Transcript New application areas for speech recognition in the EMR

New application areas for speech recognition in the
EMR and their effects on patient safety
Mert Öz, Product Manager Innovations, Nuance Healthcare
[email protected]
1
Agenda
• EMRs: A bird’s-eye view
• The silver bullet: EMR promise and reality
• Facilitating EMR adoption with speech recognition
• “Not your father’s speech recognition”
> Page
2
Complex Eco-system of IT Entities
> Page
3
EMR / EPR / EHR / PHR …
• Many names, many meanings
• Hailed as the key to sustainable healthcare
• US stimulus plan calls for vast government subsidies for
EMR adoption
• European Commission: “EMRs should be interoperable
by 2015 to ensure cross-border healthcare.”
• Big players increase their activities: Google, Microsoft,
IBM, SAP…
> Page
4
The Cost Promise
•
prevent unnecessary costs (labs, images,
medications, etc.)
•
through improved disease management
•
optimize patient management
•
help in anti-fraud measures
•
reduce malpractice costs
•
generate data for developing more cost
effective care
•
better regulatory compliance (less fines,
accurate and timely reimbursement etc)
•
…
> Page
Efficient hospital: 91% of spendings
related to medical care.
Source: Blue Cross Blue Shield of Michigan.
5
The Care Promise
•
reduce diagnostic & medication errors
•
improve treatment through e.g. EBM
•
avoid unnecessary procedures &
medications
•
indulge in preventive care
•
raise quality of life through disease
management
•
educate patients on their condition /
treatment plan
•
…
> Page
6
The Reality
•
Adoption rate 10-12% in US
•
Systems not always used to their full
potential or don’t deliver to the promise
•
Simply converting paper to electronic forms
is not enough
•
Adoption barriers and resistance among
physicians
EMR adoption: Making physicians
happy. Always?
> Page
7
Adoption challenges
•
Costs of implementation / transition /
operation
•
Interoperability / standards
•
Security & privacy concerns
•
Costs / benefits alignment
•
…
USABILITY
> Page
8
Speech Recognition in Healthcare today: An Update
Backend
– MTSOs
– In-house / on-premise with own /
outsourced transcriptionists / editors
Front-end
– Mostly radiology
– Limited usage in EMRs, but growing
• At specific control points in
workflow (e.g. discharge
summary)
• “Dictate Anywhere” paradigm:
Dragon Medical
> Page
Healthcare documentation: Every
time has its methods
10
Speech Recognition in Healthcare today: Workflow dimension
The classical documentation workflow enhanced with speech recognition.
Raw data
Text attached
Text
EMR
Report
Billing
> Page
11
Speech Recognition in Healthcare today: Workflow dimension
SpeechMagic
/ Discharge
Summary
SpeechMagic
InterActive
/ Patient Encounter Note
File
Tools Tools
File
Chief Complaint
The patient
a 58 year
oldyear
male
of chestofpain
and
shortness
of breath.
[The is
patient
is a 58
oldcomplaining
male complaining
chest
pain
and shortness
of breath.]
The Patient has been suffering from hypertension and high cholesterol. The patient is currently on
Lipitor Past
and Lisinopril.
Medical History
His father
died of an MI
his 60s.
[Hypertension
andinhigh
cholesterol. The patient is currently on Lipitor and Lisinopril.]
The patient smokes one half pack per day. Denies alcohol.]
Family History
Physical
Examination
[Father
died of an MI in his 60s.]
Patient’s vital signs are within normal limits. The patient appears to be in moderate distress. Skin is
diaphoretic.
are equal and react to light.
SocialPupils
History
[The patient smokes one half pack per day. Denies alcohol.]
Physical Examination
[Patient’s vital signs are within normal limits. The patient appears to be in moderate distress. Skin is
diaphoretic. Pupils are equal and react to light. ]
Status Status
bar bar
> Page
Report
Billing
StatusStatus
dividerdivider
12
Structured, Complex, Multidiciplinary –
and Many Actors  Usability in the backburner
xIS
> Page
EMR
13
Contrast: Dictated Report vs EMR documentation
SpeechMagic InterActive / Patient Encounter Note
File
Tools
Chief Complaint
[The patient is a 58 year old male complaining of chest pain and shortness of breath.]
Past Medical History
[Hypertension and high cholesterol. The patient is currently on Lipitor and Lisinopril.]
Family History
[Father died of an MI in his 60s.]
Social History
[The patient smokes one half pack per day. Denies alcohol.]
Physical Examination
[Patient’s vital signs are within normal limits. The patient appears to be in moderate distress. Skin is
diaphoretic. Pupils are equal and react to light. ]
Status bar
> Page
Status divider
14
Speech Recognition in Healthcare: Workflow dimension
The classical documentation workflow enhanced with speech recognition.
