CureHunter is a web accessible, fully integrated scientific search, data retrieval and analysis engine. Developed by a team of scientists with expertise in medical data mining, artificial intelligence software development, computational linguistics and computational biology, CureHunter “reads” the entire U.S. National Library of Medicine Medline Archive and automatically extract and quantifies the evidence for successful clinical outcomes of all known drugs for all known human diseases.

Hope had an opportunity to talk with Judge Schonfeld, CEO and Chief Scientist of CureHunter. In part II of their interview below, Hope focuses on the users and uses of CureHunter; Judge discusses the differences between CureHunter and Wolfram|Alpha, and compares search results from CureHunter to novo|seek, GoPubMed and PubMed.

The Interview, part II

One of the things I have noticed in the field of medical search is that some of the companies refer to their products in several different ways. For example, novo|seek calls itself both an information extraction system and a search engine for biomedical literature. How does CureHunter differ from novo|seek? On your site you refer to CureHunter as a discovery engine. How does that differ from an information extraction system and how does CureHunter differ from the much hyped Wolfram|Alpha, which calls itself a computational knowledge engine? And GoPubMed uses the term, “knowledge-based search” and talks of “using a domain ontology as structured background knowledge.” Please help us understand all of these arcane matters.

In general, the newer semantic and Web 2.0 search technologies are moving toward seek, read, and extract models — as opposed to just listing supposedly relevant articles using classical KWIC indexing methods to find the “relevant ones.”

The more powerful ones are moving toward the “answer system goal” of the instrument makers under the assumption that there is really something specific you want to know when you carry out a search.

Obviously now that was one of CureHunter’s original design goals: machine tell me which drug has the highest probability of curing me — based only on the body of the peer-reviewed evidence.

Whether or not an individual engine reaches its goal depends on many design factors and the fundamental capabilities of the engineers and scientists who create the system and the data to which they have access.

Everyone may have access to a major public library, that does not mean everyone has read all the books in that library with intelligence and learned from their readings. The same is true of many medical search engines claiming to read PubMed.

How do they define the goals of the readings — write the engineering specification — in the first place and the problem(s) involved in reaching the particular goal. What are they going to measure to prove system design success: accuracy, precision, types of error, global margin of error, false positive or negative return rates, reference instruments to compare.

All these QA modules were built for CureHunter because we designed it as a virtual instrument that had to be testable. The machine had to generate hypotheses that humans could validate or invalidate. And finally it had to make numerous predictions based on its internal models that could be readily checked both by human experts and canonical texts.

Generally, speaking when you run a Google or medical domain search, you have no idea if the information is all good, all bad, or a giant helping of both — but routine usage usually proves the last case. So, Google, while an incredible tool is not a precision instrument producing replicable, testable results and neither are so called Medical Information engines, even though they have domain advantage over Google.

Right now, I think novo|seek, NextBio, and GoPubMed are all doing a much, much better engineering job than Google or Microsoft or Yahoo on improving functional health search by beginning to relate sub-component ideas that help define the cluster of information that is any particular idea.

I personally find them very similar in their models and methods to each other and less so to ourselves. They are really trying to enrich key bio med concepts by cross-linking in the manner of Wiki a lot of related topical information. For example, if you look up a gene, you might want to know what diseases it is associated with and what does the gene express; so you cross link the expression databases from Entrez. Same with chemical pathways, JMOLS, etc.

Two weeks ago I had a discussion with Professor Dr. Phil Bourne at the UC San Diego Supercomputer Center and Skaggs School of Pharmacy on the possibility of cross linking the protein data bank directly to CureHunter to fine focus on protein-protein interactions leading directly to clinical cures. [Dr. Bourne is the Associate Director of the Protein Data Bank] That’s a natural problem for our technology and on our development glide path, same for gene expression data. Almost three years ago Dr. Anthony Williams, founder of ChemSpider asked us if we would directly tie to his engine for all the right and similar reasons. I hope we get to work with his team shortly as well.

When you get enough of those points selected by the machine correctly — like a fingerprint match — it knows it has found its goal idea to a predictable level of certainty. All the points of the graphs are guiding you there.

I think, generally speaking, CureHunter is at the very bleeding edge of graph theoretical ontology models because we built it based on computational linguistic models founded in a lot of knowledge about many languages and how they work to construct new ideas from their own lexical networks.

