Using AI in Pain Management...

[drusso]

If I were an insurance company and found out that a pain doctor used a virtual AI ambient scribe to create clinical documentation that incorporated all the medical necessity criteria from the health plan's medical policies for interventional pain procedures into the note, and then prompted the clinician to ask specific questions at the end of the encounter if said criteria were not fulfilled, I'd be pissed...

---

Members don't see this ad.

 

[lobelsteve]

If I were an insurance company using AI to decline all procedures ordered for a legitimate purpose, I'd be rich.

 

[callmeanesthesia]

If I were an insurance company and found out that a pain doctor used a virtual AI ambient scribe to create clinical documentation that incorporated all the medical necessity criteria from the health plan's medical policies for interventional pain procedures into the note, and then prompted the clinician to ask specific questions at the end of the encounter if said criteria were not fulfilled, I'd be pissed...

That sounds awful. Where precisely would I find such an application so I can make really sure to avoid it.

 

[drusso]

If I were an insurance company using AI to decline all procedures ordered for a legitimate purpose, I'd be rich.

Have your bots talk to my bots...

 

[Agast]

All that’s missing is the AI to do the procedure

 

[drusso]

All that’s missing is the AI to do the procedure

Coming soon to a pain clinic near you...

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study - PubMed

The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.

pubmed.ncbi.nlm.nih.gov

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study​

Adam Margalit 1, Henry Phalen 2, Cong Gao 2, Justin Ma 2, Krishna V Suresh 1, Punya Jain 1, Amirhossein Farvardin 2, Russell H Taylor 2, Mehran Armand 2, Akhil Chattre 1, Amit Jain 1

Abstract​

Study design: Phantom study.
Objective: The aim of our study is to demonstrate in a proof-of-concept model whether the use of a marker less autonomous robotic controlled injection delivery system will increase accuracy in the lumbar spine.
Methods: Ideal transforaminal epidural injection trajectories (bilateral L2/3, L3/4, L4/5, L5/S1 and S1) were planned out on a virtual pre-operative planning software by 1 experienced provider. Twenty transforaminal epidural injections were administered in a lumbar spine phantom model, 10 using a freehand procedure, and 10 using a marker less autonomous spinal robotic system. Procedural accuracy, defined as the difference between pre-operative planning and actual post-operative needle tip distance (mm) and angular orientation (degrees), were assessed between the freehand and robotic procedures.
Results: Procedural accuracy for robotically placed transforaminal epidural injections was significantly higher with the difference in pre- and post-operative needle tip distance being 20.1 (±5.0) mm in the freehand procedure and 11.4 (±3.9) mm in the robotically placed procedure (P < .001). Needle tip precision for the freehand technique was 15.6 mm (26.3 - 10.7) compared to 10.1 mm (16.3 - 6.1) for the robotic technique. Differences in needle angular orientation deviation were 5.6 (±3.3) degrees in the robotically placed procedure and 12.0 (±4.8) degrees in the freehand procedure (P = .003).
Conclusion: The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.
Keywords: autonomous surgical robot; interventional radiology; orthopaedic surgery; pain management; robot-assisted surgery; spinal rehabilitation.

 

[ProPropofol]

There's an open-source project in the works dedicated to creating a fully trainable AI that you could train on the insurance company policies. You could direct its training material to be updated automatically with each insurance policy change. Could review notes then tell you what needed to be added to the note to meet the medical necessity criteria for procedures. Having it happen in real time while you are talking to the patient/listening in on the conversation is a tad more complicated but hopefully a possibility in the future!

To get it to work fast, needs a decent GPU:

GitHub - openlm-research/open_llama: OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset - openlm-research/open_llama

github.com

 

[Agast]

Coming soon to a pain clinic near you...

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study - PubMed

The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.

pubmed.ncbi.nlm.nih.gov

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study​

Adam Margalit 1, Henry Phalen 2, Cong Gao 2, Justin Ma 2, Krishna V Suresh 1, Punya Jain 1, Amirhossein Farvardin 2, Russell H Taylor 2, Mehran Armand 2, Akhil Chattre 1, Amit Jain 1

Abstract​

Study design: Phantom study.
Objective: The aim of our study is to demonstrate in a proof-of-concept model whether the use of a marker less autonomous robotic controlled injection delivery system will increase accuracy in the lumbar spine.
Methods: Ideal transforaminal epidural injection trajectories (bilateral L2/3, L3/4, L4/5, L5/S1 and S1) were planned out on a virtual pre-operative planning software by 1 experienced provider. Twenty transforaminal epidural injections were administered in a lumbar spine phantom model, 10 using a freehand procedure, and 10 using a marker less autonomous spinal robotic system. Procedural accuracy, defined as the difference between pre-operative planning and actual post-operative needle tip distance (mm) and angular orientation (degrees), were assessed between the freehand and robotic procedures.
Results: Procedural accuracy for robotically placed transforaminal epidural injections was significantly higher with the difference in pre- and post-operative needle tip distance being 20.1 (±5.0) mm in the freehand procedure and 11.4 (±3.9) mm in the robotically placed procedure (P < .001). Needle tip precision for the freehand technique was 15.6 mm (26.3 - 10.7) compared to 10.1 mm (16.3 - 6.1) for the robotic technique. Differences in needle angular orientation deviation were 5.6 (±3.3) degrees in the robotically placed procedure and 12.0 (±4.8) degrees in the freehand procedure (P = .003).
Conclusion: The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.
Keywords: autonomous surgical robot; interventional radiology; orthopaedic surgery; pain management; robot-assisted surgery; spinal rehabilitation.

