It was 15 years ago this week that my son Chase Cringely died of Sudden Infant Death Syndrome (SIDS) at age 74 days. I wrote about it at the time and there was a great outpouring of support from readers. Back then, before the advent of social media, parents didn’t get a chance to grieve in print the way Mary Alyce and I did. We shed a light on SIDS and, for a couple years, even led to some progress in combating the condition, which still kills about 4,000 American babies each year.
When you lose a child, especially one who dies in your lap, as Chase did with me, you can just curl up and die yourself or you can try to fix the problem. With the help of readers all over the world I tried and failed to build a practical SIDS warning device with the idea of not curing SIDS, but avoiding it. You see the syndrome only lasts for about 11 months, from age 1 month to one year. And while events such as Chase’s can’t be made not to happen, with proper detection and the simplest of alarms the baby can be literally roused out of death.
Alas, in 2002, while we knew what we were looking for, the cost of a proper warning device was just too high for the market to bear at that time. We used ex-KGB biometric monitoring technology that worked but pretty much required a PC (or a hefty FPGA) to work and the market definitely wasn’t ready to pay for that. And don’t get me started on the FDA, which was useless.
But times have changed and I realized tonight talking about it with my surviving children that we’re now in an era where a cloud SIDS alarm is really possible. I’m too old to build one so I’m going to tell you how to do it if you want to carry that torch.
I think the perfect platform for a cloud SIDS alarm is a $49.99 Amazon Echo Dot virtual assistant. I suspect an unmodified Dot would do the job, though it requires running a SIDS Alexa app that has yet to be written.
The goal of the alarm is to monitor the sleeping baby’s heart, detect a SIDS event, then set off a very loud alarm to rouse the baby because waking Mama often doesn’t work. So the Dot will be listening for the baby’s heart, monitoring its pattern, then blasting a loud noise if SIDS is detected. I know I just wrote pretty much the same thing twice but the sequence is that important.
Don’t use this Dot for anything except as a SIDS alarm. If you want it to play lullabies or act as a regular baby monitor, then buy another Dot for that. Place the SIDS Dot UNDER the crib, upside down attached to the mattress with velcro. Though the heartbeat sound has to go through the mattress to the Dot, it’s often quieter under there and sometimes the mattress springs will sympathetically vibrate, making detection easier.
We have to increase the accuracy of the microphones in the Dot. The technique is to use all seven microphones individually to detect the heartbeat, comparing them to each other and sampling over a sliding window of 5-6 seconds of time to properly identify the right sound. A software band-pass filter might help, too. This process is essentially an audio version of what’s called “super-resolution” in video processing. We want to isolate that little heart and really listen to it.
Now you’d think that detecting SIDS once you can hear the heart would be as simple as setting-off the alarm whenever you no longer can hear it. Nope, that won’t work. Maybe, instead of the baby dying, it’s just been moved to the changing table. You don’t want to set off a 120 dB siren every time you change a diaper!
Fortunately there’s an easier way to detect SIDS, but you have to know what you are listening for. The American SIDS Institute (today in Naples, Florida, but in our day it was in Marietta, Georgia), has an audio library of SIDS deaths that actually happened while on a heart monitor. Remember what I said about parents being too tired to hear the alarm? Sadly the Institute has quite a selection of SIDS deaths to choose from and analysis of those deaths shows there is a characteristic slowing of the heart prior to a SIDS death. In every case the pattern (the rate of deceleration) is the same and the result is that death can almost always be predicted several minutes before it actually happens. That’s plenty of time to intervene, IF you know to do so.
So the Dot listens not just for the baby’s heart but especially for that characteristic slowing pattern. Only then does the loud alarm go off. And with the Dot right under the baby, that should be enough to save the day.
Now somebody go out and build that app!
Chase would thank you. I thank you, too.
I would want such a device to emit some confirmation (acoustic or optical) indication when it re-acquires the heartbeat signal of the baby (after, e.g. a diaper change). Without that you’ll never know if the device is (still) guarding your baby. I am not familiar with the Amazon Echo Dot; maybe it has some LEDs that you could use for this.
is an echo the best fit here? I love my echo but it is far from fallible, especially if more sounds compete for her attention, which feels like a bigger problem the more sensitively you tune the mic which would surely be required for detecting a baby’s tiny heart beat. Fallibility here means false alarms and I don’t know how many of those terrified parents would cope with before disabling the feature and 1 star reviewing the app.
