Category Archives: Head

AI Can Detect Emergence From Coma Better Than Doctors

Recovery from severe traumatic brain injury (TBI) can be frustrating for families and trauma professionals alike. It occurs in fits and starts, and the longest wait occurs while waiting for the patient to wake up. We perform serial neurologic exams and monitor closely for any visible response to commands.

A group of medical and engineering researchers at SUNY Stony Brook theorized that muscle movements in response to commands might be too subtle for human detection during early emergence from coma. They developed an AI system called SeeMe that studied the patients’ facial appearance down to the level of pores, and trained it to detect very fine motor movements in response to three commands:

  • Stick out your tongue
  • Open your eyes
  • Show me a smile

A group of 16 normal volunteers and 37 TBI patients were then tested while being video recorded. Both SeeMe and trained experts judged responses.

Here are the factoids:

  • SeeMe detected facial responses 4 days earlier than the trained experts
  • It detected eye opening in 86% vs 74% of human observers
  • SeeMe was able to detect mouth movements in 94% of patients without endotracheal tubes
  • The SeeMe-detected responses correlated with the clinical outcome at discharge

Bottom line: Severely brain-injured patients are able to respond to commands with subtle facial muscle movements before human observers can detect them. A specially trained AI like SeeMe can identify these movements and help predict recovery sooner than clinicians. Imagine being able to tell the family, who has been seeing their loved one making no progress, that improvement is occurring! And imagine what other applications focused AI can have on other clinical areas where human senses don’t have the capacity that carefully trained machines do!

Reference: Computer vision detects covert voluntary facial movements in unresponsive brain injury patients. Commun Med 5, 361 (2025). https://doi.org/10.1038/s43856-025-01042-y

The Modified Brain Injury Guideline Criteria (mBIG)

In my previous post, I reviewed the Brain Injury Guideline criteria (BIG) that were published in 2014, and cited some early papers promoting its use for simplifying neurotrauma care. These criteria allowed trauma professionals to use our neurosurgical colleagues’ services more sensibly.

As a reminder, these are the original BIG criteria:

Some revisions were proposed in 2020 to improve patient safety and reproducibility further.  Here are the revised criteria:

So, what are the differences?

  • The “loss of consciousness” was changed to a more objective assessment, the GCS
  • Intoxication is defined as a blood alcohol concentration > 80 mg/dL
  • Aspirin and NSAIDs are not considered antiplatelet agents
  • Epidural hematoma (EDH) is no longer sized; any epidural moves the patient to mBIG 3
  • Multiple intraparenchymal hemorrhages (IPH) move the patient to mBIG 3
  • Subarachnoid hemorrhage is more objectively classified

The mBIG criteria were tested in a multi-institutional review comparing the original criteria with the modified criteria. BIG 3 patients were excluded, since these patients required admission and neurosurgical consultation, which is maximal therapy. All patients underwent repeat CT scans to monitor for progression of the injury.

Here are the factoids:

  • A total of 269 patients were included; 98 were BIG 1 and 171 were BIG 2
  • In both BIG 1 and BIG 2 cohorts, CT progression was seen in about 11% of patients. These patients tended to have more severe injuries overall and were more likely to have EDH or IPH.
  • Two BIG 2 patients decompensated and required neurosurgical intervention; both had EDH

These findings prompted the changes that are now part of the mBIG score. Here is the complete algorithm based on the mBIG criteria (click to see full-size):

A larger validation study was published in 2022 by the same authors, following the addition of 496 patients from the same three trauma centers. The total number of patients included in the study was 496.

More factoids:

  • There were now a total of 223 mBIG 1 patients and 273 mBIG2
  • The number of CT scans and neurosurgery consults was significantly decreased
  • Hospital length of stay was also significantly decreased

Bottom line: The mBIG criteria perform better and are at least as safe as the initial BIG criteria. The mBIG criteria are more objective, making it easier to stratify patients accurately. 

The mBIG criteria should be adopted by any center seeking a consistent and validated process for stratifying patients for observation, admission, or neurosurgical consultation following head trauma. This will conserve resources and allow our neurosurgical colleagues to focus on the patients who truly need them.

References:

  1. Multicenter assessment of the Brain Injury Guidelines and a proposal of guideline modifications. Trauma Surgery & Acute Care Open, 5(1), e000483.
  2. A multicenter validation of the modified brain injury guidelines: Are they safe and effective?. Journal of Trauma and Acute Care Surgery 93(1):p 106-112, July 2022.

The BIG Brain Injury Guidelines

Until five years ago, there was tremendous variability in the way brain injuries were managed at trauma centers. There were no clear guidelines describing what should be done during the initial evaluation, and no consensus as to when to involve neurosurgery. This resulted in a lot of flailing about and unnecessary calls to our neurosurgical colleagues.

Then the Brain Injury Guidelines (BIG) came along 15 years ago. They were developed to allow trauma programs to stratify head injuries in such a way as to better utilize resources such as hospital beds, CT scanning, and neurosurgical consultation.

Injuries are stratified into three BIG categories, and management is based on them. Here is the stratification algorithm:

And here is the management algorithm based on the stratification above:

(RHCT = repeat head CT)

The original study was published ten years ago and was a retrospective review of 4,000 patient records. It found that a significant number of these patients could be managed exclusively by the trauma surgeons.

The AAST BIG Multi-Institutional Group set about prospectively validating this system to ensure that it was accurate and safe. They identified adult patients from ten high level trauma centers that had a positive initial head CT scan. They looked at the the need for neurosurgical intervention, change in neuro exam, progression on repeat head CT, any visits to the ED after discharge, and readmission for the injury within 30 days.

