=Paper=
{{Paper
|id=Vol-1960/paper3
|storemode=property
|title=Learning from Administrative Health Registries
|pdfUrl=https://ceur-ws.org/Vol-1960/paper3.pdf
|volume=Vol-1960
|authors=Jonathan Rebane,Isak Karlsson,Lars Asker,Henrik Boström,Panagiotis Papapetro
}}
==Learning from Administrative Health Registries==
https://ceur-ws.org/Vol-1960/paper3.pdf
Learning from Administrative Health Registries
Jonathan Rebane, Isak Karlsson, Lars Asker, Henrik Boström, and Panagiotis
Papapetrou
Dept. of Computer and Systems Sciences, Stockholm University, Sweden
{rebane,isak-kar,asker,henrik.bostrom,panagiotis}@dsv.su.se
Abstract. Over the last decades the healthcare domain has seen a
tremendous increase and interest in methods for making inference about
patient care using large quantities of medical data. Such data is often
stored in electronic health records and administrative health registries.
As these data sources have grown increasingly complex, with millions of
patients represented by thousands of attributes, static or time evolving,
finding relevant and accurate patterns that can be used for predictive
or descriptive modelling is impractical for human experts. In this paper,
we concentrate our review on Swedish Administrative Health Registries
(AHRs) and Electronic Health Records (EHRs) and provide an overview
of recent and ongoing work in the area with focus on adverse drug events
(ADEs) and heart failure.
1 Introduction
Swedish Administrative Health Registries (AHRs) and Electronic Health Records
(EHRs) provide a valuable source of information for a patient’s medical his-
tory. They typically include billing codes of diagnoses (e.g., ICD10), laboratory
tests, pharmaceutical information (e.g., drug prescriptions), and clinical notes
(e.g., short texts written by healthcare practitioners). Such data sources can be
exploited for developing robust predictive models for solving challenging tasks
within the domain of healthcare, such as detecting adverse events (AEs), as well
as for understanding different variations in treatment of heart failure.
In contrast to spontaneous reports, which usually contain only a limited snap-
shot of the circumstances surrounding a suspected ADE for a specific individual
or particular treatments for heart failure, EHRs and AHRs and provide med-
ical practitioners and clinical pharmacologists with a much richer description
of the medical history of not only individual patients but also of large groups
of patients sharing a similar medical conditions or with high similarity in their
recorded clinical history. Such rich and complex data sources can be effectively
and efficiently processed, studied, and analyzed through the usage of advanced
machine learning techniques, both in a supervised and an unsupervised manner.
In this paper, we discuss the current state-of-the-art and present recent work
on Swedish AHRs and EHRs. We provide an overview of recent and ongoing
work in the area with focus on adverse drug events (ADEs) and heart failure.
Our main contributions include:
Jonathan Rebane et al.
2. DETECTING ADVERSE DRUG EVENTS
– we present our recent work on detecting and understanding ADEs, with
focus on predictive modeling techniques, methods for mining disproportional
patterns, and finally we present the ADE explorer, a tool for studying ADEs
from EHRs;
– we present ongoing work on understanding the effectiveness of treatment of
heart failure from AHRs, with emphasis on understanding the reasons behind
the large variation of the usage rate of basic treatment by 50 hospitals in
Stockholm County;
– we discuss directions for future research on our current projects involving
EHRs and AHRs.
2 Detecting Adverse Drug Events
Adverse drug events (ADEs), commonly defined as undesired harms caused by
the intake of medications [12], account for an increasing amount of hospital-
izations and deaths worldwide [3, 7]. Adverse events are both a serious health
concern, estimated to be the seventh most common cause of death in Sweden
[21], and a significant burden on the health care system [15]. Although a ben-
efit–risk analysis of newly developed drugs is already conducted during clinical
trials, post-marketing detection and surveillance are often performed to detect
unanticipated events. For instance, clinical trials are normally performed with a
limited sample of patients, who are followed for a limited period of time. As a
result, not all serious adverse events can be detected prior to market deployment,
which results in drugs being withdrawn from the market due to serious adverse
reactions not detected during clinical trials.