I talked to Stephen Wolfram early on, two years ago about Wolfram|Alpha, and was an early tester on it for him. I was a big fan of NKS and still am. I really like the way Stephen thinks about problems and you can see we are in sync on this idea of not just finding valuable information but in making it directly computable.

Mathematica is such a rich product, some days I wish I had nothing to do but play with it. The Wolfram Alpha demo site is a great toy for any scientist … toys that will lead you to powerful new analytic applications and visualizations of complex data.

Many of the CEOs at major software houses at first saw the web as their enemy because boxware and shelfware had to move to online formats and that played havoc with many traditional software engineering considerations: architecture, modeling, delivery, data integrity and licensing revenues. All of which are still a big problem for the high quality information publishers who are losing control of their IP/data assets to the Internet free information and open source forces: Elsevier, BMJ, Wiley, Wolters, Thomson, McGraw Hill.

We don’t ever want to lose high quality, human edited, carefully documented, source controlled scientific publications. The web already has way to much noise to signal ratio on it and it is getting harder to tell the science from the chaff all the time.

Wolfram|Alpha is the real deal. It will be harder to use for most people than other types of search and answer tech because it is essentially mathematics-based. Its NLP is not as good as it needs to be, but again that’s sort of like saying those first PCs were junk. No. They were fantastic because they gave us a new way to think about the world and making that world computable … which, of course, is what we are all doing more of every day as we convert more and more analog and verbose source material to digital form.

So short answers to feature definitions:

Extraction = function were a set of measurable results with question-answering data is taken from or filtered out of the source articles other than simple citation facts or counts of total articles.

Knowledge Engine = algorithms can generalize over results to some degree even if stated somewhat differently and group related notions other than those that are simply keyword or key phrase matches. Knowledge relationships may be defined by canon, ontology or custom algorithms of the provider.

Semantic Web = some ability to resolve synonymous ideas when phrased or spelled differently; may include thesaurus-like filtering; some ability to understand the value of the returned content in terms of closeness of fit to the query intention.

Data Mining = some extraction functions and implies extraction functions enabling precise quantities of desirable substance to be retrieved from the mass of the search (the raw earth text). In one graphic we show CureHunter finding the GPS location of gold ore in random hills, measuring the density of the deposit, extracting the ore, assaying its purity, and turning it into a ring on your finger: The Cure. So how far does the system take you is a key question for data miners. And what is the purity of the mined element of value. How does it assay out in terms of answering real questions or solving real problems.

Discovery = also some data mining capability; implies ability to find data that no one knows is actually there or to connect extracted material that has increased value when related to another subject in the domain but which the user did not query per se. For example, a lot of health info programs list “Experts.” CureHunter lists experts, but only those whose papers were cited because their experiments had achieved a significant clinical outcome; and thus the data in their papers could be cross computed with the data from other papers of a similar expert nature — and they could be life changing when facing a deadly illness. The graphs in CureHunter cross link diseases that share effective drugs to provide greater understanding of utility and mechanisms of biological action. CureHunter discovers unsuspected connections and suspected connections and links them with known good connections that reinforce our knowledge of the whole cluster point.

Let’s try the search term, “warfarin” as an example — please tell us how to search in CureHunter, novo|seek, GoPubMed, PubMed and Wolfram|Alpha for that term and what we could best find using each.

Well, let’s try it:

CureHunter = Canonical definition, and list of numerous chemical, brand and trade names for the drug identifying it in the literature source, MeSh Breakout hierarchy for all chemical forms; list of 590 diseases where it has clinical utility broken out by specific statements of clinical outcome and statements from formal trials where warfarin was used. Related drugs indicated that also work on the target disease and the history and sources for all statements. The interactive network graph showing the nearest neighbor link by 5 degrees of separation with visual weighting for the most tightly clustered functional biological factors.

novo|seek = List of articles to read, not specific extractions; list of related categories of information with some bar graphs showing relative volume of information available , e.g. Genes and Proteins, Signs and Symptoms, Organisms, etc.; related information, however, is not linked to specific source article, disease, treatment, cure or outcome … so utility compared to CureHunter’s is not really comparable, although its good information to have. Links are casual, not computable.

