A concept for review. Not a medical device. Nothing here has been built or used on a patient.

EveryWave

A low-cost EEG headband for anesthesia with no wires and no monitor of its own. It uses the snap electrodes already in your supply room and displays on an iPhone or iPad.

In the 1980s I worked on an EEG monitor called the Lifescan. It measured every wave the brain produced, on the left and on the right, and drew them on a screen the anesthesiologist could read at a glance. It was a cabinet with a CRT, cabled to the patient.

The same analysis now fits in a phone. The amplifier fits in a pod the size of a matchbox. The sensor can be five ordinary monitoring electrodes. I have designed that device and tested its software, and I have not built it. Before anyone spends money, I want the judgment of the people who would have to use it.

$1.55per patient: five ordinary snap electrodes, nothing proprietary
No wiresbattery and Bluetooth; nothing runs from the patient to a machine
No dedicated displaythe screen is an iPhone or iPad the department already owns
Every wave, both sideseach wave measured one at a time, left and right, the way the Lifescan did

Two-sided monitoring is not new, and I am not claiming it. The Lifescan drew both hemispheres in the 1980s. Today NeuroWave's NeuroSENSE reports an index for each hemisphere, Masimo's SedLine shows left and right spectrograms, and Medtronic's four-channel BIS has an asymmetry indicator. Each of them needs a patient cable, its own monitor or module, and its maker's sensor. Those three things are what EveryWave changes.

“It’s been said that brain activity monitoring should be used in all high-risk surgical procedures and for routine procedures on high-risk patients. I’d like to take that one step further and envision the day when brain activity is routinely monitored in all patients receiving general anesthesia.”N. Ty Smith, M.D., in the Lifescan video

The display

This is running now, in your browser, on the same analysis code that would run on the phone. The EEG is synthetic, not a patient. Move the depth slider and watch both sides respond. Weaken one side to see the asymmetry warning. Add an artifact to see what the monitor does about it.

The frame is what the app would show on an iPad; on an iPhone the two sides stack. The buttons inside the frame are the clinician’s: snapshot, compare, recall, electrode check, export. The controls under the frame are a simulator. They stand in for a patient and are not part of the product.

EveryWaveSynthetic EEG. Not a patient.
Asymmetry +0.00Elapsed 0:00Updated at 0:00, next in 2 sElectrodes
LEFT--Hz
SEF95 --Suppression 0%Activity --Quality --
RIGHT--Hz
SEF95 --Suppression 0%Activity --Quality --
Delta 0.3 to 3Theta 3 to 7Sub-alpha 7 to 9Alpha 9 to 12Beta 12 to 30 HzWhite line on top of each box: activity edge. The edge number on the front takes the color of its band.
Show snapshot
Recalllive
Settings

Simulator. Not part of the product.

How to read it. The top traces are the raw EEG, left above right. In each box, every vertical line is one wave: its position is its frequency, its height is its amplitude, its color is its band, and older waves step toward the back. The large number is the activity edge, the frequency below which 80% of the wave activity lies, averaged over 10 seconds as the display opens. The studies further down this page used 30 seconds; Settings changes it. The same number sits on the front of each box, in a small box beside the square that marks the edge. Both take the color of the band the edge is in, as they did on the Lifescan, so the color changes as the edge crosses from one band to the next. Nothing below the raw trace changes more than once every two seconds. The voltage scale in Settings applies to the whole screen: the raw traces and the height of every wave.

What the Lifescan already did

The Lifescan carried about 30,000 lines of code, as I remember it. A good part of that did jobs a phone now does without being asked: drawing the screen, storing data, compressing it. The rest were functions a brain monitor needs in an operating room, and a new one cannot offer less. Each one is listed with how it is handled today and how far along it is.