The activities related to the detection, signaling, and assessment of adverse
drug events is referred to as pharmacovigilance or post-marketing drug surveil-
lance. During post-marketing surveillance, a vast array of automatic approaches
for detecting potential safety hazards of drugs have been investigated, cf. [1, 13],
using various data sources, the most prominent of which is a disproportionality
analysis of spontaneous individual case reports [19]. One of the main obstacles,
however, with current systems for collecting and analyzing data regarding ad-
verse drug events is the fact that serious ADEs are heavily under-reported, while
known ADEs are over-reported, by both clinicians, in the case of EHRs, and by
patients, in the case of individual case reports [5]. Complementary and alterna-
tive sources have thus been investigated, such as online communities [10], EHRs
and other administrative health registries. The major benefit of EHRs and health
registries is that they typically contain longitudinal observational data of large
samples of patients, including demographic information, medical history, drug
consumption with exposure time and dose information, and clinical measure-
ments, including lab results and drug concentrations. To improve the reporting
rate, systems have thus been investigated to automatically detect ADEs from
electronic health records, which avoids several of the limitations present in case
reports cf. [9].
Next, we discuss work that has been carried out to (a) mine disproportionate
(i.e., unexpected) patterns and (b) construct predictive models that are used
2
Jonathan Rebane et al.
2. DETECTING ADVERSE DRUG EVENTS
to identify patients with potential adverse drug reactions. We also describe the
prototype of a system where health practitioners can explore and test hypotheses
with respect to adverse reactions from drugs.
2.1 Mining disproportionate patterns
In recent work[2], we have explored ways of improving ADE detection by com-
bining sequential pattern mining with disproportionality analysis. In particular,
we investigated the use of sequential pattern mining for finding frequent drug
sequences, which then form the basis for the disproportionality analysis, i.e., in-
stead of looking for unexpected drug-diagnosis pairs, the novel method will find
unexpected pairs of drug sequences and diagnoses. Since the proposed method is
better suited to handle drug interactions, it is expected to handle cases where a
sequential administration of interacting drugs is responsible for a certain ADE.
An empirical investigation of the novel method has been performed using a sub-
set of the Stockholm EPR corpus [4]. The data used in this study consists of
all diagnoses and medications for 3189 patients that have received at least one
heart related diagnosis during the period 2008 - 2010.1
The empirical investigation showed that the proposed method indeed could
discover some patterns with sufficient support and that they occur much more
frequently for the patient groups with the diagnoses of interest than what is
expected in general. Using frequency-based sequential mining alone would not
highlight the discovered patterns as they would be ranked far behind patterns
that appear more frequently in the whole patient group, i.e., independently of
whether the diagnosis is present or not. On the other hand, traditional dispro-
portionality analysis would not allow us to find candidate interactions, since that
type of analysis is based on one diagnosis and one drug at a time.
The patterns discovered by the proposed method must however be treated
as possible hypotheses or candidates for adverse drug interaction, rather than
actual causes of the disease, since there may be many natural explanations for
why a certain combination of drugs occur more frequently for patients with
the diagnosis of interest than for patients in general, some of which have been
pointed out for the findings concerning drugs for cardiovascular patients. Hence,
any findings need to be further carefully analyzed to allow for finding true adverse
drug interactions.
2.2 Predictive modelling of ADEs
Knowledge extraction from EHRs is a rather new research area, since EHRs
were, until recently, not only relatively rare but also not easily accessible for re-
searchers due to their sensitive nature. However, they have become more abun-
dant and accessible for research during recent years in several countries, such as
USA and Sweden. In one example study, 667,000 inpatient and outpatient EHRs
1
This research has been approved by the Regional Ethical Review Board in Stock-
holm, permission number 2012/834-31/5.
3
Jonathan Rebane et al.
2. DETECTING ADVERSE DRUG EVENTS
were analyzed to discover new relations between drug intake and reactions. The
prediction of AEs using EHRs is an ongoing research endeavor, in which most
efforts to date have focused on using either structured[22] or unstructured data
[6], separately. Preliminary results show that predictive performance is substan-
tially improved by combining heterogeneous types of clinical data sources [6]. A
comprehensive overview of the research area can be found in [11].
Recent work on detecting adverse drug events has shown that a bag-of-words
model that exploits the set of drug prescriptions and diagnoses for a large set
of patients can give promising results in terms of recall and AUC. Nonetheless,
recent studies have shown that there is still plenty of room for improvement
by exploiting the temporal properties of the data sources in EHRs [20]. For
example, the early diagnosis or prediction of an AE can be highly correlated
with a positive prognosis and timely treatment [11]. Hence, the temporal and
causal features inherent in EHRs, e.g., in the form of time-evolving variables
or cause-effect relations, should be modeled and exploited to the largest extent
possible.
