=Paper=
{{Paper
|id=Vol-2142/paper2
|storemode=property
|title=Case-base maintenance of a personalized insulin dose recommender system for Type 1 Diabetes Mellitus
|pdfUrl=https://ceur-ws.org/Vol-2142/paper2.pdf
|volume=Vol-2142
|authors=Ferran Torrent-Fontbona,Joaquim Massana,Beatriz Lopez
|dblpUrl=https://dblp.org/rec/conf/ijcai/Torrent-Fontbona18
}}
==Case-base maintenance of a personalized insulin dose recommender system for Type 1 Diabetes Mellitus==
https://ceur-ws.org/Vol-2142/paper2.pdf
Case-base maintenance of a personalised bolus
insulin recommender system for Type 1
Diabetes Mellitus
Ferran Torrent-Fontbona, Joaquim Massana, and Beatriz López
Universitat de Girona, Polytechnical School, Building EPS-4,
Campus Montilivi, Girona, Catalunya
ferran.torrent,joaquim.massana,beatriz.lopez@udg.edu
http://exit.udg.edu
Abstract. With the goal of aiding people with Type 1 Diabetes Mel-
litus (T1DM), some mobile applications are being developed based on
artificial intelligence techniques. Some of these applications are based on
case-based reasoning methodologies due to the advantage regarding a
personal and adapted recommendation. However, the quantity and qual-
ity of the cases in the CBR system is crucial for the system outcome.
Most of the case-base maintenance methods developed are designed for
CBR systems which provide a nominal recommendation. However, rec-
ommending a bolus dose involves a numeric recommendation. Therefore,
this paper presents a new maintenance approach for an insulin recom-
mender system based on CBR. The resulting insulin recommender sys-
tem is tested using the UVA/PADOVA T1DM simulator and the results
show that the proposed approach is capable of making the case-base
more efficient, i.e. the accuracy of the recommendations is maintained or
even enhanced while the size of the case-base is reduced.
1 Introduction
The use of systems to continuously monitor blood glucose levels and the
increased computation power of mobile devices such as smart-phones has
led to the proliferation of applications, based on artificial intelligence,
with the aim of aiding people with T1DM. Mobile applications enable
the connectivity with sensors to measure and record the glucose level,
physical activity, quality of sleep, etc.
In this context, Case-Based Reasoning (CBR) [10] has been proved as a
useful methodology to develop adaptive and personalised insulin recom-
mender systems [8, 9, 17, 18] because it is capable of optimising insulin
dosage using past experiences.
The performance of a CBR system depends on the experiences or cases
stored in the case-base. Moreover, in an insulin recommender system,
the contents of the case-base should be maintained in order to capture
the persons physiological changes evolution, and provide adapted recom-
mendations over time. All insulin recommender systems based on CBR
propose to use a simple technique to maintain the quality of the case-base
2 F. Torrent-Fontbona et al.
and they, mainly, rely on a small set of attributes to keep the case-base
small and efficient [13,14,17]. However, the metabolism of carbohydrates,
glucose and insulin depends on many factors (e.g. stress, physical activity,
time of day, ambient temperature, etc.) and such simplistic approaches
may hide. Therefore, applications which consider more attributes are
needed, but if the number of attributes grows, so does the combinatorial.
In this situation, current maintenance approaches of CBR insulin recom-
mender systems fail in keeping the case-base efficient. Thus, a case-base
editing techniques for CBR insulin recommender systems are needed in
order to keep the case-base efficient even with a big number of attributes,
and to follow possible changes in the users physiology (problem known
as concept drift [19]).
This paper proposes a maintenance methodology that extends the method-
ology of PepperRec, [17], which is a CBR insulin recommender system.
The proposed methodology is inspired in the maintenance methodology
proposed in [5] which consists of three steps: retain, review and restore.
Most case-base editing techniques are proposed for CBR systems which
provide a nominal recommendation. Nevertheless, PepperRec provides
a numeric recommendation. Thus, this paper presents a new case-base
editing methodology for a CBR system which provides a numeric recom-
mendation.
The proposed methodology is finally tested with the UVA/PADOVA
T1DM simulator proving that it is capable of achieving a more efficient
case-base than PepperRec, and even enhancing the accuracy of the rec-
ommendations.