Lifescan, 1985EveryWave
FunctionLifescan, 1985EveryWave
Electrode check, continuous A very small 40 Hz signal went out through the common electrode the whole time, and every other electrode picked it up. The software read its level, then removed it with the same kind of notch filter it used for 60 Hz. The amplifier chip has this built in: a test current of a few nanoamps at one quarter of the sample rate, 125 Hz here. That is above the EEG band, so it can run the whole time. Contact impedance falls as frequency rises, so the pass mark has to be set on real hardware, not copied from 40 Hz. Designed. The firmware today reads only the chip’s on or off flags. Simulated in the display.
Recall About 12 hours of EEG held in memory, with no disk. Give it a start time and it replayed. I wrote the compression routine myself, in PL/M-86, because there was nothing to buy. A phone needs no compression. Twelve hours of raw EEG from both channels is about 130 MB. The wave-by-wave record is about a million waves, a few megabytes. Works in the display, for the session. Storage in the phone app is not built.
Snapshots Nine numbered snapshots of the screen. Bring one back for both sides or for one side. Most useful in carotid endarterectomy: take a baseline, then call it back beside the present at any time. Nine numbered snapshots, shown for both sides or for one side beside now. Whether two forehead channels are enough for carotid surgery is a question for the people who do it. Works in the display.
Interface to the record An RS-232 output with its format printed in the user manual. The Arkive anesthesia record keeper, and others, used it to chart the edge. The pod’s Bluetooth format is written down the same way. From the phone, the numbers would reach the anesthesia record by the route hospitals already use for device data, an IHE device message through a gateway, or by FHIR. The reasoning step needs the same connection in the other direction, to learn what the pump is giving. Not built.
Research software A free package for a standard PC. It captured the wave-by-wave data, not the waveform, for publications and drug research. Export waves in the display writes that kind of file. The tools that read it are the ones that processed the 2,574 recordings on this page. Export works in the display. The tools are not released.
User preferences Display times, and a choice of how the edge was calculated, including a sum-of-squares method meant to sit closer to a spectral edge. Under Settings in the display. I tested the edge methods before offering them. The result is below. Works in the display.

The edge, counted three ways

The same waves can be counted three ways. Every wave counts once. Every wave counts by its height, which is the activity edge used everywhere else on this page. Or every wave counts by its height squared, which is how power is counted. I ran all three on the 324 propofol patients from the awake-or-anesthetized check further down.

EveryWaveCommercial monitor, same patients
Edge counted byBefore propofolUnder propofolHigher awake, share of patients
Wave count24.0 Hz17.6 Hz100%
Amplitude (the activity edge)20.9 Hz14.5 Hz87%
Amplitude squared (power)9.6 Hz12.4 Hz42%
The monitor’s own spectral edge16.8 Hz16.2 Hz52%

Squaring the amplitude does what it was meant to do: it moves the edge toward a spectral edge. On this test that is the wrong direction, most likely because a few large slow waves, blinks among them, take over while the patient is awake. Counting every wave once separated awake from anesthetized in all 324 patients.

Two cautions. Small fast waves on an awake forehead are likely part muscle, not all brain, so some of that separation may be the forehead and not the cortex. And between light and deep anesthesia none of the three follows BIS better than the others: 0.31, 0.37 and 0.33 within a case, on a scale where 1 is perfect. The edge is still not a depth number. Tuning half of the dataset; the other half is sealed.

How it goes on

How the band goes on: front and side viewsFrontpodRight foreheadLeft foreheadCenter, under the podBehindright earBehindleft earPatient's rightPatient's leftSideOn the bonebehind the earForehead electrodePod(no cable)Ear lead slidesto fit
Five electrodes: left and right forehead, one behind each ear, and a center electrode under the pod. No cable leaves the patient.
  1. Snap on five electrodes. Ordinary pediatric monitoring electrodes with a standard 4 mm snap. Any brand the hospital already stocks.
  2. Peel and place the forehead three. The band holds them in line, so there is nothing to measure.
  3. Slide each ear lead until its electrode sits on the bone behind the ear, then press it down.
  4. Press the button. The pod's light comes on, the phone shows five green electrodes, and the display starts.

The band and pod are reused. The electrodes are thrown away. Whether the band itself should be wipeable or single-patient is one of the questions below.

Why five and not three. Each side gets its own pair, forehead to ear, so the two channels are independent views of two hemispheres. With three forehead electrodes alone, the two channels share an electrode and sit 3 cm apart.