(a) Decision tree model constructed from (b) Disproportionality analysis of the
the case and control group. events in the case group as compared to the
population.
Fig. 1: Exploring patients between ages 74 and 90 that have and have not been
diagnosed with essential hypertension using (a) decision trees and (b) dispro-
portionality analysis
2.3 Adverse drug event explorer (ADEX)
The Adverse Drug Event eXplorer (ADEX) is an exploratory prototype system
for investigating and testing hypotheses regarding ADEs. The system allows
medical practitioners to define, using a complex rule system, a population and
a case group (e.g., patients that have experienced an adverse event and those
who have not) and then explore these patients based on disproportionate events,
importance of attributes, or rules. For instance, if one is interested in exploring
patients older than 75 years that have and have not suffered from heart diseases,
then one could define the population as Age > 75 and the case group as ICD
4
Jonathan Rebane et al.
3. EFFECTIVENESS OF TREATMENT IN HEART FAILURE PATIENTS
= I109 (see Fig. 1). These groups can then be analyzed using a plethora of
different methods, which in ADEX includes decision trees, random forests and
disproportionality analysis.
Although ADEX allows for practitioners to investigate and explore medically
relevant hypotheses, these hypotheses are still rather limited. In particular, the
tool does note allow one to explore medical trajectories of patients or to in-
corporate temporality in neither rules, decision trees nor pattern importances.
Moreover, to fully investigate the impact of treatments the rule language used
to describe case and control groups should be refined to allow one to express
rules temporal rules, e.g., ICD = I109 before ATC = C01AA01.
3 Effectiveness of Treatment in Heart Failure Patients
The Swedish National Board of Health and Welfare has issued national guidelines
for cardiac care [18], including recommendations for the treatment of patients
with heart failure. These include descriptions of preferred medications based on
diagnosis, severity of symptoms and factors related to the individual patient.
In the recommendations, it is stated that the basic treatment of patients with
heart failure should be renin angiotensin aldosterone system (RAS) inhibitors
combined with beta blockers. In order to evaluate the compliance to the rec-
ommendations, the National Board of Health and Welfare has also established
target levels for various indicators describing the desired portion of certain pa-
tient groups that should be eligible for specific treatments [16]. One such target
is that at least 65% of the HF patients should receive basic treatment consisting
of a combination of RAS-inhibitors and beta blockers. Other indicators are also
defined for the use of mineralcorticoid receptor antagonists (MRA) and CRT
pacemakers. In a recent evaluation of the compliance to the guidelines [17], it
was noted that for heart failure, only three of the 22 county councils in Swe-
den reach the target levels regarding basic medication of heart failure. For the
Stockholm region in total, only 57% of patients with heart failure were medi-
cated according to the national recommendations. However, deviations from the
basic treatment can often be motivated, which explains why the target level is
not set to 100%. For example, the basic treatment is known to have a good
effect on patients with heart failure with reduced ejection fraction (HFrEF), but
there is less evidence that is has the same effect on patients with heart failure
with preserved ejection fraction (HFpEF). International studies and the Swedish
quality register RiksSvikt indicate that between 50 – 80 % of the patients have
HFrEF [17].
In order to better understand and characterize patients that receive the ba-
sic treatment for heart failure, and what distinguishes them from patients that
according to the formal requirements should, but have not, received the basic
treatment, an analysis of administrative records collected in the Stockholm City
Council during 2010-2016 has been made [8]. In that work, we presented re-
sults from applying frequent pattern mining on data from heart failure patients
receiving basic treatment, and where these patterns are ranked according to de-
5
Jonathan Rebane et al.
3. EFFECTIVENESS OF TREATMENT IN HEART FAILURE PATIENTS
viations from the expected, using heart failure patients that have not received
basic treatment as the control. These deviations were quantified by using dis-
proportionality analysis [14] on the frequencies of the discovered patterns in the
test group against the control group.