When our daughter was in that vulnerable window we had a baby monitor with a sensor that sat between the mattress of the crib and some plywood. It was incredibly sensitive and I’d see feedback for just gently running my fingertips over the mattress. If this sensor felt nothing for 10 seconds it warned a pip, at 30 seconds the alarms blared. The pip typically sounded if we forgot to turn it off during feeds/changes so far from fully automated. But we had ZERO false alarms.
I feel iterating over this design to remove the manual steps (more automated) is a better endeavor than taking something like the dot way out of its comfort zone where there is surely way more margin for error.
Cheers
Does waking the baby actually work to prevent death? You stated something that made it seem so, but I have not read up on this so do not know. If that is so, maybe a wearable device, like a mini-Fitbit would be a useful tool here…they (or a different wearable) should have enough sensors to detect the slowing heart rate and either buzz/vibrate to wake the baby, emit an alarm (loudness compromised by size) or trigger an alert on other devices….or all of the above.
With the tech available today, it seems ludicrous to me that this situation is not easily solved, or at least improved.
I think using something like angelcare baby monitor as a starting point would be better than the dot. It is a big pad underneath the matress with a monitor. We used it when our kids were little and it worked great. Now their kit is designed to detect lack of movement. Not sure if it could be used as is or would need to monitor the heart directly.
Yeah, we used the Angel Care under-mattress mat. It went off a few times – once when our daughter scooted all the way to the edge of the mattress where it didn’t recognize the movement and then after she figured out how to get out of her crib. We used that for years with our son to discourage him from getting out of bed and playing at night.
I didn’t know about your son and am truly sorry. I’ve known other SIDS parents and would like very much for there to be effective and inexpensive warning systems. I think technology will get us there. Amazon Echo could be a good path forward.
As one who works in technology I am also disturbed by the regular reports during summer months of infants and toddlers left in overheating cars. Could technologists please develop an effective warning system for this also? I’m thinking something that 1) detects presence of passengers, 2) monitors for dangerous temperature, and 3) calls police, others, honks the horn if conditions 1) and 2) are met. Can’t engineers do this with a handful and few dollars worth of parts?
I can’t find such an audio library but would like to look into this more… can’t find performing a search on sids.org nor just a general google search for SIDS deaths audio library, etc. keywords.
Has anyone found this audio library?
“I’m too old to build one so I’m going to tell you how to do it if you want to carry that torch.”
This is a terrible time to bring this up: Are you also too old to reply to your Kickstarter? Too old to be responsible for funds you were supplied? Too old to demonstrate to your children how dad takes action for the delays?
You are truly, truly insane. You really need to get professional help.
While even I feel hesitant about bringing MineServer up on a post about children dying (old people dying is okay), I do agree that @NA has a very valid point.
.
The issue of SIDS is no laughing matter and I cannot fathom how much pain that must have caused you nor would I wish it on anyone. That said, how can you make a comment like “I’m too old to build one” after just accepting $35k to seemingly do a similar technical challenge?
.
I want to be on your side on this matter, especially on this post in particular, but you’re making it very difficult. Every time I start to feel a bit of humanity for you and remorse for my actions (which isn’t much), you have more verbal diarrhea and I remember that this could all go away if you stopped taking the hours to research and write these posts and just wrote in the comments here or on the KS site:
.
“I f’ed up. No MineServers are coming. I know sorry doesn’t excuse me, but I AM sorry. There are no remaining funds and I dipped into my own pockets to try to rectify this months ago, but it didn’t work. No refunds will be given, nor will I be shipping what’s left of the product. I’m sorry. Can we all move on from this?”
.
