Due to the variability of diagnostic measures resp. patterns it is a comprehensive task to make them searchable and requires a clear reply to the following questions:

• How can the doctor provide a diagnostic pattern for which similar patterns should be found on the database?
• How can the database recognize the kind of diagnostic pattern provided by the doctor and so isolate the set of comparable patterns on the database?
• How can the database quantify the similarity between the provided pattern and the comparable patterns with attached articles in the archive to calculate their rank in the search result?

It turns out that there are satisfying answers to these questions in all cases of comparable patterns. They are abbreviated:

In case of concise patterns the doctor can enter the pattern directly by keyboard, e.g. as sequence of numbers, together with an unique "pattern name", which specifies the kind of the pattern. In other cases the doctor can upload the pattern as file from diagnostic software which is designed for handling of this pattern kind. If appropriate, this software may be connected with some digitizing device or it uses data from a laboratory.

The database recognizes the kind of the pattern by the pattern name. Then it searches within the archive for publications whose associated patterns have the same pattern name. Those with most similar numerical representation will have highest rank in the search result.

Quantification of similarity depends on the kind of the pattern, which is known together with the pattern name. The numerical representation of the pattern is designed in a way that the database can calculate their similarity by direct comparison using an efficient algorithm.

First of all it is appropriate to explain some frequently used abbreviations:

Some digital form of information. A searchable feature vector which is usually a sequence of numbers¹ represents it. The dimensionality of the feature vector (the length of the number sequence) is variable; it depends on the pattern definition. Similarities of the original data are mapped to spatial similarities of the feature vectors.

Every pattern file represents a well-defined pattern. It contains a header with the pattern name which identifies the kind of a pattern, the date, a link to associated patient records or text, and some additional information, e.g. optionally a link to original data². The feature vector which is the numerical representation of the pattern follows the header. We recommend a special filename ending for quick recognition and XML format as shown in [18W Orthuber. Universal pattern search on the web http://www.orthuber.com/wpa.htm., since 2006-06-02 ].

If a pattern is given for a search, it is necessary to quantify the similarity to other patterns on the database with the same pattern name. The result of such comparison is the deviation or distance d≥0, in which d=0 if the two compared patterns are identical, else d>0; d is the greater, the more they deviate. The smaller d, the higher is the rank of the associated URLs in the search result.

The multidimensional feature vectors which represent the patterns should be designed to be quickly comparable by the software of the database, using a short distance function for calculation of d.

The pattern name is a string which can contain letters and numbers like Internet domain names, and points. It is the name which uniquely identifies the kind of a pattern; in the sense of the W3C it is an URN, a uniform resource name [20W3C. Naming and Addressing http://www.w3.org/Addressing, viewed 2007-07-24 ]. To guarantee uniqueness also in case of expansion of the search method over the web we recommend the following convention:

Let dn denote the name of an Internet domain, in which patterns names are defined. Then these pattern names have the structure dn.*, where the ending * is a string without spaces. All definitions of patterns are done in the pattern domain which is a special subdirectory with name dn.pat (Fig. 2). In our case dn is identical to the domain name of this database, if all definitions are done within it. Examples of pattern names may be:

Fig. (1) Task sharing in pattern search.

"dn.blood-concentration.xyantigen",

  "dn.blood-concentration.psapair",

    "dn.ultrasonic.heart-results-1",

                "dn.ekg1.avr",

     "dn.vertebral-body-heights",

             "dn.dna-seq.12",

     "dn.features.fundus.oculi.1",

      "dn.features.melanoma.4",

                "dn.ICD.10",

         "dn.evaluation.1" etc.

Pattern names make it possible to develop optimized structures and associated comparison algorithms to any kind of pattern independently of other kinds. Due to the variety of diagnostic methods and associated patterns it is necessary to share the work and to give motivation to participate. Therefore we orientate on the policy for Internet domain names which has been very successful. According to our suggestion the owner of the internet domain name dn owns also the pattern domain dn.pat and with this the privilege to define all pattern names of the form dn.*. The patterns with these names form a pattern group.