3.1 Itemset mining formalization
More concretely, we define a set of possible item labels Σ, which correspond to
diagnoses or prescription codes. An itemset of size k, also called a k-itemset, is
defined as a set I = {l1 , . . . , lk } of k labels, with li ∈ Σ, ∀j ∈ [1, k]. A transaction
T = {I1 , . . . , IN } is a set of itemsets. The size of the transaction is the number
of itemsets that it contains. We say that a transaction T contains an itemset
I and denote it as I v T , if there is at least one occurrence of the itemset in
the transaction. Given a set of M transactions D = {T1 , . . . , TM }, the frequency
of an itemset I in D is equal to the fraction of transactions that contain the
itemset, i.e.,
|I v D|
f req(I, D) =
M
Hence, the objective of frequent itemset mining is to identify the set of fre-
quent itemsets F in D, given a support threshold min sup, where for each Fi ∈ F
it holds that f req(Fi , D) ≥ min sup. Finally, considering an additional collec-
tion of transactions C, acting as a control group to D, it should hold that the
two sets are independent, i.e., C ∩ D = ∅. Using these sets, we define the degree
of itemset disproportionality of an itemset I in D against C is defined as follows:
f req(I, D)
Idisp(I, D, C) = . (1)
f req(I, C)
3.2 Preliminary results
The experiments carried out so far2 have used data extracted from a regional
healthcare data warehouse GVR/VAL, which contains diagnoses (ICD-10), drugs
(ATC), and other data related to consultations in primary and secondary care for
more than 2 million inhabitants of the greater Stockholm area. All information
is anonymous in order to preserve patient integrity. The population selected
for this study consists of all individuals in the GVR/VAL data warehouse that
during the time period 2010-2016 have been hospitalized for at least one night
and been diagnosed with at least one heart failure related diagnosis; ICD-10:
I50, I11.0, I42 (excluding I42.1 and I42.2), and I43. In total the data used in this
study relates to 70,474 unique heart failure patients (9,446,322 events defined as
assigned diagnosis codes). In total these patients are described by approximately
7,013 distinct diagnose codes. For this study, all diagnoses were represented by
the first three characters of the ICD-10 code. In the experiments the patients are
2
This research has been approved by the Regional Ethical Review Board in Stockholm
(Dnr. 2016/479-31/5)
6
Jonathan Rebane et al.
4. FUTURE OUTLOOK AND CHALLENGES
divided into two groups based on whether or not the patient has been prescribed
the primary basic treatment for heart failure as defined by the national guidelines
from Socialstyrelsen [18].
The results of the analysis highlight groups of patients that are more likely to
receive basic treatment. By ranking the frequent itemsets according to their rel-
ative frequency between the groups, we get a better understanding of what types
of patients are present in the respective groups. The most disproportional fre-
quent itemsets where approximately 7 to 10 times more frequent among patients
that received primary basic treatment than among those that did not. These
itemsets consisted of combinations of 4 or 5 of the following 7 diagnoses: E11
(type 2 diabetes mellitus), I10 (essential (primary) hypertension), I25 (chronic
ischemic heart disease), I48 (atrial fibrillation and flutter), I50 (heart failure),
Z92 (personal history of medical treatment) and Z95 (presence of cardiac and
vascular implants and grafts) (Table 1). For more details the reader may refer
to the original paper by Karlsson et al. [8].
Table 1: The top ranked itemsets, showing combinations of diagnoses that are more
likely to indicate basic treatment. The itemsets are ranked based on their disproportion-
ality score which shows how much more likely it is that a patient with this combination
of diagnoses will receive basic treatment compared to not receiving it. A bullet indicates
the presence of an item in the itemset.
Disp. E11 I10 I25 I48 I50 Z92 Z95
9.675 • • • • •
9.410 • • • • •
9.254 • • • •
9.221 • • • •
8.220 • • • •
7.945 • • • •
7.707 • • • •
7.638 • • • • •
7.376 • • • •
7.356 • • • •
4 Future outlook and challenges
Future endeavours into this domain will consist of a variety of challenges that
are both data and clinically centered. Firstly, due to the nature clinical data
reporting being inconsistent, the data sets in focus must be processed to account
for: various missing values, measurements being recorded at once during the
day, and various other types of errors which impact quality. Although current
directions in healthcare involve moving towards more consistent and structured
data sets, this is a prospect of the future, and data sets at hand must undergo
7
Jonathan Rebane et al.
5. CONCLUSIONS
well-thought-out pre-processing procedures such as interpolation, extrapolation,
replacement and deletion.