How it works

No wires

  • The pod amplifies and digitizes two channels of EEG, 500 times a second.
  • It sends the raw samples over Bluetooth Low Energy. All analysis happens on the phone or tablet.
  • Lost packets are detected and marked. They are never drawn as EEG.
  • The pod will not acquire while it is on its charger. A patient is never connected to anything plugged into the wall.

Every wave, not an average

  • The usual method runs a Fourier transform on short blocks of EEG, typically two seconds, and reports the average frequency content of each block.
  • Aperiodic analysis finds each wave: valley, peak, valley. Its height is the amplitude. The time between valleys is the frequency.
  • A wave spoiled by artifact is dropped by itself. Its neighbors are kept.
  • The method was published in 1986 and its patents have expired. It is free for anyone to use.

What is inside

Three parts do the work. Each was chosen because it is small, cheap, low in power and already made in volume.

JobRecommended partWhy
EEG amplifier and converterTexas Instruments ADS1292Two channels, 24 bits, electrode-off detection and a driven reference in one 4 mm chip, at about 0.7 milliwatts. It was designed for ECG, and its data sheet lists 8 microvolts of noise, peak to peak (150 Hz bandwidth, gain of 6). NeuroWave specifies under 2 for the NeuroSENSE (0.125 to 100 Hz). The bandwidths differ, so that is not a clean comparison, but the gap is real. Whether this part is quiet enough for low-voltage fast EEG is the first thing to test on a bench.
Processor and wirelessNordic nRF54L15 in a pre-certified module
Fallback: nRF52832, which the firmware was first written for
Processor and Bluetooth radio in one part. A pre-certified module avoids radio approval of a custom antenna. No specific module has been chosen.
BatteryLithium-polymer cell, about 150 mAh, with its own protection circuitAt an estimated 2 milliamps the cell should last about three days of continuous use. That figure is calculated, not measured.
Schematic-level drawing of the EveryWave podSnap electrodesInput protectionper electrode: series R,clamps, RF filterADS12922-channel, 24-bit EEG front end1Left foreheadIN1P2Left earIN1N3Right foreheadIN2P4Right earIN2N5Center foreheadRLDOUTdriven referenceRadio + processor modulenRF54L15 (or nRF52832), pre-certifiedSCLKSPI clockDINSPI outDOUTSPI inCSGPIODRDYGPIO interruptSTARTGPIORESETGPIOBluetooth LEPowerDock contactsCharger ICLi-polymer cell150 mAh + protection3.0 V low-noiseregulator3.0 V to both chips,separately decoupledCharge-present signal to the processor: the firmware will not acquire while external power is connected.Design concept, not reviewed by an engineer. The patient-protection network (amber) is not designed.
The circuit at schematic level. The amber block is the patient-protection network: defibrillator withstand, electrosurgery filtering and leakage limits. It is specialist work and it has not been designed.
Board floorplan to scaleBoard floorplan, to scale: 38 x 24 mm, four layersBandconnector5 leadsInputprotection(not designed)ADS1292referencecapacitors3.0 Vregulatoranalog sidedigital sideRadio + processormodule(drawn at 10 x 15 mm;depends on module)antennakeep-outchargerbatteryconnectorbuttonlight10 mmTwo charging pads sit on the underside. The battery lies under the board in a 42 x 28 x 14 mm pod.A floorplan shows where parts sit. It is not a routed board, and no engineer has reviewed it.

What it would cost

Two numbers matter to a department: what you pay once, and what you pay for every patient. Each table sets EveryWave against what is on the market today.