If you did that, 95% of us would take a moment, absorb, be a little annoyed, but ultimately we’d accept that and go away. Why is the 5% that won’t scaring you from addressing us? Just put an end to this, because you know we aren’t going to. Is this really how you want to spend the remainder of your career? Is this the image you want to present to your children about how to conduct yourself? I sure hope not, but you have yet to react in a way that seemed predictable/sane, so I’ll try not to be surprised when you continued to do nothing and hide behind your blog.
.
I’m sorry for your loss – SIDS sucks. But ultimately, so do you. If you think otherwise, prove it.
Yeah, this is my stopping point. I’ve followed Cringely to PBS and then pleaded with him to keep going after PBS, but time to get off the train. I didn’t invest in MineServer, but I did write to him and ask him to address it because I’m tired of the forums getting filled up with people complaining. But his failure to do so makes me wonder why I bother. I shouldn’t. We shouldn’t. It’s time, people, to let Cringely go.
I agree with your general point, that he should man up and do something about the kickstarter.
But this specific post is not the place to bring it up. Nor was the previous post, an obituary. Next time he talks about random tech BS, go for it. but god, man, show some decency.
Before you argue that bob isn’t showing decency by ignoring your entreaties, STFU and man up yourself.
Here’s an interesting take on why Bob’s been silent on the Mineserver issue. The obituary post you mentioned would normally receive less than 20 comments, but thanks to Mineserver, it’s up to 64 and counting. The Mineserver complaints will significantly increase the number of comments, until such time as Bob passes on the torch, at a higher price than he would otherwise. So no matter the subject matter of the comments, we are all contributing to Bob’s retirement fund.
I did a brief review of the Echo Dot development environment, and concluded it would not support this type of application out of the box. It would likely require hacking the Dot hardware to load custom code. Not impossible (probably), but it’s certainly more difficult than writing a standard Dot app the way Amazon expects you to.
I’d think that one of the various under-the-mattress HRM systems like, for instance, the one Withings makes would be a good platform to build this sort of a device off of. I’m no engineer, but it seems like those are sensitive and accurate enough that the hard part has been done, and the pattern detection / alarm triggering part would be relatively straightforward.
Ask Amazon to develop one? MASSIVE upside for them …?
I am so sorry for you loss, and how your post must be dredging up the memory of that horrible time.
From your post of 15 years ago:
“In the neonatal intensive care unit, where Chase spent his first few days, there are lots of monitors and they go off when they detect apnea — a cessation of breathing lasting for 20 seconds or more. Chase had a problem with apnea. Twice he turned blue right in my arms, simply forgetting to breathe.[…]
But to the medical establishment, apnea isn’t SIDS. If apnea is falling asleep at the wheel and driving off the road, SIDS is falling asleep at the wheel and driving into a bridge abutment. The doctors tell me leg shaking won’t end a SIDS attack and monitoring won’t detect one.”
Now you seem convinced that monitoring can detect a SIDS attack, and that a loud noise will end one. Has the technology of monitoring and counteracting a SIDS attack changed? Where can we read about the successful remediation of a SIDS attack? And I’d also like to examine the audio traces you refer to, but they don’t seem to be on the SIDS site.
I’m sorry to ask for such detail, but did Chase turn blue in your lap when he died? Maybe a monitor of skin tone/color is what would catch it?
Would a doximeter work, checking blood oxygen levels?
So if I understand, what you’re trying to detect is a recognizable slowdown in heart rate.
I wonder if a thermal imaging camera could pick that up. Hm, a little searching tells me someone else has been thinking along those lines: http://www.cv-foundation.org/openaccess/content_cvpr_workshops_2013/W13/papers/Gault_A_Fully_Automatic_2013_CVPR_paper.pdf
Here’s the problem I see. Is SIDS something that can be identified beforehand as a risk factor?
If every baby has a small one in a thousand chance, then are people really going to spend $50 to eliminate it?
And the chance is probably less than that, with things that are not SIDS likely being classified as that afterwards.
That issue of spending $50 to eliminate exactly one rare problem can be addressed two ways I can think of:
1) Make the device something you *rent* (or borrow) instead of buying, for much, much less than $50.
2) Make the device have other functions. To come back around to maybe using thermal imaging, a thermal imaging baby camera with computer vision processing could also detect, for example, a fever, and possibly many other conditions.