If a pattern group and domain should be useful and not ignored, its owner should:

• Provide useful definitions of all pattern components,
• If not trivial, describe efficient ways for their generation from original data,
• If necessary, give information to software for creation of patterns and/or donate or sell it,
• If necessary, give information about associated digitizing devices, he/she may also sell them.

Someone who invests much work in optimization of the own patterns can gain from this, because an efficient pattern is more frequently used. Some consequences:

• Communication in the own special field is more efficient.
• The own pattern domain "dn.pat" is more attractive
• The own software and/or digitizing devices which are necessary for generation of the dn.* patterns are more attractive.

So there are scientific and commercial reasons which make pattern domains attractive. The pattern domain owners play an important role; Fig. (1) illustrates the task sharing:

Certainly there would be much motivation for a search request, if there are appropriate diagnostic digitizing devices and a good database.

But is there enough motivation for a doctor within today’s framework to invest work and upload documentations resp. articles, to share own experiences with colleagues? Perhaps the feedback on this article will give first answers. At least the success of existing electronic archives indicates, that after some time of familiarization there can be also much motivation for doctors of medicine to become author in a worldwide read open archive. They can contribute a lot to science and progress by plain reality conform documentation. Health professionals who frequently upload, will become better known. Those who upload from the beginning will get particular attention, because initially there will not be a large number of authors, and all articles will be accessible chronologically.

There is another way for feeding the database which will become more and more important: Since some years there are increasing efforts [21MRInstitute leading the way to electronic medical records http://www.edrecinst.com, visited 2007 ] to collect all spread medical documentations of one patient in a standardized set of electronic medical records, which is accessible as a whole. After anonymization these records could be integrated into the database, if the patient explicitly whishes that. In this case he should also have the right to comment and to rate. Of course this would be an additional motivation for the doctors to achieve a good treatment result. If whished, the patient could be also contacted, e.g. for exchange of experiences in self help groups.

Additionally there will be a directory for conventional articles which describe clinical trials. The associated patient records should also be uploaded and referred. They will automatically get links backwards (Fig. 2).

Fig. (2) Proposed initial directory structure of the database. All relevant data are accessible via URL. There are links of articles to patient records and backwards, and links of the pattern files to the associated text.

The author can designate his article as "xy percent documented", if in a prospective study the records of at least xy percent of initially participating patients are uploaded and evaluated. Then all referred patient records will get a mark which shows this quality. If one restricts a search request on records which belong to "100 percent documented" clinical trials, one has greater assurance that also patient records with unwanted outcomes are evaluated.

Values like xy could be integrated in a more general multidimensional pattern with name "QualityDescriptor" which can be associated to documents which fulfill a certain quality standard. It could be used as additional filter for a search.

It is not difficult to define patterns according to current research - the feature vectors can contain all necessary data which are measured in clinical trials. The associated patient records can be uploaded and the results are directly accessible and comparable. For identification of diseases among others a pattern defined according to the International Classification of Diseases (ICD) can be used. Parallely to this it would be advantageous to search for pattern definitions which systematically map subjective and physical similarities of symptoms to similarities of the feature vectors. One of the first steps would be to define appropriate curved coordinate systems for the constituents of the human body.

The initial considerations which lead to development of this idea arose from the field of orthodontics, which is concerned with the study and treatment of malpositioned teeth and the control and modification of facial growth. Cephalometrics is done for treatment planning [39Athanasiou E. Orthodontic Cephalometry. London: Mosby-Wolfe 1995., 40Schutyser F, Hausamen AC, Swennen JE. Three-dimensional cephalometry, G R J A color atlas and manual. Berlin Heidelberg New York: Springer 2006.]. At this lateral skull radiographs are taken under standardized conditions and measured (Fig. 4). The results can be used for building feature vectors. Using these data improves prognosis of skelettal growth.

