Danger, Will Robinson!!! or injury prevention with sensors and algorithms

Health is determined by many factors including:

• Behavior (Physical Activity, Eating habits, Tobacco or substance abuse, responsible sexual choices, etc)
• Mental Health 
• Injury and Violence 
• Environmental Quality 
• Preventative measures such as immunization 
• Access to Health Care

All these factors are quantifiable, predictable and preventable. Injuries are most likely to be  perceived as “accidents” and “acts of fate”,  but they depend on the same determinants as other health factors: individual behavior, social and physical environment.  The likelihood of injuries -  unintentional ones and those caused by acts of violence - can be computed from physical location (estimations for USA¹ are a good example), gene-environment interactions², prior medical history, and physical traits³.

There are many ways to prevent injuries - just say "no" to risky behaviors, wear preventative gear while playing sports or fall-optimized shoes for elderly, watch out for others engaged in similar activities... Yet, sometimes we forget to watch, don't have access to histories of others or get diverted.  Would a body sensor or a gadget with smart software be able to warn us about potential accidents ahead to help prevent accidents?  What would it need to measure?

Software and devices automatically detecting and reporting accidents already exist:

Halo Monitoring's fall detection system, for example,  consists of a chest strap and belt clip with motionOnStar or mbrace that "intelligently integrate the driver, the vehicle and the environment" - capabilities such as this will be provided in the area of next-generation health management systems like Aurametrix.
sensors, heart rate and skin temperature monitors. Although the system detects falls only after they happen, a study showed that just the fact of wearing it increases alertness of seniors and reduces the number of falls. Although fall detection systems are not as advanced as telematics for cars - like
Unprecedented accumulation of data  - such as snapshots of driving behavior or 1.2 million person-years of hip fracture observations (Kanis JA) allows development of smarter software able to predict injuries.  Logistic regression models (Kononen et al., 2011) predict seriousness of auto accidents,  first-principles mathematical models (such as AHAAH for the ear) connect forces with injuries, neural net and other data mining approaches foretell which juvenile offenders are likely to return to crime (source of  "intentional injuries"), or allow to calculate risk of fractures based on milk intake, personal history of accidents and body mass index. Self-quantifiers such as René Ghosh are able to figure out how to use their own data to predict future injuries. Using simple math (Riegel equation bringing all running logs on to a comparable level) and trend analysis, he tied his accidents to wanes following waxes in running performance. Researchers keep refining the variables predicting injuries.  Swanenburg et al., for example, predicted multiple falls for those with a history of multiple falls (odds ratio, 5.6) and use of multiple medications (odds ratio, 2.3). And there is another simple measurement of standing position helpful in prediction. Frequent fallers, indeed, have a narrower stance width than non-fallers.


In the always-connected smart-sensor-equipped future, things such as Intel's magic carpet - picking up the weight, angle and pressure of steps - will be a commodity. Gene tests predicting injuries will be integrated with data coming from our carpets, clothing, footwear and location information. And this may be sooner than you think.


References

1. Centers for Disease Control and Prevention (CDC), National Center for Injury Prevention and Control. Web-based Injury Statistics Query and Reporting System (WISQARS); 2010 Mar 4 Available from: http://www.cdc.gov/injury/wisqars/index.html

2. Husted JA, Ahmed R, Chow EW, Brzustowicz LM, Bassett AS. Childhood trauma and genetic factors in familial schizophrenia associated with the NOS1AP gene. Schizophr Res. 2010 Aug;121(1-3):187-92. PMID: 20541371

3. Swanenburg J, de Bruin ED, Uebelhart D, & Mulder T (2010). Falls prediction in elderly people: a 1-year prospective study. Gait & posture, 31 (3), 317-21 PMID: 20047833

4. Kononen DW, Flannagan CA, Wang SC. Identification and validation of a logistic regression model for predicting serious injuries associated with motor vehicle crashes. Accid Anal Prev. 2011 Jan;43(1):112-22. PMID: 2109430

5. Price GR. Predicting mechanical damage to the organ of Corti. Hear Res. 2007 Apr;226(1-2):5-13. Epub 2006 Sep 15.PMID: 16978813

You are the Chosen One, at least by your bacteria

Host genomics is not the main decision-making factor for bacteria immigrating into human body, but  it is an important factor. Two papers recently published in the Proceedings of the National Academy of Sciences help to understand why you are chosen and how the choosers make their decisions.

Benson et al studied microbes of mice C57BL/6J, HR and their offspring. BL6 is a common inbred line prone to diet-induced obesity, type 2 diabetes, and atherosclerosis. They also develop age-related hearing loss, if are not following recommended dietary allowance. High runner (HR) mice is lean and fit and loves to exercise - it's in the genes.

Noninvasive 16S RNA sequencing (Roche 454) showed that the abundance of microbes in "core measurable microbiota" depended on 530 host SNPs, mostly those located in 13 quantitative trait loci and was influenced by 5 more QTLs.

Some of the genetic regions appear to determine what kind of bacteria immigrate and strive in the host, other regions influence the immigration rate, attracting a wide variety pf or specific nationalities. Supplementary material elaborates on  sources of variation and genotype frequencies at given SNP locations. 

How are bacteria making their decisions to colonize or not to colonize?

In another PNAS article, Ben-Jacob and Schultz explain why microbes could be smarter than humans. We may think that our decisions are well thought and sophisticated, but we are, indeed, influenced by other people and our over-interpretations of other people's reactions. Bacteria can assess the noisy and stressful environment around them more objectively and rationally. They anticipate possible drastic changes in the environment and find the best decisions by providing every bacterium with the freedom to choose its own fate. This may look like throwing dice, but the colony manages the odds and effectively programs the effect of the noise on the gene circuit performance.

