m-Medicine

1
m-Medicine

• Jayanta Mukhopadhyay
• Dept. of Computer Science and Engg.

2
Collaborators..

• A.K. Majumdar
• Suman Kundu
• Soubhik Paul
• Ashish Shubham

3

• Desktop-based e-Healthcare solutions are not
  adequate due to the dynamic nature of hospital
  environments

• Popularity of accessing medical record using
  handheld devices at the point of care.
• Portable.
• Mobile Access of Information.

4
In a Hospital Environment

• Doctors are always on the move.
• Regular Exceptional Events.
• Continual follow-up process.
• Heterogeneous Medical Information.

5
Requirements

• Anywhere, anytime availability of medical records
• Accessibility of EMR through various equipments
• Static (PC)
• Mobile (Laptop, PDA, Cell Phone)
• Secure information access
• Reminder services for doctors and patients
• Automated calls to doctors during emergency
• Interactive discussion with other doctors and
  staff with patients data.

6
Some Applications

• Medical references.
• Read Journal Clinical Trial.
• Medical (Dose) Calculator.
• Electronic medical record access.
• Emergency Messaging.

7
Some applications on mobile phones

• Mobile Camera phones in Digital Soft Tissue
  injuries
• Tele-Consultation for Orthopedic patients using
  MMS/Mobile.
• 3G Mobile links for consultation between a moving
  ambulance and the hospital base station
• Mobile phone ready EHR System

8
Applications under consideration

• Integration with EHR systems.
• Emergency messaging.
• Online video and data conferencing.

9
Work Flow in Hospital Environment
10
Integration with mobile based access system

• Integration of Indoor Patient Management System
• PDA based Wireless Medical Information Access
  System
• Wireless Medical Information Access Server.
• Client Tools for PDA
• SMS based Emergency Messaging System

11
Telemedik 2005

• Manages Patients Electronic Medical Records in a
  backend RDBMS
• Connects multiple hospitals in West Bengal and
  Tripura for medical information communication
• Online Video and Data Conferencing

12
Extending Telemedik 2005 for indoor patient
management

• Integration of Indoor Patient Management System
• PDA based Wireless Medical Information Access
  System
• Wireless Medical Information Access Server.
• Client Tools for PDA
• SMS based Emergency Messaging System

13
System Architecture
Clients Layer
Personal Computer
PDA
Mobile Phone
Indoor Patient Management (IPM) system
Telemedik system
Wireless Medical Information Access system
Emergency Messaging system
Application Layer
Telemedik database
WMIAS database
IPM database
EMS database
Database Layer
14
System Architecture
15
imediK- A web-based system

• iMedik supports all the features of existing
  TelemdiK installations.
• Separate module handling presentation of the
  content.

16
(No Transcript)
17
iMedik Test Environments

• Installed at IIT Kharagpur and is accessible via
  URL http//tmportal.iitkgp.ernet.in
• Deployed at CMCH, Kolkata
• iMedik is accessible through Internet.
• Access to WBSWAN.
• WMIAS server is installed for handheld devices.

18
Limitation of handheld devices

• Small screen area.
• Hard to view complete pages.
• Increases scrolling and searching complexity.
• Increases cognitive load.
• CPU Speed.
• Limited Memory.
• Display resolution .
• Input Device (Stylus).
• Bandwidth.

19
Solutions offered

• Client Server based approach
• Data filtering
• Partitioned image display for large images
• Buffer management

20
Data browsing and logging through

• Patient data browsing
• a. Text data
• b. Image data
• Prescribing drugs and advice

21
Routine Blood test and grouping form as displayed
on PC
22
Routine Blood test and grouping Form as
displayed on PDA
23
Scrolling Required to view Telemedik forms on
PDA Designed for PC.
Avg. Max. Min.
Vertical Scrolling. 4 times 7 times 2 times
Horizontal Scrolling. 3 times 4 times 2 times
24
X-RAY Data Display
High Scrolling Required
25
Our Approach

• Creation of Medical Knowledge Base.
• Prioritization of keywords.
• Term Frequency Calculation
• Most Frequently Suggested Test
• Text fragmentation algorithm .
• Adaptive partitioning for display of large
  images.
• Image Caching Mechanism.