EveryWaveOn the market today
Every patientCostBasis
EveryWave: five snap electrodes$1.553M Red Dot 2248-50 at $310.09 per 1,000, a US distributor's listed price in November 2026 checked
BIS sensor, published figureabout $17Abenstein, 2009 published
BIS sensor, listabout $31 to $40US reseller list prices seen in November 2026. Hospital contract prices will be lower and are not public list price
NeuroSENSE electrode kit: four pre-gelled electrodesnot publishedNeuroWave's brochure calls the kit “affordably priced” and gives no figure. I could not find one not found
OnceCostBasis
EveryWave: parts for one pod and band$23 to $43My part-by-part estimate at prototype quantities. Not quotes. Excludes assembly, testing and the charging dock estimate
EveryWave: purchase price, assumed$150 to $350An assumption: five to eight times the parts cost, to carry assembly, testing, regulatory work, support and margin. Argue with it assumption
EveryWave: display$0An iPhone or iPad the department already owns
BIS monitor, published figureabout $9,000Abenstein, 2009 published
NeuroSENSE monitornot publishedI could not find a public price not found

I have compared EveryWave only with prices I could source. If you know what your department pays for a BIS, SedLine or NeuroSENSE sensor, that number is worth more than any on this page.

Parts estimate by line: amplifier $6 to $9, radio module $5 to $8, battery $3 to $5, charger and regulator $1 to $2, input protection $1 to $2, small parts $1 to $2, circuit board $2 to $4, five snap sockets $1 to $2.50, pod shell $1 to $3, band $2 to $5.

What we know, and what we do not

Done

  • The 1986 algorithm rebuilt from the published paper, in three programming languages that agree wave for wave.
  • 63 automated checks, including the Bluetooth link with packets deliberately lost.
  • The analysis run on 2,574 public operating-room EEG recordings.
  • The Lifescan’s clinician functions in the display on this page: nine snapshots, compare, recall, export. On synthetic EEG, in a browser.

Not done

  • No hardware exists. Nothing has been powered.
  • No recording from both sides of a head. The public recordings are one-sided.
  • The phone app has none of the Lifescan functions yet, and the continuous electrode check is designed, not written.
  • No patient, no clinical study, no regulatory submission.

The result you should hear from me first

I ran the analysis on recordings from 2,574 surgical patients in VitalDB, a public dataset from Seoul National University Hospital. Each recording holds the raw EEG and, beside it, what a commercial BIS monitor reported at the same moment. Half of the cases were set aside unopened, for one final test. The numbers here are from the other 1,256 cases, 1,921 hours of anesthesia.

Median edge frequency against the commercial monitor's BIS, 1,256 public cases10141822where most of the case is spentunder 3030-4040-5050-6060-7070-80over 80BIS from the commercial monitor (deep on the left, awake on the right)Median frequency, HzEveryWaveactivity edgeThe monitor's ownspectral edge
Median edge frequency at each level of BIS. 1,256 cases. Data: VitalDB (Lee and colleagues, Scientific Data 2022), CC BY 4.0.

The good. The activity edge from this 1986 method lands within about 2 Hz of the commercial monitor's own spectral edge and moves with it (correlation 0.74). It clearly separates an awake patient from an anesthetized one.

The bad. Between light and deep anesthesia it goes flat. So does the monitor's own spectral edge, though less. Inside a single case, the activity edge agreed with BIS only moderately (0.39 on a scale where 1 is perfect, against 0.60 for the monitor's spectral edge), and in about one case in eight it ran the wrong way.

What EveryWave can tell you about depth

The edge frequency is one number, and one number was never going to carry depth. So I asked three narrower questions of the same 1,256 cases.

EveryWaveOn the market today
QuestionHow it was testedEveryWaveCommercial monitor, same patients
Awake or anesthetized?324 patients given propofol by a pump that records the dose. Each measure before the drug, against the same measure under it. No monitor decided which was which.Edge frequency higher before the drug in 87 percent of patients (20.9 Hz against 14.5 Hz). The index: all 324.Its own spectral edge: 52 percent. BIS: all 324.
Too deep?Finding the periods of burst suppression.The suppression measure finds the periods the monitor flags: 0.94 on a scale where 0.5 is chance and 1 is perfect.Its suppression ratio is the reference here.
How deep, from 0 to 100?An index computed from the whole wave picture, not from the edge alone. Every value was computed for a patient the index had never seen.Within 10 points of BIS 89 percent of the time, with no bias.BIS is the reference here.
What I will not claim. The edge frequency alone cannot titrate between light and deep, and neither can the monitor's own spectral edge. The index is learned from BIS, so it inherits whatever BIS gets wrong. All of this is on recordings made with another company's sensor at one hospital, not on EveryWave hardware. Half of the cases are still sealed for one final test.