2 Background
This sections briefly explains CBR and the insulin recommender system
called PepperRec, which are necessary to follow this paper.
2.1 Case-Based Reasoning
CBR is a lazy learning technique that uses past experiences in order to
search a solution for a new problem. The basic CBR methodology was
described in [1] using 4 steps. First, given a query problem, situation or
case, the retrieve step searches similar past experiences from the case-
base. Second, the reuse step adapts the solutions of the retrieved cases
to the query case. Third, the revise step analyses the outcome of the
proposed solution and corrects it if necessary. Fourth, the retain step
decides about to store the query case or not according to some strat-
egy. In so doing, more recent approaches like [5] propose to unfold the
CBR methodology into maintenance and application, moving the retain
step into the maintenance part, and complementing it with review and
restore steps, as depicted in Fig.1. This new approach highlights the
importance of the quality and size of the case-base regarding the CBR
system performance.
CBR systems can be divided into classification and regression approaches.
CBR classifiers aim to provide a nominal solution, e.g. binary. These
Case-base maintenance of a bolus recommender system 3
INITIALIZATION
RESTORE RETRIEVE
REVIEW CASE-BASE REUSE
RETAIN REVISE
MAINTENANCE APPLICATION
Fig. 1. CBR cycle extended with a maintenance phase.
approaches are the most common ones. On the other hand, regression
approaches aim to provide a numeric solution, e.g. a real number. Both
types can follow the retrieve-reuse-revise-retain methodology of CBR,
but the techniques implementing the steps may be different.
2.2 Pepper insulin recommender
The work presented in this paper is based on the Pepper recommender
system proposed in [17], which follows a CBR methodology. The system
takes advantage of mobile technology to gather information about dif-
ferent sensors which sends information to the mobile through bluetooth
low energy (physical activity band and continuous glucose monitor).
The goal of the system is to provide personalised bolus insulin recom-
mendations for subjects with T1DM. Cases consist of the attributes that
characterise and contextualise the ingest (case description) and the so-
lution. Attributes are the following: time of the day, amount of carbohy-
drates of the meal (g), previous physical activity (quantified in a four-
level graded scale) and planned physical activity during the postprandial
(in the same scale). The solution consists of the Insulin to Carbohydrates
Ratio (ICR) that enables the computation of the insulin dose (bolus).
The CBR system automatically revises the proposed solutions analysing
the postprandial blood glucose. In particular, the theoretical optimal
bolus is calculated using the minimum postprandial blood glucose. Using
this optimal bolus, the ICR is further corrected according to the clinical
knowledge as reported in [9, 17].
Finally, the retain step is executed and it consists of storing the new case,
but check if there is an equal case (or similar enough) in the case-base
independently of the solution. If this is the case, the old case is removed.
No other maintenance method was developed. Thus, this paper focuses
on the full maintenance procedure of such system, including the review
and restore steps.
4 F. Torrent-Fontbona et al.
3 Related work
CBR systems rely on the case-base to provide accurate solutions. There-
fore, the case-base is expected to efficiently describe the problem space.
Case-base editing techniques are responsible of avoiding case-bases to
continuously grow in size and remove cases that may be redundant or
not necessary.
However, the problem space can evolve and change throughout time.
In such situations, old cases stored in the case-base may become less
representative than new cases. This problem is called concept drift and
there are some works in the literature that tackle this problem.
The Instance-Based learning Algorithm3 (IB3) [2] was one of the first
attempts to handle the concept drift monitoring of the cases accuracy
and the retrieval frequency. In [15], the Locally Weighted Forgetting
(LWF) algorithm was proposed to reduce the weights of the k-nearest
neighbours (k-NN) of a new case, so a case is discarded if its weight falls
below a threshold. In [16], Salganicoff achieved suitable results in time-
varying and static tasks with a method called Prediction Error Context
Switching (PECS). With the aim of controlling in an autonomous manner
the size and the composition of the case-base, Beringer and Hllermeier
[3] presented an Instance-Based Learning on Data Streams (IBL-DS)
algorithm. In [7] Delany et al. Proposed a two-level learning technique
with the aim of solving the concept drift issues.