26
WMIAS (Wireless Media Information Access Server )

• Patient data browsing.
• Text Data.
• Context Sensitive Priority Based Text
  Fragmentation Algorithm
• Image Data.
• Fixed Partition Image Navigation Algorithm
• Prescribing drugs and advice.
• Recording of Patients Routine Checkup.

27
MEDICAL KNOWLEDGE BASE

• Medical terminology of diseases, symptoms, test
  reports.
• Normal range of each test report.
• Abbreviations and Acronyms of medical
  terminologies.
• Critical key word (Ex High, Low, Abnormal etc.).
• Prioritization of Keywords.

28
Term Frequency Calculation

• Search engine Google
• Input Document sets searched with Key words
  (Disease Name, Synonym, Abbreviation, )
  (Cardiology, Heart Disease, Cardiac Surgery,
  Cardiomyopathy,.).
• Priority Value The frequency of occurrence of a
  keyword on the document set.

29
Most Frequently Suggested Tests

• Input Data from database.
• Priority Value proportional to the percentage of
  patients of a particular disease type are asked
  to perform that particular test.

30
PRIORITIZATION OF KEY WORDS

• A priority vector table maintains the
  significance of each keyword in test reports in
  context of a particular disease.
• Priority vector table is dynamic.

Lipid Profile
Cardiology Dermatology
Total Cholesterol 100 77
HDL 89 62
LDL 81 100
Triglycerides 40 52
VLDL 29 56
31
Context Sensitive Priority Based Text
Fragmentation Algorithm

• Present data in order of there relevance for
  diagnosis and treatment.
• Context is the patient disease type, signs and
  symptoms.
• Relevance is assigned in terms of priority value.
• Relevance of a test report gets changed with the
  change of context.
• A fragment is a set of fields, which are having
  very close relevance for diagnosis and treatment.

32
Context Sensitive Priority Based Text
Fragmentation Algorithm
Step1 Orders the elements in the test report
with respect to their priority value in the
priority vector table.
Step2 If the form is of type investigation
report then execute step3 else (while the form
is of type systemic or physical examination)
execute step5.
Step3 Orders all the elements in the form with
respect to there percentage of deviation from
normal range.
Step4 If the priority value of a particular
field is less than a threshold value and the
value of the field is out of normal range it gets
highest display priority.
33
Continued.
Step5 Search the presence of critical
keyword. Field having Critical keyword gets
higher priority.
Step6 Replace terms with standard abbreviations
and acronyms.
Step7 Use color coding to distinguish the
normal and abnormal fields.
Step8 Data is fragmented according to the
screen resolution of PDA.

34
Context Sensitive Priority Based Text
Fragmentation
Abnormal Data
Fragment 1
Fragment 2
35
Dynamic Partition Image Navigation
36
Visualization Applications for PDA.

• Viewing, Zooming and marking of image.
• Skin Patch Viewing Application.
• ECG Viewing Application.
• Display of graphs and charts.

37
Region of Interest
38
Adaptive partitioning of large images
Region of interest
Image Viewer.
39
Image Viewer.
40
ECG Viewer.
Skin Patch.
41
Caching Mechanism

• Multiple copies of the latest requested image is
  cached in the the PDA memory.
• It is found that, for 30 of the requests, the
  image is retrieved from local cache.
• Image have to be zoomed in and out to reach
  optimum resolution for display.
• PDA supports single window display.

42
Performance with Caching
It is found that average. image access time
reduces to 24 with the use of caching scheme
suggested.
43
iMediK for mobile devices

• The System needs to fragment the data
• Fragmentation of frame based display
• Fragment of summary page
• Fragmentation of reports

44
System Architecture
Desktop Client
Page Request
Page Response
Web Proxy Layer
Mobile Client
Page Request
Page Response
Firewall

• A secure four tier architecture - Web proxy
  layer, Presentation Layer, Business Logic layer
  and Database layer.
• Protects not only the medical database but also
  the application components.

Presentation Layer
Business Logic Layer
Database Layer
Refer Security Analysis and Implementation of
Web-based Tele-medicine Services with a Four-tier
Architecture By Amiya K. Maji, Arpita Mukhoty,
Arun K Majumdar, Jayanta Mukhopadhyay, Shamik
Sural, Soubhik Paul, Bandana Majumdar At CPMP
2008, Finland
45
Fragmentation of frame based display

• Desktop- multi-frame based interface
• Small Display-Multi-frame based approach is not
  suitable
• Each frame represents as a single page
• To access data user needs to navigate from one
  page to another

46
(No Transcript)
47
Fragmentation of reports

• Patients reports contain many fields and data.
• System divides the reports in small fragments
  depending on two parameters
• No. of characters per row
• No. of rows
• Uses HTTP header for device specific information.
• Use abbreviations guided by a dictionary.

