatment of the medicalcondition. 19 As used herein, the term "computing apparatus", may refer to one or morephysical entities, such as devices, apparatuses, computers, servers or the like. This maymean that embodiments herein may be implemented in one physical entity. Alternatively,the embodiments herein may be implemented in a plurality of physical entities, such asan arrangement comprising said one or more physical entities, i.e. the embodiments maybe implemented in a distributed manner, such as on a cloud system, which maycomprise a set of server machines. ln case of a cloud system, the term "computingapparatus" may refer to a virtual machine, such as a container, virtual runtimeenvironment, a software module or the like. The virtual machine may be assembled fromhardware resources, such as memory, processing, network and storage resources,which may reside in different physical machines, e.g. in different computers.

As used herein, the term "unit" may refer to one or more functional units, each ofwhich may be implemented as one or more hardware units and/or one or more softwareunits and/or a combined software/hardware unit in a node. ln some examples, the unitmay represent a functional unit realized as software and/or hardware of the node.

As used herein, the term "computer program carrier", "program carrier", or"carrier", may refer to one of an electronic signal, an optical signal, a radio signal, and acomputer readable medium. ln some examples, the computer program carrier mayexclude transitory, propagating signals, such as the electronic, optical and/or radiosignal. Thus, in these examples, the computer program carrier may be a non-transitorycarrier, such as a non-transitory computer readable medium.

As used herein, the term "processing unit" may include one or more hardwareunits, one or more software units or a combination thereof. Any such unit, be it ahardware, software or a combined hardware-software unit, may be a determining means,estimating means, capturing means, associating means, comparing means, identificationmeans, selecting means, receiving means, sending means or the like as disclosedherein. As an example, the expression "means" may be a unit corresponding to the unitslisted above in conjunction with the Figures.

As used herein, the term "software unit" may refer to a software application, aDynamic Link Library (DLL), a software component, a software module, a softwareobject, an object according to Component Object Model (COM), a software function, asoftware engine, an executable binary software file or the like.

The terms "processing unit" or "processing circuit" may herein encompass aprocessing unit, comprising e.g. one or more processors, an Application SpecificIntegrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or the like. Theprocessing circuit or the like may comprise one or more processor kernels.

As used herein, the expression "configured to/for" may mean that a processingcircuit is configured to, such as adapted to or operative to, by means of softwareconfiguration and/or hardware configuration, perform one or more of the actionsdescribed herein.

As used herein, the term "action" may refer to an action, a step, an operation, aresponse, a reaction, an activity or the like. lt shall be noted that an action herein may besplit into two or more sub-actions as applicable. Moreover, also as applicable, it shall benoted that two or more of the actions described herein may be merged into a singleaction.

As used herein, the term "memory" may refer to a hard disk, a magnetic storagemedium, a portable computer diskette or disc, flash memory, random access memory(RAM) or the like. Furthermore, the term "memory" may refer to an internal registermemory of a processor or the like.

As used herein, the term "computer readable medium" may be a Universal SerialBus (USB) memory, a Digital Versatile Disc (DVD), a Blu-ray disc, a software unit that isreceived as a stream of data, a Flash memory, a hard drive, a memory card, such as aMemoryStick, a Multimedia Card (MMC), Secure Digital (SD) card, etc. One or more ofthe aforementioned examples of computer readable medium may be provided as one ormore computer program products.

As used herein, the term "computer readable code units" may be text of acomputer program, parts of or an entire binary file representing a computer program in acompiled format or anything there between.

As used herein, the terms "number" and/or "value" may be any kind of digit, suchas binary, real, imaginary or rational number or the like. Moreover, "number" and/or"value" may be one or more characters, such as a letter or a string of letters. "Number"and/or "value" may also be represented by a string of bits, i.e. zeros and/or ones.

As used herein, the terms "first", "second", "third" etc. may have been usedmerely to distinguish features, apparatuses, elements, units, or the like from one anotherunless othen/vise evident from the context. 21 As used herein, the term "subsequent action" may refer to that one action isperformed after a preceding action, while additional actions may or may not beperformed before said one action, but after the preceding action.

As used herein, the term "set of" may refer to one or more of something. E.g. aset of devices may refer to one or more devices, a set of parameters may refer to one ormore parameters or the like according to the embodiments herein.

As used herein, the expression "in some embodiments" has been used toindicate that the features of the embodiment described may be combined with any other embodiment disclosed herein.

Even though embodiments of the various aspects have been described, manydifferent alterations, modifications and the like thereof will become apparent for thoseskilled in the art. The described embodiments are therefore not intended to limit the scope of the present disclosure.

Claims (1)

1. Claims A method, performed by a computing apparatus (110), for evaluating care qualityand/or assessing patient safety, wherein the method comprises: obtaining (A010) an episode of care (EOC) for treating a medical condition of oneor more patients, referred to as “a patient”, wherein the EOC comprises a plurality ofdiagnostic events related to the treatment of the medical condition, collecting (A020), from at least one healthcare institution, information associatedwith at least two of the plurality of diagnostic events, referred to as “two diagnosticevents”, for the patient, obtaining (A030) quality test results for the two diagnostic events, wherein saidtwo diagnostic events in the episode of care are associated with two standardizedquality tests, respectively, wherein said two standardized tests are provided andmonitored by a control organ, generating (A040), for the EOC, at least one score based on the collectedinformation and the quality test results, and providing (A050) information indicative of said at least one score for use asevaluation and/or decision support for the treatment of the medical conditionThe method according to claim 1, wherein said two diagnostic events comprise atleast one of a result from a technical analysis of a sample associated with thepatient, a result from a diagnostic analysis of a graphical representation, obtainedusing a medical imaging technology, wherein the graphical representation isassociated with at least a portion of the patientThe method according to claim 1 or 2, wherein the generation (A040) of at least onescore comprises generating a respective score for each one of said two diagnostic eventsA computing apparatus (110) configured to perform a method according to any oneof the preceding claimsA computer program (603), comprising computer readable code units which whenexecuted on a computing apparatus (110) causes the computing apparatus (110) toperform the method according to any one of claims 1-6A computer program carrier (605) comprising the computer program according to thepreceding claim, wherein the carrier (605) is one of an electronic signal, an opticalsignal, a radio signal and a computer readable medium.