GoPubMed = Articles list fairly good, but not comprehensive. Order by date sort, not clear why selected other than they contain target drug name. Some key statement extractions — not consistent from one search to another: not at all clear as to why the particular extracted statements were chosen or conclusion to draw from them? Term frequency distributions, knowledge base breakout of related information by categories: e.g. Organisms, Psychiatry and Psychology, Proteins, et al. Seems a little bit of a laundry list of where you can also find references to the parent term although some are very valuable depending on what context you are trying to understand vis-à-vis warfarin. Lot of good citation and additional breakout information. Good clean design. I think GoPubMed is a useful resource but it is not clear to me that you can compute anything very valuable from it directly or discover anything in it that you can’t also find somewhere else.

PubMed itself = the mother ship. NIH, NCBI, NLM have worked for years to maintain carefully edited and source controlled data. Their work is critical for CureHunter and all the rest of the neo search technologies. If you sample from this source you know you are drawing from a good well. By constantly upgrading from ASCII to HTML and XML and beyond and driving data and taxonomy standardization, the library directly and indirectly enables new levels of computability. What they aren’t doing is data mining and discovery; that’s still the job of end user specialist scientists and teams like CureHunter.

One of the things you said during our phone conversation that I found quite intriguing came when I asked you who your competitors are and what products are comparable to CureHunter. You replied stoutly that there really aren’t any comparable products. Could you elaborate? What makes CureHunter unique and who in the medical field should take a serious look at it? Chief medical information officers? Registered health information administrators? Would it be of interest to those in the field of nursing informatics?

CureHunter is different from all the others: its fundamental design is as a scientific instrument seeking to make medical knowledge directly computable and consistently quantifiable and testable and predictive.

That isn’t to say we are smarter than all the other really good companies engaged in medical information. There are many informative, useful, richly advanced search and CDSS products in Medical Informatics and Bioinformatics that are enhancing health care treatments and delivery.

There are 10,000+ health information sites on the web, many of which meet the honor code standards for quality and accuracy of the information they dispense.

But if you have been taking the standard drugs for years and not getting well, or someone has told you there’s nothing better for your chronic illness, or God forbid you have been given a diagnosis of terminal disease — you ought to look at CureHunter right now — because it will have gathered and measured all the best drug data for you.

If you are a doctor and want to practice evidence-based medicine and just can’t keep up with data overload, you owe it to yourself and patients to have a subscription to CureHunter for the cost of less than one professional journal per year.

If you are an administrator, payer, provider or insurer or on a formulary committee, there is no more objective or complete body of instant meta-analytic data available to you anywhere than CureHunter. You should have a subscription to our evidence monograph library and a site license. You will save thousands of dollars a year by knowing when a generic is just as good as a branded drug or which branded meds are best or which ones have the best chance of improving patient outcomes. You will add safety, efficacy, and cost control to everything you do.

CureHunter is the only scientific system on the web that can actually compute directly from the evidence the drugs with the highest possibility of making a person well and it does so with one mouse click — not endless user hours of browsing article, after article, after article.

CureHunter is the only information system that can write a source documented report on demand, just in time, and up to date to the hour of all the drugs that cure an illness or show hope and promise of curing it in the future. The only one that computes the relativistic efficacy of all such drugs.

That’s the content in the Patient Physician Summary Report downloadable from the site in the form of a disease-specific monograph on the patient’s illness. Graduate researchers could spend years compiling such a report and analysis by hand — that they can now get in 10 seconds for $24.00. (Ok, that’s with fries and a coke, med students).

CureHunter is certainly and last but not least, the only machine of its kind in the world that can autonomously compute new cures for human disease and has demonstrated that capability in advanced scientific settings such as US National Science Foundation Conferences and Canadian conferences and proprietary laboratories at major pharma. Any medical teaching center or pure research organization within a pharmaceutical organization should have CureHunter available to all their researchers because it can dramatically speed up their achieving new results and extended uses for the molecules and compounds they are studying. Universities that seek to develop and license new meds should definitely review their portfolios now as they may discover with CureHunter significant new clinical applications and revenues for the substances they have already researched. It’s as simple as entering the name of the key agent in the professional pharmaceutical search system.

Thus CureHunter is uniquely functional, up to date, and technologically advanced way beyond other tools that seem similar on the surface because they index articles from Medline. CureHunter reads the articles. Understands them to a significant degree and makes discoveries based on its readings, just like a bright human would. Many doctors have said quite astounded on first seeing the engine in action: “How does it do that?” or as Arthur C. Clarke wrote … any technology significantly advanced will appear like magic.