Recently, the authors in [11] proposed a case-base editing methodology
to keep the case-base of a CBR binary classifier as small as possible but
also capable of following a concept drift. The methodology consists of
applying a case-base reduction technique, named Conservative Redun-
dancy Reduction (CRR), but also, monitoring class instances variability
to detect changes in the majority class in relevant regions of the solu-
tion space. Then, when a change is detected, old instances are removed
(forgotten) because it is assumed that there is a concept drift.
Despite this research, there is still need of maintenance algorithms ca-
pable of dealing with numerical solutions, in order to dispose of reduced
and compact case-bases even with the presence of concept drift.
4 Pepper recommender maintenance
The maintenance approach proposed in this paper consists of the three
methods: recent strategy, time analysis and coverage and, finally, reacha-
bility analysis, which are applied in the retain, review and restore steps of
the CBR methodology as described below. The retain step (recent strat-
egy) uses the same methodology proposed in [17], but the time analysis
and coverage and reachability analysis are new. Therefore, this paper
extends the methodology proposed in [17] with the time analysis and
coverage and reachability analysis.
The methodology proposed in [17] has been proved effective when cases
are described with a few attributes. But the aim of this paper is to
provide a complete maintenance methodology capable of dealing with
cases described by many attributes.
Case-base maintenance of a bolus recommender system 5
4.1 Retain: Recent strategy
As proposed in [17], the retain step consists of before storing a new case,
check if there is an equal case in the case-base regarding the problem
description. If an equal case to the new one is found, the old case is
removed from the case-base. This approach assumes that a pair of cases
with equal attributes but different ICR are due to a concept drift. There-
fore, the old case should be removed. On the other hand, if equal cases
have equal solutions, they are redundant and there is no need to keep
both.
4.2 Review and Restore: Time analysis
If the combinatorial of the attributes is big, and the strategy is limited
to the condition of finding identical case description, the capacity of
following the concept drift by the proposed retain is low.
Thus, we propose to statistically analyse the ICRs of the cases in the
case-base throughout time, and if there are significant differences in the
time-line, we assume that there is a concept drift. Specifically, we sort the
cases according to their timestamp (time when they were stored), and
the mean and standard deviation of the ICR of the cases is calculated
using a sliding window. When, significant differences are detected respect
the first window, the older cases are removed.
4.3 Review and Restore: Coverage and reachability
analysis
Redundancy of cases could happen because cases with equal solutions
are closely located in the problem space, i.e. the description of the cases
(attributes) and their solutions are equal or very similar. Metrics such
as the coverage or the reachability of the cases are then used to evaluate
how useful and redundant the cases are. The coverage of a target case
is defined as the set of cases that can be accurately solved by the target
case. On the other hand, the reachability of a target case is defined as
set of cases that can be used to accurately solve the target case.
Review results are then used to restore cases in the case-base, or remove
those considered as redundant.
In order to decide if a numeric solution like the ICR is valid to solve
another case, this paper proposes to convert the maximum accuracy of
insulin infusion (or minimum error) to a maximum allowed difference
between ICRs in order to be considered as equal. Thus, if the dose quan-
tification error in the insulin infusion system is half a bolus, then this
value is converted to a maximum difference between ICRs. Thus, it is
converted to the maximum error in terms of ICR.
Once the maximum difference between ICRs is calculated, reachability
and coverage of each case are calculated. Next, given the reachability and
the coverage of the cases, restore techniques such as CRR [6] or Iterative
Case Filtering (ICF) [4] can be applied.
The CRR algorithm uses the coverage to remove the redundant cases.
In particular, it sorts cases by descending order of coverage. Then, it
6 F. Torrent-Fontbona et al.
iteratively adds the cases in the new case-base, but when a case is added,
the cases of its coverage are removed from the cases-pending-to-add list.
Therefore, these cases are removed from the final case-base.
On the other hand, ICF calculates the reachability and coverage of all
cases and then removes those whose reachability is greater the coverage.
5 Results and discussion
Experimentation has been carried out using 11 virtual adults of the
UVA/PADOVA simulator [12]. These consist of 180 days and 20 rep-
etitions. The performance of the proposed methodology is evaluated in
terms of the portion of time the blood glucose of the subjects is in, below
or above the glycaemic target range, which has been set to [70,180] mg/dl
for all the virtual subjects. The proposed methodology is also evaluated
in terms of size of the case-base.