Secondly, a key challenge involves providing models that perform well enough
on metrics such as AUC and recall, such that they are clinically reliable to the
perception of clinicians. Indeed, the use of predictive models in clinical practice
imposes a loss of autonomy on a clinician which can be perceived as a treat if
the results of such models do not demonstrate a direct benefit and often devi-
ate from a clinician’s expectations. To combat a perceived threat to autonomy,
more interpretable models can be chosen, such as decision trees, that are more
descriptive in explaining predictions in real world logic. However, such descrip-
tive models may not preform as well as black box models such as random forests
which possess poor interpretability. This trade-off between medical interpretabil-
ity and performance thus presents a challenge which can perhaps best be resolved
through questioning medical professionals and experimenting with the compli-
ance of systems in real world settings. On another note, such predictive models
must demonstrate high performance in a clinical domain due the the high cost
involved related to patient outcomes. Although false negatives may result in
the overlooking of certain ADEs, such oversights are inevitable. In regards to
legal and ethical accountability, final prescriptive decisions must be left to the
discretion of medical experts to correct for such errors.
Finally, it is an ongoing challenge to deal with the ever changing health care
system, which consistently encounters a high velocity of novel relevant data such
as medications and treatments. Prescriptive models for use in clinical practice
should ideally be constantly updated and built on real-time data as a means of
early detection for a variety of medical situations such as ADEs. Although such
real-time systems provide a clear means towards revolutionizing health care,
various challenges are faced such as possessing data sets at a necessary quality,
and with ensuring that updated models maintain the required validity for use in
clinical practice.
5 Conclusions
We have presented an overview of recent and ongoing research on learning from
EHRs and AHRs. Our review focused on Swedish health registries and con-
centrated around ADE understanding and detection, as well as modeling and
understanding the effectiveness of treatment for heart failure patients. More
concretely, we presented our recent work on detecting and understanding ADEs,
with focus on predictive modeling techniques, methods for mining dispropor-
tional patterns, and finally we present the ADE explorer, a tool for studying
ADEs from EHRs. in addition, we presented ongoing work on understanding
the effectiveness of treatment of heart failure from AHRs, with emphasis on
understanding the reasons behind the large variation of the usage rate of basic
treatment by 50 hospitals in Stockholm County. Finally, we discussed directions
for future research on our current projects involving EHRs and AHRs.
8
Jonathan Rebane et al.
5. CONCLUSIONS
Acknowledgments
This work was partly supported by the VR-2016-03372 Swedish Research Council
Starting Grant and by the Stockholm County Council.
References
1. Almenoff, J., Pattishall, E., Gibbs, T., DuMouchel, W., Evans, S., Yuen, N.: Novel
statistical tools for monitoring the safety of marketed drugs. Clinical Pharmacology
& Therapeutics 82(2), 157–166 (2007)
2. Asker, L., Boström, H., Karlsson, I., Papapetrou, P., Zhao, J.: Mining candidates
for adverse drug interactions in electronic patient records. In: Proceedings of the
7th International Conference on PErvasive Technologies Related to Assistive Envi-
ronments, PETRA 2014, Island of Rhodes, Greece, May 27 - 30, 2014. pp. 22:1–22:4
(2014), http://doi.acm.org/10.1145/2674396.2674420
3. Beijer, H., De Blaey, C.: Hospitalisations caused by adverse drug reactions (ADR):
a meta-analysis of observational studies. Pharmacy World and Science 24(2), 46–54
(2002)
4. Dalianis, H., Hassel, M., Henriksson, A., Skeppstedt, M.: Stockholm epr corpus:
A clinical database used to improve health care. In: Proceedings of the Fourth
Swedish Language Technology Conference (2009)
5. Hazell, L., Shakir, S.A.: Under-reporting of adverse drug reactions. Drug Safety
29(5), 385–396 (2006)
6. Henriksson, A., Zhao, J., Boström, H., Dalianis, H.: Modeling electronic health
records in ensembles of semantic spaces for adverse drug event detection. In: 2015
IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2015,
Washington, DC, USA, November 9-12, 2015. pp. 343–350 (2015), https://doi.