As we know, the Obama administration is pouring money into the development of healthcare IT but is also stressing the concepts of “meaningful use” and also of “comparative effectiveness.” Can you discuss those concepts and explain why healthcare administrators (who, after all, hire the IT guys, the medical librarians, the informaticians, etc.) would want to look into CureHunter?

If you use CureHunter’s on demand evidence functions to reduce the use of ineffective, over marketed, unsafe and adverse medications in a routine way at the point of patient treatment, IT managers can take their cost center and turn it into a profit center for better care. Nationally we have estimated we could save the health care system $20 billion per year if CureHunter Evidence Checks were standard operating procedure.

A very small amount of engineering pipes CureHunter directly into any major EMR. A great first step for President Obama to take would be to ask Dr. Zeke Emanuel to help us build CureHunter into VA Vista/CPRS [the Department of Veteran’s Affairs electronic health record, Computerized Patient Record System (CPRS)].

VISTA is an excellent software engineering platform and I would love to be able to do that. We could also use VISTA as a national test platform for AHECS and major medical teaching centers supporting health care in poor urban and rural environments — zones where specialists with expert drug knowledge are few and far between and out of cost reach.

During our phone conversation, I was quite intrigued by the way you argued that CureHunter is a sort of uber tool — useful for such varied audiences as frontline physicians (say, oncologists struggling from the many strains of information overload, heavy workloads and tricky, crucial treatment decision-making dilemmas), pharmaceutical scientists working in the drug discovery realm and clinical researchers working on meta-analyses and drug safety and efficacy issues. Could you give us real-world examples of in what sectors CureHunter is being used and what specific kinds of medical people and scientists are using it? For example, your say on your site, “Evidence-Based Medicine is now possible in Real Clinical Time.” Can you elaborate on the phrase “real clinical time?” Is CureHunter any more up to the minute than UpToDate, for example?

Dr. Lou Degennaro former Director of drug discovery Research at Wyeth and now Chief Scientific Officer at the Leukemia and Lymphoma Society has opened a dialogue with us about working in concert with his team on their target agents. We have done in depth research for friends and associated scientists on Alzheimer, Arthritis, Parkinson, Colon Cancer, Ovarian Cancer and MS.

Ten of the world’s major pharma have scientific use licenses for drug discovery. NIH and FDA are both heavy users of the system as are seven National Cancer Institutes around the world. BMJ, Lilly and Pfizer hit the site a lot as do millions of patients from all over the world. About 60% of licensing is now coming from pharma scientists and 40 from doctors and others.

The major contract drug research houses have on going discussions with us specifically for taking target agents they or their clients own and computationally re-targeting them. Automatic new drug discovery is, after all, a holy grail for patients and pharma researchers both.

A broad range of doctors in general practice have bought the Patient-Physician reports for all the diseases they treat in their specific clinics and patients, of course, purchase the ones for the diseases they or their families are facing head on. Wherever possible we do pro bono analyses, but we really are out of time without a grant partner to do much more.

Right now Dr. Rick Deyo, Kaiser Permanente Professor of Evidence-Based Medicine at Oregon Health Sciences University, and Dr. Eric Orwoll, Director of OCTRI: Oregon Clinical and Translational Research Institute, at OHSU have written NIH asking them to fund joint research between themselves and CureHunter. Getting CureHunter itself into a major clinical use trial is a major goal for us next year.

So if you are a patient, doctor, or advanced Ph.D. researcher at a supercomputer center, CureHunter has probably “blown your mind” more than once.

I addressed the just how UpToDate is UpToDate question above … historically, it was updated quarterly and then limited to the findings of its particular experts. CureHunter reads everything and updates its entire database every night to include even pre-press as much as four months prior to publication. And nothing in UpToDate is directly computable.

Evidence-Based Medicine has always meant historically empowering a panel of human experts to review the state of knowledge in a field, make formulary analyses, carry out meta-analyses of large samples of literature and compare clinical trial results. Obviously, before CureHunter, getting the evidence and analyzing it was a tremendously expensive, difficult and complex task not doable in real time: your patient isn’t going to stand in a gown in your clinic office while the committees go and find out if there is a better drug for her?