48
Fragmentation- An example
49
Contd..
Abbreviation for the word blood
Blood Sugar Test
50
Prescription Writing Form
51
Multimedia data in PDA

• Viewing Marking of image
• Profile Marking application
• ECG Viewer application
• Display of Graphs and Charts

52
Skin Patch Viewer
53
ECG Data Display
54
Graphs Charts
Family History Tree
Growth Chart
55
SMS based Semiautomatic Emergency Messaging System
56
Problem Description

• Emergency event create alert that should be
  delivered to
• appropriate person at appropriate time.
• Efficient routing and monitoring of alerts are
  key to quality
• and cost effective healthcare service.
• Communication of vital signs and crucial medical
  information in the
• alert message.

57
Key Issues.

• According to the requirement of medical event
  various alert types are generated.
• Alert parameters that qualifies the person to
  receive an alert.
• Availability of medical staff and their reachable
  device.
• Efficient routing , monitoring and logging of
  Message.
• Automate message generation process.
• Large area of network coverage.

58
SMS based Approach

• SMS based system.
• Anywhere and anytime availability.

• Classification Messages.
• Creation of medical knowledge base to transmit
  selective
• medical record in the limited space of SMS.
• Creation of appropriate medical groups for
  handling different
• emergency case.

59
System Architecture
Message definition library
Event Manager
Message Formatter
iMedik Database
Emergency Message generator
Scheduled Message generator
Message Communicator
Reminder message generator
User task manager
Message manager
Regular message generator
Message queue
Mobile Devices
60
Message Classification
61
Message Definition
Struct message id unique identification
number U level of urgency. R response needed
or not? T deadline. Bd message body.
id message_ type, message_generation_time, date
and serial_no.
62
Message Definition
Alert Message (ALR) Struct L ward_name room_no
bed_no Reminder Message (REM) (id, Bd).
Regular Message (REG) Referred Patient
Message (REF) Acknowledgement (ACK)
63
Medical Knowledge Base

• Send Some critical medical record in the message
  .
• Rule Base Development.
• Select medical records based on patients signs,
  symptoms and
• disease type.

R1 if ( case emergency) then (emr respiratory
rate, blood pressure, pulse rate) R2 if ( case
emergency burn) then (emr of burn, location of
burn) R3 if ( type surgical ) then ( emr
haemoglobin count )
64
Message Format

• Create Message.
• Abbreviation Dictionary.
• Medical Terminologies (BP Blood Pressure
• RBC Count, ESR etc.)
• English
• SMS (You U, To 2, Urgent Ur etc.)

References 1. http//www.treasuremytext.com 2.
http//www.ejalgaon.com 3. http//www.funsms.com
65
Message Format Continued..

• Highlighting abnormal data.
• Color Coding.
• Case Convention.
• UPPER CASE HIGH PRIORITY.
• MiXeD CaSe MeDiUm PrIoRiTy.
• lowercase low priority.

Examples ALR12320102 //High priority alert
AlR12320102 //Medium priority alert
alr12320102 //Low priority alert
66
User and Task Management
Profile ( uid, D, N, Si ) //N Phone Number,
S Duty Schedule. Event ( eid, D ) Trauma
patient management, Surgery, Stroke Myocardial
Infraction, Pre-operative care, Post-operative
care Task ( tid, D ) Example Draw Blood,
Administer Oxygen, perform CT Scan, Immobilize
patient etc. Duty ( tid, uid ) Schedule
( eid, tid, Ri )
E R Diagram
67
Emergency patient management

• Different Emergencies.
• Accidental Emergency
• Myocardial Infarction
• Stroke
• Burn Injury
• Pediatric Emergency
• Gynecological Emergency
• Etc