Raw data
Text attached
Text
EMR
Report
Billing
> Page
15
Speech Recognition in Healthcare: The Future
Information capturing and processing with advanced speech tools.
Clinical
pathways
Interpretation
CDSS
• Parsing
• Tagging
Raw data
Text
Reference
Lookup
Actionable
information
Actions
Medication
check
Point & Click /
Direct voice
entry of
structured info
> Page
Coding
Clinical
Data
Repository
Structured
reports
16
Evolution of Speech Recognition in Healthcare
SpeechMagic
InterOp
SpeechMagic
/ Discharge
Summary
SpeechMagic
InterActive
/ Patient
Encounter with
NoteStructured Data
EMR using
Nuance
/ SpeechMagic
File
File
Tools Tools
File
Tools
File
Tools
Concepts
ICD-10ICD-10
Medications
Map ofMap
Medicine
Problem List
Medications
of Medicine
Chief Complaint
Chest pain
Patient
Name:John
Doe
Allergies:None
Chest
pain
Chief Complaint
[The patient
is a 58 yearLipitor,
old male
complaining
of chest
pain and shortness of
Medications:
Lisinopril
DoB:
15.5.1951
Shortness
of breath
The patient
a 58 year
old
male
of
chestofpain
and
shortness
of breath.
[The is
patient
is a 58
year
oldcomplaining
male complaining
chest
pain
and shortness
of breath.]
Shortness
of breath
breath.]
The Patient has been suffering from hypertension and high cholesterol. The patient is currently on High cholesterol
High cholesterol
Chief Complaint
Lipitor Past
and Lisinopril.
Medical
History History
Past Medical
Sinus
pain
Sore
throat
SoB
Head
ache
Feeling
down
...
His father
died of
an MI
hisand
60s.
[Hypertension
andinhigh
cholesterol.
The patient
currently
on Lipitoronand
Lisinopril.]
[Hypertension
high cholesterol.
Theispatient
is currently
Lipitor
and
The patient smokes
one half pack per day. Denies alcohol.]
Lisinopril.]
Family History
Congestion
Cough
Cough
Runny nose
Chest pain
...
Physical
Examination
[Father
died
of anHistory
MI in his 60s.]
Family
Patient’s vital signs
are died
within
The patient appears to be in moderate distress. Skin is
[Father
of normal
an MI
inlimits.
his 60s.]
Pyhsical
Exam
diaphoretic.
are equal
and react to light.
SocialPupils
History
General
Social
History
[The patient
smokes
one half
Denies alcohol.]
WNLpack per day.
underweight
Moderate distress
Severe Distress
[The patient smokes one half pack per day. Denies alcohol.]
Physical Examination
asleep
awake
oriented
Examination
[Patient’sPhysical
vital signs
are within normal limits. The patientalert
appears to be in moderate
distress. Skin is
[Patient’s
vital
signs
are
within
normal
The patient appears to be in
Narrative:
diaphoretic. Pupils are equal and react to light.limits.
]
moderateThe
distress.
Skin
diaphoretic.
Pupils
are equal of
and
react
to and
light.shortness
]
patient
is ais58
year old male
complaining
chest
pain
of
breath.
The Patient has been suffering from hypertension and high cholesterol. The
patient is currently on Lipitor and Lisinopril.
His father died of an MI in his 60s.
The patient smokes one halfStatus
pack per
day. Denies alcohol.
divider
Status Status
bar barStatus barStatus bar
> Page
StatusStatus
dividerdivider Status divider
17
Interactive Clinical Documentation
• Demonstration by
– By David Lareau, COO Medicomp
> Page
18
Thank you
Integration Partners
Nuance @ HIMSS
2009
Booth 1448
> Page
19
A Difficult Fit: EMR and “Classical” Speech
Recognition
SpeechMagic InterActive / Patient Encounter Note
File
Tools
Chief Complaint
[The patient is a 58 year old male complaining of chest pain and shortness of breath.]
Past Medical History
[Hypertension and high cholesterol. The patient is currently on Lipitor and Lisinopril.]
Family History
[Father died of an MI in his 60s.]
Social History
[The patient smokes one half pack per day. Denies alcohol.]
Physical Examination
[Patient’s vital signs are within normal limits. The patient appears to be in moderate distress.
NotSkin
tooismany
diaphoretic. Pupils are equal and react to light. ]
places to dictate
Status bar
> Page
Status divider
21
Electronic Medical Record: The Promise -3-
• Ohio State example
– Medication turn-around times dropped fully 64 percent.
– Radiology order entry turnaround times fell from seven
hours, 37 minutes, to four hours, 21 minutes.