Here are the factoids:

  • About 2,000 patients were included in the study, with BIG1 = 15%, BIG2 = 15%, and BIG3 = 70% of patients
  • BIG1: no patients worsened, 1% had progression on CT, none required neurosurgical intervention, no readmits or ED visits
  • BIG2: 1% worsened clinically, 7% had progression on CT, none required neurosurgical intervention, no readmits or ED visits
  • All patients who required neurosurgical intervention were BIG3 (20% of patients)

The authors concluded that using the BIG criteria, CT scan use and neurosurgical consultation would have been decreased by 29%.

Bottom line: This is an exciting paper! BIG has been around for awhile, and some centers have already started using it for planning the management of their TBI patients. This study provides some validation that the system works and keeps patients safe while being respectful of resource utilization. 

My only criticism is that the number of patients in the BIG1 and BIG2 categories is low (about 600 combined). Thus, our experience in these groups remains somewhat limited. However, the study is very promising, and more centers should consider adopting BIG to help them refine their management of TBI patients. 

This was the first prospective study of the BIG criteria. A great deal of additional work has been done. And now, an attempt has been made to simplify this algorithm even further.

In my next post, I’ll review the modified BIG (mBIG) criteria and describe them in detail.

References:

  1. The BIG (brain injury guidelines) project: defining the management of traumatic brain injury by acute care surgeons. Journal of Trauma and Acute Care Surgery, 76(4), 965-969.
  2. Validating the Brain Injury Guidelines: Results of an American Association for the Surgery of Trauma prospective multi-institutional trial. J Trauma Acute Care Surg. 2022 Aug 1;93(2):157-165.

Are Prophylactic Antibiotics Needed For Facial Fractures?

The use of prophylactic antibiotics in patients with facial fractures has been controversial since forever. Some trauma professionals argue that these fractures, many of which involve a sinus or the mouth, should be considered as open fractures.

Several studies on the use of antibiotics prophylactically, preoperatively, and postoperatively have shown a significant amount of variability. A few have shown no benefit from the use of short-, long-, or no antibiotics. In fact, the Surgical Infection Society issued a practice guideline on antibiotic use in facial fractures. Essentially, they recommended that antibiotics not be administered to patients who do not require surgery. And for operative fractures, they recommended against pre- or post-operative antibiotics.

A recently published study examined current practices regarding antibiotic administration, timing, and adverse events. The null hypothesis was that prophylactic antibiotics would not reduce facial fracture-associated infectious complications in nonoperative facial fractures.

The AAST Facial Fracture Study Group performed a prospective, observational study of adult patients who did not undergo operative repair of their facial fractures. Patients receiving antibiotics for other causes,  those who were immunocompromised, and patients with bowel injuries were excluded. The primary outcome was any related infection, drainage, or follow-up visit requiring antibiotics. Secondary outcomes included demographic indicators such as length of stay, ventilator time, discharge disposition, and readmission within 30 days.

Here are the factoids:

  • A total of 1,835 patients were studied, and two-thirds (64%) did not receive any antibiotics
  • Infections developed in 0.7% of patients without antibiotics and 1.7% with
  • The vast majority of fractures in all patients (84%) were not considered open (no mucosal exposure)
  • Antibiotic administration had a significant association with infectious complications, although the duration of antibiotics did not seem to make a difference

The authors concluded that infection rates were very low despite the majority of patients receiving no antibiotics.

Bottom line: This study provides another set of data points that show us that antibiotics are not necessary in many facial fractures. This is an observational study, so there were wide variations in practice patterns that make the study more difficult to interpret.

There was a relatively small number of patients with “open fractures” that involved exposure to the mucosa. This weakens the study conclusions for this group.

This study joins a growing number that would indicate that nonoperatively managed facial fractures do not require antibiotics. For those that do need surgery, the usual perioperative antibiotic rules still apply.

Reference: Prophylactic antibiotic use in trauma patients with non-operative facial fractures: A prospective AAST multicenter trial. Journal of Trauma and Acute Care Surgery 98(4):p 557-564, April 2025.

Everything You Wanted To Know About: Cranial Bone Flaps

Patients with severe TBI frequently undergo surgical procedures to remove clot or decompress the brain. Most of the time, they undergo a craniotomy, in which a bone flap is raised temporarily and then replaced at the end of the procedure.

But in decompressive surgery, the bone flap cannot be replaced because doing so may increase intracranial pressure. What to do with it?

There are four options:

  1. The piece of bone can buried in the subcutaneous tissue of the abdominal wall. The advantage is that it can’t get lost. Cosmetically, it looks odd, but so does having a bone flap missing from the side of your head. And this technique can’t be used as easily if the patient has had prior abdominal surgery.

2. Some centers have buried the flap in the subgaleal tissues of the scalp on the opposite side of the skull. The few papers on this technique demonstrated a low infection rate. The advantage is that only one surgical field is necessary at the time the flap is replaced. However, the cosmetic disadvantage before the flap is replaced is much more pronounced.

3. Most commonly, the flap is frozen and “banked” for later replacement. There are reports of some mineral loss from the flap after replacement, and occasional infection. And occasionally the entire piece is misplaced. Another disadvantage is that if the patient moves away or presents to another hospital for flap replacement, the logistics of transferring a frozen piece of bone are very challenging.

4. Some centers just throw the bone flap away. This necessitates replacing it with some other material like metal or plastic. This tends to be more complicated and expensive, since the replacement needs to be sculpted to fit the existing gap.

So which flap management technique is best? Unfortunately, we don’t know yet, and probably never will. Your neurosurgeons will have their favorite technique, and that will ultimately be the option of choice.

Reference: Bone flap management in neurosurgery. Rev Neuroscience 17(2):133-137, 2009.