org/10.1109/BIBM.2015.7359705
7. Howard, R., Avery, A., Slavenburg, S., Royal, S., Pipe, G., Lucassen, P., Pirmo-
hamed, M.: Which drugs cause preventable admissions to hospital? A systematic
review. British journal of clinical pharmacology 63(2), 136–147 (2007)
8. Karlsson, I., Papapetrou, P., Asker, L., Boström, H., Persson, H.E.: Mining dis-
proportional itemsets for characterizing groups of heart failure patients from
administrative health records. In: Proceedings of the 10th International Con-
ference on PErvasive Technologies Related to Assistive Environments, PETRA
2017, Island of Rhodes, Greece, June 21-23, 2017. pp. 394–398 (2017), http:
//doi.acm.org/10.1145/3056540.3076177
9. Karlsson, I., Zhao, J., Asker, L., Boström, H.: Predicting adverse drug events by
analyzing electronic patient records. In: Proceedings of the Conference on Artificial
Intelligence in Medicine in Europe. pp. 125–129. Springer (2013)
10. Liu, X., Chen, H.: Azdrugminer: an information extraction system for mining
patient-reported adverse drug events in online patient forums. In: Proceedings of
the International Conference on Smart Health. pp. 134–150. Springer (2013)
11. Meystre, S.M., Savova, G.K., Kipper-Schuler, K.C., Hurdle, J.F.: Extracting in-
formation from textual documents in the electronic health record: a review of
recent research. Yearbook of medical informatics pp. 128–44 (Jan 2008), http:
//www.ncbi.nlm.nih.gov/pubmed/18660887
12. Nebeker, J.R., Barach, P., Samore, M.H.: Clarifying adverse drug events: a clin-
ician’s guide to terminology, documentation, and reporting. Annals of internal
medicine 140(10), 795–801 (2004)
9
Jonathan Rebane et al.
5. CONCLUSIONS
13. Pariente, A., Gregoire, F., Fourrier-Reglat, A., Haramburu, F., Moore, N.: Im-
pact of safety alerts on measures of disproportionality in spontaneous reporting
databases the notoriety bias. Drug safety 30(10), 891–898 (2007)
14. van Puijenbroek, E.P., Bate, A., Leufkens, H.G., Lindquist, M., Orre, R., Egberts,
A.C.: A comparison of measures of disproportionality for signal detection in spon-
taneous reporting systems for adverse drug reactions. Pharmacoepidemiology and
drug safety 11(1), 3–10 (2002)
15. Schneeweiss, S., Hasford, J., Göttler, M., Hoffmann, A., Riethling, A.K., Avorn,
J.: Admissions caused by adverse drug events to internal medicine and emergency
departments in hospitals: a longitudinal population-based study. European journal
of clinical pharmacology 58(4), 285–291 (2002)
16. Socialstyrelsen: Nationella riktlinjer – Målnivåer, Hjärtsjuk-vård (2015), artikel-
nummer 2015-10-3
17. Socialstyrelsen: Nationella riktlinjer – Utvärdering, Hjärtsjukvård (2015), http:
//www.socialstyrelsen.se
18. Socialstyrelsen: Nationella riktlinjer för hjärtsjukvård (2015), http://www.
socialstyrelsen.se
19. Suzuki, A., Andrade, R.J., Bjornsson, E., Lucena, M.I., Lee, W.M., Yuen, N.A.,
Hunt, C.M., Freston, J.W.: Drugs associated with hepatotoxicity and their report-
ing frequency of liver adverse events in VigiBaseTM . Drug safety 33(6), 503–522
(2010)
20. Velupillai, S., Skeppstedt, M., Kvist, M., Mowery, D.L., Chapman, B.E., Dalianis,
H., Chapman, W.W.: Cue-based assertion classification for swedish clinical text
- developing a lexicon for pycontextswe. Artificial Intelligence in Medicine 61(3),
137–144 (2014), https://doi.org/10.1016/j.artmed.2014.01.001
21. Wester, K., Jönsson, A.K., Spigset, O., Druid, H., Hägg, S.: Incidence of fatal
adverse drug reactions: a population based study. British journal of clinical phar-
macology 65(4), 573–579 (2008)
22. Zhao, J., Henriksson, A., Asker, L., Boström, H.: Detecting adverse drug events
with multiple representations of clinical measurements. In: 2014 IEEE Interna-
tional Conference on Bioinformatics and Biomedicine, BIBM 2014, Belfast, United
Kingdom, November 2-5, 2014. pp. 536–543 (2014), https://doi.org/10.1109/
BIBM.2014.6999216
10