Our genes may be shaping microbial communities that could, in their turn, control our physical and mental health. Yet our lifestyle choices could break the patterns and let us decide what types of bacteria we want to live with.

And for those whose fight against unwanted microbes is too hard, there may be light in the end of the tunnel: Personal Genomes project has just announced a new collaboration with Rob Knight and Noah Fierer that will enable to explore the microbial diversity of various habitats of the human body and correlate it to the genotype.

References

• Andrew K. Benson,, Scott A. Kelly,, Ryan Legge,, Fangrui Ma,, Soo Jen Low,, Jaehyoung Kim,, Min Zhang,, Phaik Lyn Oh,, Derrick Nehrenberg,, Kunjie Hu,, Stephen D. Kachman,, Etsuko N. Moriyama,, Jens Walter,, Daniel A. Peterson,, & Daniel Pomp10.1073/pnas.1007028107 (2010). Individuality in gut microbiota composition is a complex polygenic trait shaped by multiple environmental and host genetic factors Proceedings of the National Academy of Sciences of the United States of America, Published online before print October 11, 2010
• Ben-Jacob E, &; Schultz D (2010). Bacteria determine fate by playing dice with controlled odds. Proceedings of the National Academy of Sciences of the United States of America, 107 (30), 13197-8 PMID: 20660309

Predicting catastrophic health events - noninvasively and short term

"I've just picked up a fault in the AE35 unit. It's going to go 100% failure in 72 hours". These were famous words of the almighty computer HAL in "2001: A Space Odyssey". Few of us believe too much in software forecasts - be it weather, earthquakes or computer hard disk failures. Yet, we all know that sometimes it works. And such systems are very valuable, assuming they continuously improve.

Word cloud generated from QS #15 intros

Wellness is always a common theme of the many presentations and experiments of Quantified Self enthusiasts - citizen scientists quantifying everyday life in order to improve it.  "Health" was the most frequent word among the two-word introductions of QS #15 attendees, followed by variations of sleep and happiness, and ways to measure and understand it.
Are health failures predictable?  Nobody argues they are, although most available services  - such as genomic testing - provide only long term predictions.  Biomarkers that scientists are interested in are obtained through invasive or costly interventions - like blood proteins or intracranial electroencephalograms. Technologies such as Mobile Cardiac Outpatient Telemetry™ (MCOT™) developed by CardioNet  are based on real time EKG focused on heart rhythm abnormalities that can't be detected in small 24 or 48 hour windows. These relatively rare events are correlated with symptoms and used for diagnostics.

Your husband just died, … here’s his black box
(from Gordon Bell's presentation)

Perhaps in the future every one of us will leave a black box holding all the truth about our health, helping next generations to better maintain, test and repair their bodies. Many lives have already contributed to the understanding of causes and effects such as the link between cholesterol levels, diet and heart attack. But what about the short term prediction horizon,  like the 72-hour window of HAL or 30 seconds to 15-to-45 minutes warning by seizure dogs?
Could computer luminary Gordon Bell predict his heart attack if he wore his heart monitor strap while bicycling?  A cardiologist would say "no way", but maybe sometimes it's better to keep quantifying and experiment despite of what medical establishment has to say?
Data from the Women’s Health Initiative study (129,135 postmenopausal women observed over a period of nearly eight years) show that a woman’s resting heart rate may be a good indicator of her risk for a heart attack. Hsia and others (2009) found that women whose resting heart rate is more than 76 beats per minute are significantly more likely to have a heart attack than women with resting heart rate less than 62 beats a minute. This risk factor is particularly strong for women between the ages of 50 and 64, less so for women over the age of 65. (Trial NCT00000611)

Of course, women have different kinds of heart attacks than men do. They are more likely to die from a spasms of heart and the blood vessels leading to the heart, and are more likely to complain of fatigue and sleep disturbances in the weeks and months leading up to a heart attack. Sleep disturbances and decreased physiological differences between day and night are increasing heart attack and stroke risks for males too, at least for shift workers. Exercise tests  - known for their false positive results - have better cardiovascular prognostic value for smokers with high cholesterol than healthy men.

Finger arterial pulsatile volume changes or finger blood flow - related to blood pressure - is another medium-to-long term predictor of pending cardiac events. A simple, noninvasive finger sensor test called EndoPAT  can predict major cardiac events such as a heart attack or stroke for people who are considered at low or moderate risk.

AngelMed Guardian System (inventor: Dr. Tim Fischell) is an early warning system - telling 24 hrs to a week before if heart attack is coming. Average time between the cardiac event and hospital arrival is 3 hrs, and about 5 hrs before the surgery starts. By that time 90% of muscles could be dead, so 5 or 10 minute warnings could save lives.  Unfortunately, Guardian is highly invasive - sized as an iPod, it is implanted directly into the patient's chest, monitoring electrogram  waveforms and other crucial heart-signal data 24-7.

Many portable oximeters and ECG are already in the market - and even though consumers are complaining about noise and difficulties in getting readings of diagnostic intervals, the technologies will continue to improve and self-quantifiers will be finding solutions for better health.

REFERENCES
Hsia, J., Larson, J., Ockene, J., Sarto, G., Allison, M., Hendrix, S., Robinson, J., LaCroix, A., Manson, J., & , . (2009). Resting heart rate as a low tech predictor of coronary events in women: prospective cohort study BMJ, 338 (feb03 2) DOI: 10.1136/bmj.b219


Mayo Clinic (2009). High resting heart rate could predict heart attack in women. Mayo Clinic women's healthsource, 13 (7) PMID: 19498326