So how does CureHunter make evidence-based medicine available at the point of care without interruption in the clinical workflow? Click CureHunter in Patient EMR: in 10 seconds a meta-analytic graph computing relativistic drug evidence from the oldest to the newest data (1932 forward to the previous night) appears on the doctor’s screen.

“So Mrs. Jones, you aren’t doing well on the Avandia, let’s try the older and less expensive Metformin. The docs at Johns Hopkins found it just as good and often better. Here’s the data for the decision. Here’s a print out of the CureHunter meta-analysis comparing the efficacy of these drugs.”

This scenario is acted out in clinics all over the U.S. thousands of times a day: a patient has had an adverse reaction to first line default med, a patient can’t afford that med, a patient has an ER event as a result of the selected med, a patient has burned out an organ on one med because their condition is chronic, your first choice would interfere with a drug for another condition, your patient is allergic to your preferred med. Your patient is dying and you just don’t know what can help … until you check CureHunter. Some new drug maybe showing promise but you haven’t had time to research it. Those are just the basic ways CureHunter is functional right now in daily medical practice.

Every time a change of med decision is made, it will be more safe, effective and well tolerated if evidence-based. And that is what CureHunter functional utility is all about for the health care system. If a patient doesn’t come back because the drug you gave him or her the first time cured them … you just saved the system 2x the cost of treating them or more if the drug they did take causes serious adversity.

Some proof: two years before the law suits began the CureHunter engine highlighted MI, BP destabilization, and other major cardiac events as a good reason not to prescribe VIOXX. A ten second check would have saved millions of dollars in law suits not to mention, pain, suffering and death.

I could write a book on how we are approaching chemo therapy protocol optimization and most of that work is currently proprietary at the moment; but we do have several cases of patients reporting that the CureHunter recommendations for their doctors (all pro bono) improved their outcomes.

In the future, Justin and I hope to devote a great deal of our time to algorithms specifically designed for that task and we take it very seriously indeed.

Let’s talk healthcare information management. On your site we read, “CureHunter evidence data can be directly integrated into your EMR systems such as Epic, GE Centricity, and VA CPRS.” Let us say I am neurologist treating a 46-year-old male epileptic who has had such a terrible seizure that he ended up in the emergency room for the treatment of injuries from a bad fall and comes to me for help a few days later. I have never treated him before. I work in a small five-hospital network that lacks the sophistication of Kaiser Permanente when it comes to electronic medical records. What kind of EMR system am I likely to be using and what would CureHunter look like within it as I sit down to try to figure what the patient’s current drug regime is and as I decide what to do for the patient?

CureHunter EV-STAT is a prototype application showing the integration of the CureHunter evidence engine directly into the General Electric Centricity Electronic Medical Record. Physically the software interface can look on screen like an employee database record with various tabs for documenting the individual’s history with the organization. Most EMRs have treatment windows that show which drugs the patient has used before and is using currently along with various diagnostic and text windows.

Under a TAB called Drug Evidence, CureHunter can be hot linked into that record.

Nationwide, about 50% of EMRs are provided for smaller hospitals and independent practitioners by local medical system software integrators, and there are many simpler record systems available than those used by the major national providers. About 17 major health care payers control about 90% of the payment traffic for health care in the US today, so it is practical and efficient for small hospitals and practices to use a system that is a good fit for both their clinical uses and administrative and billing functions.

Now to your specific question on epilepsy: your neurologist probably knows the major drugs to treat epilepsy already. But he can with one mouse click in his EMR pop up the CureHunter blue graph of clinical efficacy where ten major high performing meds are displayed and rated. When the incoming patient describes the meds, if any, he is currently on, your neurologist can ask him how he is doing on them. And if not so well, with one look at the Chi graph the neurologist can find ten others with specific statements of evidence backing up their usage:

E.G. 05/01/2009:
“Epilepsy was well controlled in 65 out of 81 (81%), mainly with valproate and phenobarbital, and improved with age in all. ”

Checking the gold standard drug, finding an alternate, switching to a new med not contraindicated for the specific patient can all be done in seconds.

You mentioned on the phone that Britain’s National Health Service is one of your clients. As you know, in the current healthcare reform debate, the NHS is held up as a model of compassionate, socially equitable care by some and as a whipping boy by those who contend that its ambitious implementation of a nationwide EMR has been a hugely expensive fiasco. Can you discuss how CureHunter is used by the NHS and what lessons that use holds for policymakers and informaticians in the U.S.?