– Medical transcription errors were eliminated where the
system was in use. Where it was not yet implemented,
errors reached as high as 26 percent.
> Page
22
Electronic Medical Record: The Promise -4-
• Small Practice example
–
Dr. Peter Masucci, a pediatrician with his own office in Everett, Mass., embraced electronic
health records to “try to get our practice into the 21st century.” He could not afford conventional
software, and chose a Web-based service from Athenahealth, a company supplying online
financial and electronic health record services to doctors’ offices. Dr. Masucci was already using
Athenahealth’s outsourced financial service, and less than two years ago adopted the online
medical record. Today, Dr. Masucci is an enthusiast, talking about the wealth of patient
information, drug interaction warnings and guidelines for care, all in the Web-based records.
“Do I see more patients because of this technology? Probably no,”
Dr. Masucci said. “But I am doing a better job with the patients I am
seeing. It almost forces you to be a better doctor.”
> Page
23
Electronic Medical Record: The flip side -2-
Cedars-Sinai Medical Center in Los Angeles
– … $34 million Computerized Physician Order Entry
system, but only included the input of a few physicians
before launching it hospital-wide in late 2002 without
thorough training (Connolly, 2005). Physicians who
were used to scribbling a few notes by hand were now
required to go through nearly a dozen screens and
respond to numerous alerts for even common orders.
Such usability issues with the “clunky and slow”
interface caused more than 400 doctors to demand
its removal within three months of its launch
(Ornstein, 2003).
> Page
24
Electronic Medical Record: The flip side -3-
VA Example:
– ... display that did not clearly indicate stop orders for treatment,
leading to reported cases of unnecessary drug doses. The
Associated Press (2009) reported that “patients at VA health
centers were given incorrect doses of drugs, had needed
treatments delayed and may have been exposed to other medical
errors due to the glitches that showed faulty displays of their
electronic health records.” This prompted the chairman of the
House Veterans Affairs Committee, Rep. Bob Filner (D-California)
to state that "… confidence must be inherent in any electronic
medical records system."
> Page
25
Barriers to implementing EHR
> Page
26
Barriers to implementing EHR
When inspecting this table, some interesting observations emerge. Certainly, well-known factors like security and cost are
cited as key factors, but another theme – usability – floats near the top. Usability is rarely mentioned by name as a
barrier to EHR adoption by respondents at these group practices; yet, two of the top five barriers to implementation are
related to the usability of EHRs (items 3 and 4). And while implementation costs are important barriers to practitioners,
some of the other popularly cited reasons for lack of adoption – security, privacy, and systems integration – are
outranked by usability and productivity concerns. Usability issues are also a factor in why EHR implementations fail. In
a survey conducted by Linder et al., (Linder, Schnipper, Tsurikova, Melnikas, Volk, & Middleton, 2006), primary care
physicians were asked to list reasons they did not use the EHRs available to them. Thirty-five percent of those
physicians listed specific EHR usability issues, the most common of which were: problems with screen navigation, no
access to secondary functions, and concerns that data will be lost. Anecdotal support for usability and EHR failure
comes from Cedars-Sinai Medical Center in Los Angeles.
developed a $34 million Computerized Physician Order Entry system, but only included the input of a few physicians before
launching it hospital-wide in late 2002 without thorough training (Connolly, 2005). Physicians who were used to
scribbling a few notes by hand were now required to go through nearly a dozen screens and respond to numerous
alerts for even common orders. Such usability issues with the “clunky and slow” interface caused more than 400
doctors to demand its removal within three months of its launch (Ornstein, 2003). Poor usability can also endanger
patient health. One example of a usability failure was a display that did not clearly indicate stop orders for treatment,
leading to reported cases of unnecessary drug doses. The Associated Press (2009) reported that “patients at VA
health centers were given incorrect doses of drugs, had needed treatments delayed and may have been exposed to
other medical errors due to the glitches that showed faulty displays of their electronic health records.” This prompted
the chairman of the House Veterans Affairs Committee, Rep. Bob Filner (D-California) to that "… confidence must be
inherent in any electronic medical records system.“ Clearly, there is a dissociation between the importance of usability
and its lack of inclusion in the procurement process. On one hand, we have usability being a main barrier to entry and
a significant reason for lack of acceptance, and on the other, we have seen that usability is largely ignored during the
procurement process.
Defining usability: usability goals must be set by specifying target values for effectiveness, efficiency, and satisfaction. For
each product, these attributes should be measured in order to compare products to each other and to the usability
goals.
> Page
27
Other Countries' Experience : examples of EHR
adoption
Source: How to Select an Electronic Health Record System that Healthcare Professionals can Use
User Centric, Inc.
February 2009
> Page
28