This website is certified by Health On the Net Foundation. Click to verify. This site complies with the HONcode standard for trust worthy health information:
verify here.

Search only trustworthy HONcode health websites:


REACTION is affilliated with these programs and organisations:

REACTION is delivering better and more efficient healthcare services in Europe, thus supporting the Commissions activities in ICT for Health: eHealth.

The REACTION platform allows for the creation of inclusive applications with accessibility for all. The project supports the Commissions campaign: eInclusion - be part of it!

Pattern management in diabetes care

Self-monitoring of blood glucose can provide large amounts of data which might be hard to interpret both for patients and health professionals. Automated data processing can add valuable information to the interpretation of the data. Pattern management is a systematic approach to help patients and health care providers to identify patterns in blood glucose readings to determine whether changes are needed to optimize their glucose control. This demo presents a prototype which implements the pattern management approach.

Enter a patient id, a date interval of at least two weeks. Select if you wish to see relevant advice to a patient or to a health professional. Then click on the “Show patterns” button to see the list of identified patterns.

Some example input data you can use:
Patient ID: 2, date interval: 2009.10.10 - 2010.01.13
Patient ID: 29, date interval: 2010.04.29 - 2010.12.16
Patient ID: 58, date interval: 2010.08.22 - 2010.09.20
Patient ID: 61, date interval: 2011.05.16 - 2011.06.17

The prototype shows the measured blood glucose values in the given period as a colour-coded table. Rows show the time of the day (morning, noon, afternoon, evening, night); the columns are the individual days. Gray means that no measurement was taken in a given time slot, yellow means low, green means normal and red means high blood glucose level. The tooltip of a cell shows the exact time of the measurement. If multiple measurements were performed in a time slot, only the first value is presented, and an * is added to the cell.

Below the table a list of identified patterns is show. Patterns may include:
  • The number of hypoglycaemic or hyperglycaemic events exceeding a threshold in a 7-day period.
  • Common hypoglycaemia or hyperglycaemia events at a specific time of day.
  • Dawn phenomenon or Somogyi effect
  • Too high excursions between two consecutive meal times.
If the option for showing advice is set, a brief text explaining the possible causes and recommended actions for each type of pattern is displayed.

A more detailed description of the demo including the full list of patterns can be downloaded from here.

The prototype was developed by:
Applied Logic Laboratory
Hankoczy u. 7.
H-1022 Budapest
Contact: info@all.hu