For comparison, BIS is cleared by the FDA with the wording that it “may be used as an aid in monitoring the effects of certain anesthetic agents.” An aid. That is the claim I am working toward, and no more than that.

Depth depends on the drug and the patient

One index and one target band, for every drug and every patient: that is how the depth number is generally used. I do not think it is right, so I tested it on the same cases.

Then the test that matters. I built one index for each kind of drug, each trained to follow that drug's own concentration from the waves, and asked how well each measure follows the drug inside a single patient. A score of 1 is perfect.

EveryWaveOn the market today
Following the drug inside one patientGas, 477 casesPropofol, 752 cases
EveryWave index built for that drug0.590.42
BIS0.500.23
EveryWave edge frequency alone0.32−0.13

The index built for the drug beat BIS in 319 of the 477 gas cases and in 574 of the 752 propofol cases. Every value was computed for a patient the index had never seen. The edge frequency alone ran the wrong way on propofol, which is one more reason not to lean on a single number.

A caution. Drug concentration is not depth. The propofol figure is the pump's estimate, not a blood level. Surgery and other drugs change what the brain does at the same concentration. What the table shows is narrower: an index that knows which drug it is reading follows that drug better than an index that does not.

Where this goes. Depth should be judged against a range for this drug and this patient, with the drug taken from the pump or the anesthesia machine and not typed in by a busy clinician. And if the record says the drug is running while the brain is getting lighter, the monitor should say so, because that is what a failed intravenous line would look like. A first, crude test of that check is reported further down, under three days of testing. It did not work yet. Patent pending.

These indexes are machine-learned from the wave picture. Reasoning over the drugs, the patient and the vital signs together, in plain language, is the work that comes next.

Limits of this test. BIS is another company's index, not the truth about the brain. The recordings come from one hospital, were filtered by the BIS monitor, and were stored at 128 samples a second. Agreement with BIS shows the method behaves sensibly on real signals. It does not show clinical benefit.

Three days of testing: what held up and what did not

Everything on this page was designed and tested in three days, by one person working with an AI model, against 2,574 recorded operations and 20 sedated volunteers. About half of what came back was bad news. Both halves are listed.

Held up

  • Awake against anesthetized, from the edge alone: 87% of 324 patients.
  • A 0 to 100 index from the wave picture: within 10 points of BIS 89% of the time.
  • An index built for the drug in use follows that drug better than BIS does.
  • The low-cost amplifier chip: no measurable loss.
  • The electrode behind the ear: waves 1.6 times taller than forehead to temple.
  • Noticing the propofol stop: level with BIS, once the waves above 30 Hz were counted.

Did not hold up

  • The edge as a depth number: flat between light and deep, and it rises under light sedation before it falls.
  • The sum-of-squares edge: wrong way in more than half of patients.
  • Beating BIS at noticing the drug going away: nothing tried did.
  • Small mid-case changes: no method, BIS included, saw more than about one in three.
  • Two rules for using the pump record to judge an alarm: both failed.

The drug stops. Who notices?

At the end of 628 propofol cases the infusion stops. I treated the pump record as frozen at that moment, as it would be if the line had failed, and asked how soon each method alarmed. Every method was set to the same false alarm rate, one every two hours of steady anesthesia.

EveryWaveCommercial monitor, same patients
MethodAlarmed within 10 minutes
BIS, against the patient’s own last 15 minutes64%
Wave picture alone61%
Wave picture with very fast waves (30 to 47 Hz) and alpha riding on slow waves64%
Wave picture with the monitor’s own muscle number added69%

Level with BIS, not ahead of it. The last row is the lead worth following: the monitor’s muscle number comes from 70 to 110 Hz, which these recordings, sampled 128 times a second, cannot contain. The pod samples 500 times a second and could measure that band itself. That cannot be tested until a pod exists.