View attachment 380355

 

[hyperalgesia]

If I were an insurance company and found out that a pain doctor used a virtual AI ambient scribe to create clinical documentation that incorporated all the medical necessity criteria from the health plan's medical policies for interventional pain procedures into the note, and then prompted the clinician to ask specific questions at the end of the encounter if said criteria were not fulfilled, I'd be pissed...

They don't get pissed, they get actuaries.

 

[MitchLevi]

First and second posts in this thread were gold.

Just wanted to say that...

 

[pastafan]

Coming soon to a pain clinic near you...

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study - PubMed

The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.

pubmed.ncbi.nlm.nih.gov

Autonomous Spinal Robotic System for Transforaminal Lumbar Epidural Injections: A Proof of Concept of Study​

Adam Margalit 1, Henry Phalen 2, Cong Gao 2, Justin Ma 2, Krishna V Suresh 1, Punya Jain 1, Amirhossein Farvardin 2, Russell H Taylor 2, Mehran Armand 2, Akhil Chattre 1, Amit Jain 1

Abstract​

Study design: Phantom study.
Objective: The aim of our study is to demonstrate in a proof-of-concept model whether the use of a marker less autonomous robotic controlled injection delivery system will increase accuracy in the lumbar spine.
Methods: Ideal transforaminal epidural injection trajectories (bilateral L2/3, L3/4, L4/5, L5/S1 and S1) were planned out on a virtual pre-operative planning software by 1 experienced provider. Twenty transforaminal epidural injections were administered in a lumbar spine phantom model, 10 using a freehand procedure, and 10 using a marker less autonomous spinal robotic system. Procedural accuracy, defined as the difference between pre-operative planning and actual post-operative needle tip distance (mm) and angular orientation (degrees), were assessed between the freehand and robotic procedures.
Results: Procedural accuracy for robotically placed transforaminal epidural injections was significantly higher with the difference in pre- and post-operative needle tip distance being 20.1 (±5.0) mm in the freehand procedure and 11.4 (±3.9) mm in the robotically placed procedure (P < .001). Needle tip precision for the freehand technique was 15.6 mm (26.3 - 10.7) compared to 10.1 mm (16.3 - 6.1) for the robotic technique. Differences in needle angular orientation deviation were 5.6 (±3.3) degrees in the robotically placed procedure and 12.0 (±4.8) degrees in the freehand procedure (P = .003).
Conclusion: The robotic system allowed for comparable placement of transforaminal epidural injections as a freehand technique by an experienced provider, with additional benefits of improved accuracy and precision.
Keywords: autonomous surgical robot; interventional radiology; orthopaedic surgery; pain management; robot-assisted surgery; spinal rehabilitation.

View attachment 380355

If only it was laser guided....

 

[Dr. Ice]

If joint replacement is robot assisted, why can’t it eventually be human assisted

 

[gaseous_clay]

View attachment 380356

Most efficient way to perform a celiac

 

[Painologist]

There's an open-source project in the works dedicated to creating a fully trainable AI that you could train on the insurance company policies. You could direct its training material to be updated automatically with each insurance policy change. Could review notes then tell you what needed to be added to the note to meet the medical necessity criteria for procedures. Having it happen in real time while you are talking to the patient/listening in on the conversation is a tad more complicated but hopefully a possibility in the future!

To get it to work fast, needs a decent GPU:

GitHub - openlm-research/open_llama: OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset - openlm-research/open_llama

github.com

Are you actually utilizing something like this?

 

[drusso]

Are you actually utilizing something like this?

I've been playing with it and other versions. You load up health plan medical policies and then interrogate the model. It's very accurate for this use case. This will revolutionize our field. Robots editing our notes and scrubbing our claims.

The true "Turing Test" of our specialty will be if we can design an AI voice agent that can navigate a peer-to-peer with a hired insurance hack MD and overturn a denial.

 

[strike5858]

I've been playing with it and other versions. You load up health plan medical policies and then interrogate the model. It's very accurate for this use case. This will revolutionize our field. Robots editing our notes and scrubbing our claims.

The true "Turing Test" of our specialty will be if we can design an AI voice agent that can navigate a peer-to-peer with a hired insurance hack MD and overturn a denial.

The deep pocket insurance companies will get there before us. Unfortunately I see a day when it’s the other way around and we are fighting the insurance companies AI agent on peer to peers.

 

[Agast]

The deep pocket insurance companies will get there before us. Unfortunately I see a day when it’s the other way around and we are fighting the insurance companies AI agent on peer to peers.

Texas requires the peer to be board certified in the same specialty and licensed in the same state

Unfortunately that has led to me arguing with a bunch of anesthesiologists who don’t do pain management and have zero interest in clinic patients so don’t care if they screw them over