Fig. (4) Cephalometric analysis; the angles and distances measured on the lateral skull radiographs (cephalograms) can be used for building a feature vector of this profile.

Fig. (3) The search process.

Advanced orthodontic techniques use devices which directly digitize the three dimensional tooth positions [41Orametrix® http://www.orametrix.com/ visited 2008_02_10 ] (Fig. 5). From this data coordinate system independent feature vectors can be calculated for treatment planning.

Fig. (5) Measurements on the digitized three-dimensional surface of the dentition. Digitizing device: OraScanner™ (Orametrix, Inc. in Dallas).

We noticed, that the approach can be generalized. Feature extraction of diagnostic findings is also possible in other areas of medicine. Often such findings are the basis of severe decisions. The following examples illustrate this.

Sometimes complex original data can need complex precalculation. If simple self-evident considerations (Fig. 10) are not enough, an appropriate transformation of pictures, sounds or curves is often the first step for calculation of feature vectors. For example in case of heart sounds a wavelet transformation allows analysis of the signal at different scales and times. Initially it is necessary to select and border accurately a representative period of the sound (Fig. 6a-c). The resulting wavelet coefficients (Fig. 7) can be used for building the feature vector which represents the pattern.

Fig. (6a) Heart sounds in case of aortic valve stenosis; vertical axis: relative amplitude, horizontal axis: time in seconds. The brown dashed lines represent a bordering of the first period which has been set approximatively by the user on the screen.

Fig. (6b) A catching algorithm is applied which reproducibly refines the bordering of Fig. (6a).

Fig. (6c) The bordered part of Fig. (6c) is stretched that exactly one period remains.

Fig. (7) The sound of Fig. (6c) after Daubechies wavelet transform; smoothened absolute values of the transformation coefficients for five different scales. They can be directly used for building a searchable feature vector of this heart sound.

Fig. (10) Drawn are the lines with lengths d1, d2, d3, c2, v1, v2, v3 which are used for classification of the vertebral compression fracture and for calculation of three important numbers (v,c,d) which provide decision-relevant information about the geometry of the fracture. They show the relative remainder of the vertebral body ventral (v), central (c) and dorsal (d). Let d1, d2, d3, c2, v1, v2, v3 denote the scalar lengths of the lines drawn in Fig. (10). Then we can calculate the numbers v, c, d as follows: v=2*v2/(v1+v3), c=4*c2/(v1+v3+d1+d3), d=2*d2/(d1+d3). Additionally the number n of the vertebra and a representative measurement of bone density t like the DXA T-score may be important, so that we could define the 5-dimensional feature vector (v,c,d,n,t) for a vertebral compression fracture. For a search it is preferable, but not necessary to know all 5 values. If, for example, someone has a compression fracture and only c and n are known, it is possible to search in the database for all vertebral fractures with similar c and n.

Development and improvement of such calculations requires research. Remembering the variety of useful pattern structures it becomes clear that sharing of the work is necessary. The database cannot generate searchable patterns (Fig. 7), but it can store, compare and rank them (Fig. 8).

Fig. (8) Exemplary output of our database prototype. The uploaded pattern represents the heart sound in case of aortic valve stenosis after wavelet transformation as shown in Fig. (7). Links to articles with most similar stored patterns are listened first. The links are accompanied by structured information for test purposes. The distance d quantifies the deviation to the uploaded pattern, the first link points to an article with the same sound like the uploaded one, therefore the distance is zero.

In the next chapter we show that even complex original data like MRI scans can lead to very compact patterns.