Over 65% of the heaviest users of CureHunter are from foreign countries that have very effective national health care systems. One of my oldest executive friends predicted this market phenomenon for CureHunter by pointing out that nations that can adopt technical standards rapidly, are in much better shape for improving care and lowering costs.

The Internet is so incredibly powerful and universal because everyone in the world speaks and writes TCP/IP, html and XML and C and Java. The PC industry only thrived when Windows became a dominant OS providing large markets through common specifications for all application developers. Science only prospers when we agree on what a kilometer equals.

So how do standards and EMRs and CureHunter and all that help the NHS and everyone else? It would be very simple to see how the country could save many billions of dollars per year, simply by using CureHunter to compute the optimal uses of generic drugs and getting more prescriptions right the first time.

I am quite interested in amyotrophic lateral sclerosis (ALS). And unfortunately, Rilutek is about it for drug treatments for ALS. I was intrigued by the wording on your homepage, “Discover new potential off-label applications … ” There have been studies (sadly, rather disappointing) of the potential use of lithium, minocycline and thalidomide in ALS. Can you give an example of how researchers could use CureHunter to discover potential off-label applications of existing drugs and how CureHunter can expedite such research?

Here’s the key underlying fact about off label drugs.

Doctors prescribe a lot of them, especially for their patients where all the known “good meds” are not working. Essentially they are making guesses that a drug related to a similar condition might help. Or a specialist friend down the hall says, “I’ve had some good luck with XXX.”

CureHunter takes the guess work out of off label prescription mathematically, algorithmically. We find all cases in the evidentiary literature where a drug not originally labeled for the target condition, none the less was used for it and a patient improved. You can see these patterns by clicking the related drugs and disease TABs in the interface after searching on your primary target drug or disease.

A second much more powerful function in CureHunter is implemented by Justin’s graph theory algorithms. In those analyses we are looking at graphs showing the maximal number of drug and biological mechanism connections shared by any two or more diseases. When a disease participates in a lot of shared biological connections, you can predict with some accuracy that a drug that worked for disease A, might also work for its friend, disease B.

People who belong to common groups are more likely to communicate with people who join their or similar groups. The cell phone company family and fave calling plans were all based on these types of data models. Who gets called by whom and how often?

So if you think that tumor necrosis factor alpha (TNF alpha) is very friendly with psoriasis, it might also know arthritis and be sending both those “pals” messages like, hey turn on, tune in and inflame yourself big time. Thus, if Network Graph Theory is used to define disease-drug communication clusters, a drug that makes a good call on one disease might do so on another.

The Center for Disease Control and Prevention (CDC) also uses Network Graph Theory to predict primary epidemic pathways and the growth of the number of individuals that potentially become vectors by “calling on friends and family” and school mates and work partners who don’t yet have the disease.

And again, using ALS as an example, can you discuss how working physicians and other healthcare providers could use CureHunter to research non-drug treatments for various conditions? For example, I just tried the “Relationship Network” feature — that is pretty cool and an interesting use of visual search. Could you discuss what users will see on the Research Interface and the concept underlying it?

The important thing for users of CureHunter to understand is that our implementation of the visual network is a show and tell function that brings together massive amounts of distributed information into an observable focus. 10,000 + data points might be supporting any single screen page full of connections. But you don’t really understand just how powerful those collections of data are until you export the underlying data sets to standard database and array formats. For example, with one mouse click you can ask to see every drug that ever successfully treated any cancer and how many different ones each drug treated successfully. If you are doing cancer research this lets you quantify in seconds the work of hundreds of thousands of investigators over 70 years.

In terms of my and Justin’s work on chemo therapy protocol optimizations we can find patterns among the most successful agents that lead to cocktails that can improve the total effectiveness of the regimen.

In CureHunter, you can just go in an enter the term “biomarkers” and all diseases for which we have found them will be linked with a click. Same with genes, hormones, specific proteins etc. So the system goes way beyond “drugs” as defined as prescription meds.

Recently we did an analysis of inflammation — a centric dysfunction — to see how many diseases it triggers and why. In seconds CureHunter can show you every disease where inflammation plays a major role from cancer to heart attacks and headaches. Thus pointing out why aspirin can be helpful in all of them, and even more interesting: statins.