The performance of the proposed methodology is analysed using CRR or
ICF as case-base editing techniques, and it is compared with the method-
ology proposed in [17] and labelled as no review-restore. The attributes
of the cases are those specified in [17] (time of day, past and planned
activity and quantity of carbohydrates) plus eight random attributes:
– One binary attribute
– Five attributes with three nominal values
– Two attributes with four nominal values
Fig. 2 shows how the proposed method improves the results respect to
the absence of a maintenance step in terms of time in the glycaemic
target range. In particular, the proposed methodology with CRR signif-
icantly outperforms the method without a review-restore approach for
all subjects except subject 2 according to t-student tests. Subject 2 has
the highest blood glucose stability and this may be the cause for not
improving it, i.e. the achieved time in the target range already was very
good. On the other hand, the use of ICF instead of CRR achieves slightly
worse results, because it outperforms the method without review-restore
for subject 1, 3 and 5-8.
Regarding the time below and above the target range, Fig. 3 and 4
show that the proposed methodology achieves similar results than the
method without review-restore. T-student test confirm that the proposed
methodology using either CRR or ICF achieves significantly better re-
sults for some subjects but for other achieves results without significant
differences. This means that time below or above the target range is
maintained or improved, but never is worsened.
These aforementioned results imply that blood glucose is more stable
(has less surges or drops). Therefore, this reduces the risk of hypogly-
caemia and its consequent complications (clumsiness, trouble talking,
loss of consciousness, seizures, or death), and the risk of hyperglycaemia
and its long-term microvascular (retinopathy, nephropathy and neuropa-
thy) and macrovascular (coronary heart disease, stroke and peripheral
vascular disease) complications.
The proposed methodology is expected not only to maintain or even
improve the quality of the recommendations, but doing it with smaller
Case-base maintenance of a bolus recommender system 7
Fig. 2. Time in the glycaemic target range.
Fig. 3. Time above the glycaemic target range.
8 F. Torrent-Fontbona et al.
Fig. 4. Time below the glycaemic target range.
Fig. 5. Size of the case-base.
Case-base maintenance of a bolus recommender system 9
case-base. Fig. 5 shows the average and standard deviation of the size of
the case-bases for all the virtual subjects when using PepperRec (without
a review-restore phase) or the proposed methodology with ICR or CRR.
The results show that there is a clear reduction in the size of the case-base
using the proposed maintenance system.
Thus, the proposed methodology achieves more efficient case-bases, since
the CBR system provides slightly better recommendations but using
smaller case-bases. This is especially relevant because the system is less
computationally demanding.
6 Conclusions
Bolus insulin recommender systems based on case-based reasoning for
T1DM have been proven capable of providing accurate recommendations.
In order to be useful and accessible to people with diabetes, these systems
need to be implemented in mobile devices such as mobile phones. The
efficiency of case-based reasoning systems relies on the size and quality of
the case-base. As a consequence, this paper presents a methodology for
editing the case-base in order to keep it efficient, i.e. small and accurate,
and capable of dealing with mid- and long-term changes in the subject’s
physiology, problem known as concept drift.
The proposed method has been tested with 11 virtual adults using the
UVA/PADOVA simulator. The achieved results demonstrate that the
proposed method is capable of maintaining the case-base smaller than
other methods and the whole system is capable of providing more accu-
rate recommendations. Thus, the case-bases are smaller and the portion
of time the blood glucose of the subjects is inside the glycaemic target
range is slightly greater, which reduces the probability of hyper- and
hypoglycaemia.
This work is still not finished and needs more experimentation to support
these encouraging results. Moreover, it would be interesting to study
how to complement this work with techniques capable of learning the
relevance of the attributes.
Acknowledgments
This project has received funding from the European Union Horizon
2020 research and innovation programme under grant agreement No.
689810, www.pepper.eu.com/, PEPPER, and the grant of the University
of Girona 20162018 (MPCUdG2016). The work has been developed with
the support of the research group SITES awarded with distinction by
the Generalitat de Catalunya (SGR 20142016).
References
1. Agnar Aamodt and Enric Plaza. Case-based Reasoning: Founda-
tional Issues, Methodological Variations, and System Approaches.
AI Commun., 7(1):39–59, 1994.
10 F. Torrent-Fontbona et al.
2. David W Aha, Dennis Kibler, and Marc K Albert. Instance-based
learning algorithms. Machine learning, 6(1):37–66, 1991.