• Accidental Emergency
• Myocardial Infarction
• Stroke

68
Accidental Emergency Management
Emergency Location
Pre Hospital Care
Ambulance
Hospital
Primary emergency group
Secondary emergency group
Emergency Group
69
Emergency Patient Management Groups
Secondary Group
Primary Group
Emergency Case
Blood Bank. Radiology Group. Neurology Group.
Trauma Specialist. Ventilation Group. Respiratory
Group. Circulation Group.
Trauma.
Radiology Group.
Emergency Group. Cardiologist. Respiratory
Group. Circulation Group.
Myocardial Infarction.
Radiology Group.
Emergency Group. Neurologist. Respiratory
Group. Circulation Group.
Cerebral Stroke.
70
Approach to unconscious patient with external
evidence of trauma.
a1 Unconscious Patient
a2 Administer Oxygen (5-10)
a3 Draw blood (5-10)
a4 Emergent Head CT (30)
Reference Ferri's Clinical Advisor 2004 Instant
Diagnosis and Treatment 6th edition (June 2003)
By Fred F. Ferri By Mosby
71
Scheduling of long-term follow up care
Routine preoperative testing.
Pre-surgical visit
Move patient to OT
Anesthesia
Post anesthesia care unit.
Surgery
Reference http//omni.ac.uk The UKs gateway to
high quality Internet resources in health and
medicine. http//omni.ac.uk/browse/mesh/D011300.h
tml
72
Example Alert
Preoperational alerts. (aid1, Patient X,
radiology exam, Central Lab officer, Normal,
NA, Two days before surgery ) Operation
Alert. (aid1, Patient X, Prepare Patient, Ward
Manager, Urgent, t h) (aid1, Patient X,
Anesthesia, Anesthesiologist, Urgent, t1
h) (aid1, Patient X, Surgery, Surgeon, Urgent,
t1.2 h) (aid1, Patient X, Post operative care,
Post operative care officer, t3 h)
73
Message Communication algorithm
Input (Emergency case type) Begin
Step1. Create the content of the emergency
message from the message definition system.
Reduce the text length by suitable abbreviation
and acronyms. Fragment the message if the
message length exceeds the size limitation of
SMS.
Step2. Search the primary group of a particular
emergency case.
Step3. Search the work schedule of the primary
group and create a group of relatively free
doctors.
74
Message Communication algorithm
Continued
Step4. Produce the master group to the operator
and ask for moderating the final group.
Step5. After getting confirmation from the
operator send message to the group.
End
75
Acknowledgement handling.
Input (Message_id, User_id) Begin If a negative
acknowledgement is received. Search another
doctor of same specialization that of the user_id
of the unavailable doctor. //Modify the previous
message content. U High //Increase the level of
urgency. T (dead line) T elapsed time Send
message. End if End
76
Implementation
Mobile Phone
GSM Modem
Emergency Messaging System
Base transceiver station
Clinical Database
77
Example Emergency Message
Emergency message for attending a patient
admitted in hospital.
Emergency Message for attending a patient of
accidental emergency.
78
Emergency Messaging Service using iMedik

• Sends SMS to doctors cell phones to inform
  him/her about any emergency or patient referral.
• Follows the same multi-tier architecture
• EMS server resides outside the firewall
  intercepting incoming / outgoing messages

79
EMS Architecture
Link
80
Smartphones/PDAs in Teleconsultation

• CPUs running at 400MHz, flash memory of 256MB, We
  use Win Mobile 6.0 based. Cost about Rs. 11,000.
• 3G offers enhanced communication speed upto 7.2
  Mbps

81
Video Streaming using a PDA
82
Drawbacks / Challenges

• No shared Image marking/Annotation for effective
  tele-consultation.
• No use of Audio/Video Publishing from the Mobile
  Client to Server for conference / consultation.
• Limited to WLAN environments, global 3G, allow
  only HTTP protocol.
• MMS allows point to point transfer for
  images/data only, no broadcast. No storage for
  future reference

83
Proposed system
84
Proposed system

• Tested using Windows Mobile 6 PDA.
• Built using JavaFX and JavaME technologies
• Makes use of RTMP / RTMPT protocol for
  communication
• Red5 Flash server(open source) and MySQL database

85
Key Features

• Shared Image Drawing /Annotations Canvas

86
Key Features

• Audio/Video Publishing from Mobile Client to the
  Flash Server

87
(No Transcript)
88
Conclusion

• Increasing uses of hand held devices in accessing
  medical information.
• Integration of EHR with hand-held devices is
  essential.
• SMS infrastructure could be effectively used for
  coordinating activities.
• Increasing use of higher services of data and
  multimedia communication in mobile devices.

89
Thank You