The reasoning check, first attempt. One fact in its favor: 52% of BIS’s alarms during steady anesthesia came while the pump record showed a drug had just been turned down. The record explains half of what a brain monitor alarms about. But subtracting a brain estimate from the pump’s alarmed every time the dose went up, and silencing explained alarms left the rule deaf a third of the time. The idea has evidence and no working rule yet. The end of surgery is also a rough stand-in for a failed line.

The electrode behind the ear

A public set of 20 volunteers sedated with propofol, recorded with 91 electrodes and with blood levels measured, let me build both arrangements from the same heads: forehead to behind the ear, as on this band, and forehead to temple, as on commercial sensors. Waves were 1.6 times taller forehead to ear. The two edges agreed well (0.81) but forehead to ear read about 2 Hz lower, so anything tuned on recordings from a commercial sensor has to be fitted again on the band. The very fast waves fell as blood propofol rose in 19 of the 20. And at these light doses the edge went up, not down. The site behind the ear is the nearest one that data set kept, not the mastoid itself.

What a developer can do now

In 1985 one change to the Lifescan’s software took several hours: recode, compile, burn the chips, test. There was no public library of recorded operations to test an idea against. I estimate the traditional route to the answers on this page, from a requirements document through a development plan, a system design and a validation study, at twelve to eighteen months and a team of five. These took three days. The hardware, the patients and the regulator are all still ahead, and none of them got shorter. What got shorter is the distance between an idea and an honest answer about it.

The next stage of research: the pump and the brain, read together

An infusion pump knows what it delivered. Only the brain knows what arrived. I spent the later part of my career connecting pumps to the hospital record, so after the three days I asked a different question: what if the pump record and the EEG were read side by side, and something had to say whether they agree?

The pump and the brain, read togetherSOURCE 1Infusion pump, connectedDrug, concentration, rate,dose rate, every start and stop.SOURCE 2EveryWave headbandActivity edge, activity, very fastwaves, suppression, quality.SOURCE 3Patient monitorHeart rate and blood pressure.REASONING LAYER (AI)Reads all three,minute by minuteIs the brain doing whatthe pump says it should?No age, sex or height. No drug model.THEY AGREEStay quietNo alert.PUMP DELIVERING, BRAIN LIGHTENINGDrug may not be arrivingCheck the line, the site andwhat is in the syringe.PUMP STOPPED, BRAIN STAYS DEEPSomething is still runningCheck what else is reachingthe patient.Dashed: closing the loop back to the pump. Not built, not tested.
The idea as a block diagram. Nothing was connected. It was tested on recorded cases, with the pump record laid out the way a connected pump reports it.

How it was tested

Real recordings, real patients. I left the EEG alone and altered the pump record on purpose, so the right answer was known: in some cases a dose or an infusion was shown that never reached the patient, in some a real one was hidden, and some were left correct. A separate AI, which never saw how the cases were made, read each one and had to say which it was. The bar for each run was written down before the run.

RunBlinded AISimple fitted ruleGuessing
Sedation for endoscopy, one dose added to or removed from the record14 of 248 of 248 of 24
The same test on 24 new patients15 of 248 of 248 of 24
Operating room, an infusion stop hidden or invented, EveryWave’s own measures17 of 2415 of 248 of 24

What held up. Three runs, three results well above guessing, and above a simple rule each time. In the operating-room run, every time the AI said the drug was not arriving, it was right.

What did not. The bar I set in advance was met once and missed twice, each time by a single case. It was wrong about four times in ten. In half the hidden stops the brain showed nothing for twelve minutes after the drug really stopped, and no amount of reasoning sees a change that has not happened yet. A pump’s own pressure sensing will catch a blocked line sooner.

More research needed. This is 72 recorded cases, read after the fact, by one family of AI model. No pump and no headband were connected, and nothing here has been tried on a patient. What the brain can add is what a pump cannot know: whether the drug reached the vein, whether the syringe holds what the label says, and whether this patient needs far more or far less than the dose assumes. That is the question worth a proper study.