You just can’t do that with any other tool in the world: find the center of evidence across the world’s largest medical library of peer-reviewed findings all cross-indexed automatically to curative properties and mechanisms of action associated with specific illnesses.

You have quite a variety of products and several different client bases. For example, consumers can use free the search tools on your home page. They can also order summary reports. Would you discuss how you see the e-patient/empowered patient movement developing given that you use such wording as “clarify diagnosis with your doctor?”

We want to empower patients with knowledge and our reports give them the pure scientific data on all the drugs that might help them. We know our reports are also great evidence summaries for our doctors because they order them and tell us so.

In general I see patient empowerment as a good thing when the patient can help his or her physician better understand the health problem or bring real high quality information to the table that their doctors have not yet had a chance to review. But I urge all patients to be empowered by science not hokum or sales literature or network TV ads. Do your homework, if you want to get well safely.

Could you discuss how some of the professions you discuss on your site (e.g. independent physicians, international users, private individuals and other certified prescribing personnel such as NPs and PA) could use CureHunter?

Well CureHunter Mobile, now available on your web-connected cell phone or PDA is a great tool for Nurses, PAs and med students to quickly check the definitions of major conditions or the drugs used for them. Our data is far more comprehensive than that from Epocrates or Stedman’s.

With CureHunter on your PDA you could be quite literally stuck in an airport waiting for your Christmas flight home and discover a cure for cancer by thinking about the results brought back to your screen.

In many parts of the U.S. — not to mention the rest of the world — specialists and pharmacists with deep credentials are very few and far between. There is nobody in the “next office” to ask what do I use now, when the default med fails. Well, with a mouse click you can ask CureHunter on your office PC — no fancy EMR system needed.

Pharma research scientists, however, are the ones that are totally in love with the system. They see its power quite clearly and directly as having major impact on their work and the bottom line of their companies.

Obviously, if you can directly compute new cures (drugs) for human disease you can dramatically speed up drug development and lower the financial costs to get new products into the market. Re-targeting existing meds for good new clinical purposes is a very powerful function we can apply over any company’s existing portfolio of agents and immediately convert old research costs to profitable assets.

By working with meds that have already passed human clinical trials for the original target, the most expensive dollar and time components of fresh development can be minimized.

Are any medical libraries using CureHunter? Is that a potential market?

Medical Libraries all over the world are using the product — we gave out about 5,000 free licenses for testing ALPHA-BETA versions — but I am afraid to continue our research we are going to have to start converting all users — except charitable foundations — to commercial licenses.

You mentioned that you have some rather interesting projects going on with various academic partners. Are you at liberty to discuss those?

Well I have good friends at Stanford and the University of California and the Pasteur Institute in France and at several universities in Great Britain working on cancer research, but because we are Portland Oregon-based and we have such a great teaching center here in the Oregon Health Science University and a terrific Bioinformatics Program running under Dr. Bill Hersh, I am hoping NIH or a major EMR provider will step up to the grant plate and let us do all kinds of experimental tests with the University.

Doctors Rick Deyo and Eric Orwoll Director of OCTRI are very interested in the translational medicine applications of CureHunter and that, of course, has been the theme of all NIH Bench to Bedside programs and a core message of President Obama. Get applied real world health care improvement payback now from advanced research.

People who read this interview may be puzzled (as I was) at the relative dearth of information on your Web site about the management and scientific team at CureHunter. Could you explain your philosophy of letting the science speak for itself and pouring money into the development of CureHunter itself as opposed to providing extensive professional profiles of your executive team?

Thank you for asking the question. It’s one dear to my heart. The Internet has proven itself to be one of the great human inventions of all time. It is also a den of iniquity of all kinds and a blind for much bad behavior.

One kind of bad behavior that I particularly dislike is where the start up company goes out and gets a laundry list of famous entrepreneurs or “advisors” and then lists them on a beautifully designed Flash page as some kind of BOD or Management Committee to indicate that their company is just doing the best work on the planet — when time and again those people have nothing to do really with the company or the quality of its products or even its staying power in the market, or even good management.

It’s sometimes the case that they advertise the Fortune 500 case winning lawyer and sell you the paralegal.

Does that mean I don’t like and respect venture capitalists, or brilliant young MBA Advisors, other successful entrepreneurs or good scientific counselors, no … not at all. We could use help from all of them ourselves.

