On an EAV Based Approach to Designing of Medical Data Model for - - PowerPoint PPT Presentation

▶

Oct 20, 2023 116 likes •310 views

Petrozavodsk State University Department of Computer Science Alexander Borodin, Yulia Zavyalova On an EAV Based Approach to Designing of Medical Data Model for Mobile HealthCare Service This research is financially supported by the Ministry of

SLIDE 1

Petrozavodsk State University Department of Computer Science

Alexander Borodin, Yulia Zavyalova

On an EAV Based Approach to Designing of Medical Data Model for Mobile HealthCare Service

This research is financially supported by the Ministry of Education and Science of the Russian Federation within project # 14.574.21.0060 (RFMEFI57414X0060) of Federal Target Program "Research and development on priority directions of scientific-technological complex of Russia for 2014–2020".

UBICOMM 2015 conference July 19–24, Nice, France

UBICOMM 2015 Alexander Borodin 1 / 19

SLIDE 2

World population ageing

UBICOMM 2015 Alexander Borodin 2 / 19

SLIDE 3

World population ageing (from UN report, 2013)

UBICOMM 2015 Alexander Borodin 3 / 19

SLIDE 4

Cardiovascular diseases

Number 1 cause of death globally (31% of all global deaths in 2012)1 Can be prevented by addressing behavioural risk factors (tobacco use, unhealthy diet, obesity, physical inactivity, etc.) Need early detection and management Contribution of CVDs to mortality in CIS (percents) Georgia 67 Ukraine 64 Azerbaijan 60 Russia 57 Moldova 56 Belorussia 53 Kazakhstan 50 Armenia 50 Kyrgyzstan 49 Tajikistan 39

1Source: WHO UBICOMM 2015 Alexander Borodin 4 / 19

SLIDE 5

Electrocardiogram morphology

R R P P Q Q S S T T

UBICOMM 2015 Alexander Borodin 5 / 19

SLIDE 6

Normal sinus rhythm and abnormalities

Normal sinus rhythm Sinus tachycardia Sinus bradycardia Sinoatrial block Atrial flutter Wolff-Parkinson-White syndrome

Source: Medical Training and Simulation LLC http://www.practicalclinicalskills.com

UBICOMM 2015 Alexander Borodin 6 / 19

SLIDE 7

Rhythm anomalies detection

Электрокардиограмма

Морфологический анализ Предобработка Классификация аритмий

Рекоммендации Неотложный вызов

UBICOMM 2015 Alexander Borodin 7 / 19

SLIDE 8

CardiaCare application

UBICOMM 2015 Alexander Borodin 8 / 19

SLIDE 9

A real example...

UBICOMM 2015 Alexander Borodin 9 / 19

SLIDE 10

Connect to other sensors?

UBICOMM 2015 Alexander Borodin 10 / 19

SLIDE 11

Continuous health monitoring system operation

ECG SpO2 Data storage and processing Physician workplaces Environment sensors (temperature, smoke, etc.) Personal health data Emergency services Patient-centered wireless sensor network Smartphone Environment conditions Emergency help Prescriptions Alarms Prescriptions Alarms Sensor data UBICOMM 2015 Alexander Borodin 11 / 19

SLIDE 12

Smart service on top of monitoring service

UBICOMM 2015 Alexander Borodin 12 / 19

SLIDE 13

Smart service on top of monitoring service (cont.)

UBICOMM 2015 Alexander Borodin 13 / 19

SLIDE 14

EAV model and decomposition

Mapping EID AID Value

1 1 Yes 2 2 80 bpm

Attribute AID

Headache 1 Heart rate 2 Cough 3 1 3 Yes

Entity Attribute Value

John Doe @ 2014-09-01T09:30 Headache Yes Jane Doe @ 2014-09-12T12:30 Heart rate 80 bpm John Doe @ 2014-09-01T09:30 Cough Yes

Decomposition Name

John Doe Jane Doe

PID

1 2

PID Timestamp

1 2014-09-01T09:30 2 2014-09-12T12:30

EID

1 2 3 1 2014-09-12T12:30

UBICOMM 2015 Alexander Borodin 14 / 19

SLIDE 15

Storing the attribute values

VID ValueBool

1 Yes 2 NULL 3 Yes

EID

1 2 1

AID

1 2 3

ValueStr

NULL NULL NULL

ValueInt

NULL 80 NULL

VID Value

1 Yes 3 Yes

1 2

VID

1 2 3

EID

1 2 1

AID

1 2 3

VID Value

2 80

UBICOMM 2015 Alexander Borodin 15 / 19

SLIDE 16

Utilization of the EAV approach in CardiaCare Service

profiles of patients may be extended with arbitrary fields from contact details to billing information; clinical trials may be extended with arbitrary parameters and new types of trials may be incorporated as well; forms to be filled manually by the doctor.

UBICOMM 2015 Alexander Borodin 16 / 19

SLIDE 17

Hierarchical dicationaries in CardiaCare Service

dictionary

dictionary_id dictionary_title dictionary_sortorder

dictionary_item

dictionary_item_id dictionary_item_value dictionary_item_sortkey dictionary_id

dictionary_relation

dictionary_relation_id dictionary_parent_id dictionary_child_id dictionary_id

UBICOMM 2015 Alexander Borodin 17 / 19

SLIDE 18

Attribute metadata in CardiaCare Service

attribute

attribute_id attribute_title attribute_description entity_id attribute_sortkey attribute_parent_id dictionary_id

attribute_constraint

attribute_constraint_id attribute_constraint_type attribute_constraint_value attribute_id attribute_group_id

attribute_group

attribute_group_id attribute_group_name attribute_group_parent_id

attribute_presentation

attribute_presentation_id attribute_presentation_name attribute_presentation_value attribute_id

UBICOMM 2015 Alexander Borodin 18 / 19

SLIDE 19

Conclusion

Data model for CardiaCare service was conducted based on open schema design principles. This approach allows to extend a set of supported medical measurements without the need of making changes to the database schema. The schema was designed taking into account a possibility of automatic user and interface construction based on metadata.

UBICOMM 2015 Alexander Borodin 19 / 19