A common question to the database will be: Should we operate, and if yes, which operation has best results. If the operation has severe consequences, there must be a good justification for it. For example Fig. (9a) shows the MRI of a 2 weeks old osteoporotic⁹ compression fracture in the area of maximal kyphosis of the thoracic spine. The treating surgeon was a specialist in doing spinal fusions and recommended a dorsoventral spondylodesis. The patient trusted and accepted. After the extensive operation the patient read about kyphoplasty [42Kasperk C, Hillmeier J, Nöldge G, et al. Kyphoplastie-Konzept zur Behandlung schmerzhafter Wirbelkörperbrüche Dtsch Arztebl 2003; 100(25): 1748-52.] and heard from experts that this minimalinvasive method would have been adequate in his case. So he got the impression that the operation trauma (lateral thoracotomy, muscle dissection), which leads to chronic pain, has not been necessary. The surgeon, however, dislikes kyphoplasty [43Hopf C, Heeckt H. Kyphoplastie – Konzept zur Behandlung schmerzhafter Wirbelkörperbrüche. Kommentierung notwendig Dtsch rztebl 2003; 100(44): 2882-3.] and remains committed to his operation (Fig. 9b). Obviously medical treatment dramatically depends on the experience¹⁰ of the chosen doctor.

Fig. (9) (a) osteoporotic compression fracture (b) chosen therapy: dorsoventral spondylodesis.

This is no good situation. A comprehensive and uniform source of information like the proposed one could help and avoid dissent. If there would have been a good searchable database, before recommendation the surgeon could have looked for similar¹¹ fractures in the database and could have asked for chances of success in case of conservative therapy, kyphoplasty, minimally invasive endoscopic surgery [44Beisse R, Potulski M, Bühren V. Endoscopic surgery of the thoracic and. lumbar spine-A report on 500 treatments Osteosynthesis Trauma Care 2003; 4: 96-205.], other therapies, or dorsoventral spondylodesis with lateral thoracotomy. If the latter would have been best, he could recommend and justify a large operation, there would not be any problem. If another possibility would have been better, he could early enough recommend another treatment and avoid a large unnecessary operation trauma with all consequences.

We have seen the great significance of MRI scans. Because they seem to be innocuous, we recommend more extensive usage of this possibility also for prophylaxis:

Nearly all of us have lost an affiliated person due to cancer which would have been detectable in an early state by MRI. Cancer is so frequent and so painful that we suggest as prophylaxis periodically¹² standardized MRI scans of all interested people. At least scans of imperiled tissues should be done at an age, in which these frequently lead to detection of a serious disease¹³. Three-dimensional imaging is possible. From the most significant scans feature extraction could be done. The resulting feature vectors could be stored as searchable patterns in the database. From this we could systematically learn about feature changes, which later correlate with serious diseases. This would lead to a well-founded basis for efficient MRI prophylaxis.

Of course such scans should be combined with other measurements, e.g. blood tests like PSA, if statistically meaningful. After establishment of the database we expect competition of diagnostic methods - the most meaningful methods can be easier recognized and selected.

Besides efficient search there are additional possibilities. Immediate individual statistics and regression analysis already have been mentioned. Because the patterns are machine-readable, they could be evaluated automatically by software, e.g. for conversion, modelling - it would exceed the scope of this article to deepen this here.

• Databases with collections of patient histories are standard for documentation of clinical trials and medical studies. They are separated, specialized and often private.
• All these databases are confined to their special application and the number of diagnostic patterns is very limited, because these are defined centrally by a few persons, e.g. by some developers.

• The proposed database has an universal open and worldwide accessible interface. New anonymous patient records can be added interactively, if wished linked together with associated documentations of clinical trials.
• At this the number of allowed diagnostic and other well-defined numerical, machine-readable patterns is not limited. Their definition is done decentrally by "pattern domain owners", e.g. researchers, manufacturer of diagnostic devices, which have much more working capacity than the database's personnel. Any owner of an Internet domain name is automatically also owner of a pattern domain which starts with the same name.
• The database allows numerical search for these patterns, if wished combined with conventional text search. Furthermore it provides standard algorithms for their numerical evaluation, like statistics and modelling. Periodically calculation of up to date prediction models is possible.