But I don’t want people to validate us because of borrowed interest in a somewhat famous individual. Our whole story is the science and nothing but the science — the evidence — and that’s what I want people to know us for, test us for and buy us for.

It’s CureHunter’s ability to compute the evidence in real clinical time that makes it a powerful visionary product, a unique product that passes the Alan Turing test over 250,000x a month around the world.

Everything we do, every day is open to public scientific challenge and scrutiny because we do what no other health info system on the planet does: we predict outcomes that can be tested, compared, checked, validated by experts and novices, med students and senior physicians, Ph.D.-M.D.s from the Hopkins and Harvard, Oxford and Cambridge and National Science Foundation and NIH and FDA and NHS and NASA (another one of our heavy users). We have the real deal, no smoke, no mirrors.

So, what’s in a name? Not anywhere near as much “truth” as is in the data. Especially data subject to peer-review and scientific test by third parties with zero vested interest in our game.

How do you see CureHunter a year from now? In five years? In ten?

Well, we have our work cut out for us. We would like to find the cures for at least 10 major killer diseases and become the premier source in the world for evidence based medicine. Integration of our technology into one of the major EMRs is a clear next step in the 5-year window.

It would be a great service to science and health care if we established a central anonymized electronic health record depository — so powerful algorithms could process the learning from millions of real world case treatments and compare findings with those in the peer-review publications.

I would also like to have 5 — 10 world class pharmaceutical scientists working on drug discovery with us.

I think with our particular skills sets integrated into our scientific “swat team” of just really forward thinking guys and gals that respect and like each other a whole lot, we can get there much more quickly than anyone else.

I would like to add a few young clinical chemists, smart docs and mathematicians to the team as we go forward, plus just some great creative infrastructure people that want the most exciting job in the universe.

In the short term I am hoping some major foundation will step up to the plate and give us a charter to compute a cure for major illnesses. I think we deserve the real X prize for developing the first machine on earth to autonomously discover new cures for human disease. If we get a major outside funding round, we won’t just cure one disease, we will cure many.

But one of my major dreams is really simple in structure and doable immediately: because OHSU, Oregon Health Sciences University, wants to work with us on both our objectives for clinical research and drug discovery, a major pharmaceutical manufacturer could really speed their new product pipeline fill by endowing the OHSU-CureHunter Center for the Computation of the Cures for Human Disease.

Be practical, Judge, you say. Well that is extremely practical, for a grant of $3 — 5 million the sponsoring pharma could get first IP rights on many new agents and clinical applications: we could essentially complete the Molecule to Medicine Pathway at one center where researchers, doctors, and patients can all work together in synchronicity. The savings in new drug development costs would completely dwarf their out of pocket. Royalties could also feed back to OHSU researchers on drugs ultimately moved to market much faster.

Finally, who are your personal heroes in technology and in any other area?

I see you saved the toughest question for last, Hope.

In contemporary technology, I really do admire the people who turned the world upside down and helped us see it in a new way. I don’t think “hero” is the right word at all for our PC tech entrepreneurs like Misters Gates and Jobs or the Lion of DEC, Ken Olsen who first taught us all there was computational life after the IBM mainframe, or Mr. Turner that shook up the media network game or the Adobe boys that changed all we know about art and graphics by converting the hand drawn line to a set of a curvaceous numbers along with the likes of George Lucas and the Industrial Light and Magic brigade of compuartists that turned polygons into pure fantasyscapes. Dr. Wolfram’s book, NKS or a New Kind of Science … I’d have to say is the coolest single work that appeals to me personally. It’s just so wonderfully egotistical (just like me), driven, powerful, visionary and whacked enough to force serious new thinking outside all kinds of boxes.

Doctors without Borders. President Obama and his wife shattering all the old stereotypes ceilings. Oprah, I love that gal. You know what, Oprah has done more for Skype and all the rest of us humans in many ways than many of our best scientists by just showing everyone how cool it is to read. Reading is the real game changer, not Pong.

Thank you for your time.

You’re welcome, Hope … and be well.

Are you a Twitter user? Tweet this!

In part I of Hope’s interview with Judge Schonfeld, Judge talks about the development of CureHunter, the definition of “autonomous search” and the difference between CureHunter and other authoritative online reference services.