Data: DOSE-I (Garbe, Kantelhardt, Seeliger and Schmid; CC BY 4.0) and VitalDB (Lee and colleagues; CC BY 4.0). The pumps in the operating-room recordings were connected syringe pumps whose rates were recorded during surgery.

How it would fit together at the bedside

This is a picture of the whole idea, in the operating room or the intensive care unit. It ties together a year of work: the pump connection I spent a career on, the AI MedAgent demonstration, and this headband. None of it is connected. AI MedAgent is a demonstration that runs on a simulator.

How it would fit together at the bedsidePatient with the EveryWave headbandEveryWave appphone or tablet at the bedside1BluetoothLarge-volume channelmaintenance fluidSyringe channelpropofolTwo-channel infusion pump, connectedAI MedAgentin the cloudReasons over the pump,the brain and the recordHospital record and pump gatewayorders, the medication record,what each pump reports1EEG measures up4alert down: possible brain event2what wasdelivered5order to the pump (PCD-03)the nurse confirms at the pump3pump record5suggestedchange
Concept only. The pump is drawn generically: a syringe channel running propofol and a large-volume channel running maintenance fluid, as on the connected pumps I worked on.
  1. The brain. The headband sends EveryWave’s measures to the app at the bedside, and on to AI MedAgent.
  2. The pump. A connected pump already reports the drug, the concentration, the rate and every start and stop to the hospital.
  3. The record. AI MedAgent reads the pump record and the medication record beside the EEG.
  4. The alert. When the brain is not doing what the pump says it should, the app and AI MedAgent raise a quiet flag: a possible brain event, worth a look. It is a prompt to look, not a diagnosis.
  5. The order. If a change in the infusion makes sense, AI MedAgent suggests it. A clinician accepts or declines. An accepted order travels to the pump the standard way (IHE transaction PCD-03) and the nurse confirms it at the pump. Nothing in this picture programs a pump by itself.
What is real and what is not. Connected pumps and order-to-pump programming with a nurse’s confirmation are in use today. The AI MedAgent demonstration exists, on a simulator. The headband exists as a design. The three working together is a drawing. The tests above are the only evidence so far, and they say this is worth studying, not that it works.

Where it belongs

A phone is a good way to prove an idea and a poor place to leave a monitor. An anesthesiologist watches one screen and charts in one record. If EveryWave is worth building, its numbers belong on the anesthesia monitor and in the anesthesia record, which in many US hospitals means Epic.

Monitor values reach that record today through the hospital's device integration, using a published standard (IHE Devices, transaction PCD-01). The monitors on the market already do; NeuroWave lists Capsule connectivity for the NeuroSENSE. EveryWave would have to arrive the same way. That is real work, and it should be planned from the first day, not added at the end.

Where to start. Not with every patient. The large trials have not shown that EEG-guided anesthesia improves outcomes across the board (BAG-RECALL 2011, Balanced 2019, ENGAGES-Canada 2024). The one place a national standard says this monitoring should be used is intravenous anesthesia given with a muscle relaxant, where there is no exhaled gas to measure and the pump only estimates (Association of Anaesthetists, 2021). That is also where the pump record and the brain have the most to say to each other.

Questions for you

You have watched this field longer than most. I would value a blunt answer to any of these.

  1. Why has EEG monitoring not become routine? It has been available for thirty years. Is it cost, evidence, training, workflow, the fact that nobody is paid for it, or that the number is not trusted?
  2. If the disposable cost $1.55 and there were no cable, would you monitor more patients? Which ones, and which would you still leave alone? What does a sensor cost your department today?
  3. Is a phone or tablet acceptable as the display in your operating room, or is anything outside the anesthesia monitor and the record a non-starter?
  4. Would seeing left against right change anything you do? In which cases?
  5. Do you want the waves, or one number? Would you read the raw EEG and the wave display, or does a monitor without a single index go unused?
  6. What would you need to see before trusting a depth number from a new device? Ours agrees with BIS on recordings and has never touched a patient. What is the bar? Would a range set for the drug and the patient be more use to you than one band for everyone?
  7. Is ease of application worth five electrodes instead of one strip? Would your team accept a reusable band on the forehead?
  8. What did I miss?
Send me your answers