3. Jürgen Beringer and Eyke Hüllermeier. Efficient instance-based
learning on data streams. Intelligent Data Analysis, 11(6):627–650,
2007.
4. Henry Brighton and Chris Mellish. Advances in instance selection
for instance-based learning algorithms. Data mining and knowledge
discovery, 6(2):153–172, 2002.
5. Ramon Lopez De Mantaras, David McSherry, Derek Bridge, David
Leake, Barry Smyth, Susan Craw, Boi Faltings, Mary Lou Maher,
Michael T Cox, Kenneth Forbus, and Others. Retrieval, reuse, re-
vision and retention in case-based reasoning. The Knowledge Engi-
neering Review, 20(3):215–240, 2005.
6. Sarah Jane Delany and Pádraig Cunningham. An analysis of case-
base editing in a spam filtering system. In European Conference on
Case-Based Reasoning, pages 128–141. Springer, 2004.
7. Sarah Jane Delany, Pádraig Cunningham, Alexey Tsymbal, and Lor-
can Coyle. A case-based technique for tracking concept drift in spam
filtering. Knowledge-based systems, 18(4-5):187–195, 2005.
8. Pau Herrero, Jorge Bondia, Oloruntoba Adewuyi, Peter Pesl, Mo-
hamed El-Sharkawy, Monika Reddy, Chris Toumazou, Nick Oliver,
and Pantelis Georgiou. Enhancing automatic closed-loop glucose
control in type 1 diabetes with an adaptive meal bolus calculator in
silico evaluation under intra-day variability. Computer Methods and
Programs in Biomedicine, 146:125–131, jul 2017.
9. Pau Herrero, Peter Pesl, Jorge Bondia, Monika Reddy, Nick Oliver,
Pantelis Georgiou, and Christofer Toumazou. Method for automatic
adjustment of an insulin bolus calculator: In silico robustness evalu-
ation under intra-day variability. Computer Methods and Programs
in Biomedicine, 119(1):1–8, 2015.
10. Janet Kolodner. Case-based reasoning. Morgan Kaufmann, 2014.
11. Ning Lu, Jie Lu, Guangquan Zhang, and Ramon Lopez De Mantaras.
A concept drift-tolerant case-base editing technique. Artificial Intel-
ligence, 230:108–133, 2016.
12. Chiara Dalla Man, Francesco Micheletto, Dayu Lv, Marc Breton,
Boris Kovatchev, and Claudio Cobelli. The UVA/PADOVA Type 1
Diabetes Simulator: New Features. Journal of Diabetes Science and
Technology, 8(1):26–34, 2014.
13. Stewart Massie. Complexity Modelling for Case Knowledge Mainte-
nance in Case-Based Reasoning. PhD thesis, Robert Gordon Uni-
versity, 2006.
14. Peter Pesl, Pau Herrero, Monika Reddy, Nick Oliver, Desmond G
Johnston, Christofer Toumazou, and Pantelis Georgiou. Case-based
reasoning for insulin Bolus Advice: evaluation of case parameters in
a six-week pilot study. Journal of diabetes science and technology,
11(1):37–42, 2017.
15. Marcos Salganicoff. Density-adaptive learning and forgetting. In
Proceedings of the Tenth International Conference on Machine
Learning, volume 3, pages 276–283, 1993.
Case-base maintenance of a bolus recommender system 11
16. Marcos Salganicoff. Tolerating concept and sampling shift in lazy
learning using prediction error context switching. In Lazy learning,
pages 133–155. Springer, 1997.
17. Ferran Torrent-Fontbona and Beatriz Lopez. Personalised Adap-
tive CBR Bolus Recommender System for Type 1 Diabetes. IEEE
Journal of Biomedical and Health Informatics, 2018.
18. Ferran Torrent-Fontbona, Beatriz Lopez, and Alejandro Pozo-
alonso. A CBR-based bolus recommender system for type 1 diabetes.
In Proceedings of the 2nd International Workshop on Artificial In-
telligence for Diabetes, pages 9–14, Vienna, 2017.
19. Gerhard Widmer and Miroslav Kubat. Learning in the presence of
concept drift and hidden contexts. Machine learning, 23(1):69–101,
1996.