GB2421437A

GB2421437A - Medical testing system

Info

Publication number: GB2421437A
Application number: GB0428182A
Authority: GB
Inventors: Avinash Shishir
Original assignee: Individual
Current assignee: Individual
Priority date: 2004-12-23
Filing date: 2004-12-23
Publication date: 2006-06-28
Also published as: GB0428182D0

Abstract

A physiological testing apparatus comprising motive means, a controller to operate the motive means, means for receiving a signal that a patient is present, and means to collect data. The patient may be asked to input information such as ID code and required test. The patient may be dispensed a remote control 104 and which the patient takes to one of a plurality of cubicles 100 which contain robotic equipment that performs the test. The test may be a X-ray, ultrasound, MRI, CT scan, mammography, or blood test.

Description

1 2421437 Medical Testing System This invention relates to a medical

testing system and, more particularly, to a system for enabling medical tests to be performed in respect of patients, and data from such tests to be collected and analysed.

In diagnosing and/or treating a patient, a physician will use patient condition, symptoms and the results of applicable medical diagnostic tests to identify the disease, state or condition of the patient. The physician must carefully determine the relevance of the symptoms and test results to the particular diagnosis and use judgement based on experience and intuition in making a particular diagnosis.

Because of the predictive and intuitive nature of medical diagnosis, attempts have been made to develop neural networks and expert systems that aid in this process, and the application of neural networks to decision support systems for use in medical diagnosis has been proposed.

However, one of the main problems in the field of medical diagnosis is the ability to perfonii the required medical diagnostic tests sufficiently quickly and efficiently to ensure that diagnosis can be made early enough for the disease or condition to be treated as soon as possible. Long waiting lists in clinics and hospitals often result in a significant delay in performing the required tests.

It is therefore an object of the present invention to provide a medical testing system which enables automated medical diagnosis tests to be performed by unskilled users, and the data from such tests to be collected and analysed.

Thus, in accordance with a first aspect of the present invention, there is provided apparatus for performing an investigative procedure in respect of a live patient, the apparatus comprising testing equipment, motive means for moving said testing equipment relative to said patient, and a controller for controlling said motive means, said controller comprising means for receiving a signal indicating that a patient is present and prepared for said procedure to be performed, means for causing said motive means to move said testing equipment to a correct location relative to said patient, means for causing said testing equipment to perform said procedure in respect of said patient, and means for collecting data obtained by said test equipment during performance of said procedure.

In accordance with a second aspect of the present invention, there is provided a system for selectively performing one of a plurality of investigative procedures in respect of a live patient, apparatus as defined above being provided in respect of each respective investigative procedure, the system comprising means for enabling the investigative procedure required to be performed to be selected from a plurality of investigative procedures, means for enabling said patient to control the apparatus corresponding to the selected procedure so as to enable the selected procedure to be performed, and means for collecting data obtained by said apparatus during performance of said procedure.

Thus, because automatic testing means are provided which can be operated by the subject, it is unnecessary for a skilled practitioner to be present during performance of the procedure, thereby increasing the number of procedures that can be performed within a time period and reducing patient waiting times.

In order to facilitate the ease of use of the apparatus by the patient, means are preferably provided for interactively giving instructions to the patient and receiving signals indicating whether or not the patient has followed such instructions.

The apparatus for performing the selected investigative procedure is beneficially operable via a remote control unit. In one exemplary embodiment, when an investigative procedure has been selected, a remote control unit specifically arranged and configured to operate the respective apparatus is dispensed. The remote control unit and respective apparatus are beneficially tuned to the same, unique frequency, so as to ensure that the remote control can only operate that respective apparatus.

Interpretation means are beneficially provided for receiving data collected during performance of an investigative procedure, and interpreting said data to obtain one or more test results. A decision support system may be provided, wherein said test results and data representative of any symptoms experienced by the patient are used to generate advisory data in respect of said patient. The decision support system preferably comprises a pre-trained neural network, and a dedicated pre-trained neural network or artificial intelligence structure is beneficially provided in respect of each investigative procedure supported by the system.

In a preferred embodiment, means are provided for wirelessly transmitting data from said interpretation means andlor said decision support system to a remote communications device, such as the subject's general practitioner's PDA or the like.

These and other aspects of the invention will be apparent from, and elucidated with reference to, the embodiments described herein.

Embodiments of the present invention will now be described by way of examples only and with reference to the accompanying drawings, in which: Figure 1 is a schematic block diagram illustrating the principal functions of a front end module for a medical testing system according to an exemplary embodiment of the present invention; Figure 2 is a schematic block diagram illustrating the configuration of the testing cubicles for a medical testing system according to an exemplary embodiment of the present invention; Figure 3 is a schematic block diagram illustrating the principal components and functions of an interpretation and decision support system for a medical testing system according to an exemplary embodiment of the present invention; and Figure 4 is a schematic block diagram illustrating the architecture of robotic test equipment for a medical testing system according to an exemplary embodiment of the present invention.

Referring to Figure 1 of the drawings, a microprocessor-controlled front end module for a medical testing system according to an exemplary embodiment of the present invention first requires entry of a patient ID code and an ID code identifying the patient's general practitioner (GP). If the patient is a new patient and, therefore, does not already have a patient ID code and GP ID code assigned to them, the front end module provides the facility whereby the patient can enter their name and that of their GP, and the system will then assign corresponding patient and GP ID's.

Next, the patient is provided with a menu by means of which he/she can first select the category under which the required test, e.g. radiology (1) or pathology (2). Once the category has been selected, the patient is then asked to select the type of test required within that category, e.g. under radiology, the choices may include X-ray, ultrasound, MRI, CT scan, mammography, etc and under pathology, the types include blood test, etc., and a second menu giving the broad classifications of the selected category of test is provided for this purpose. Once the type has been selected, the patient is required to be even more specific as to what is required, and a third menu giving more detailed classifications is provided for this purpose. For example, if X- ray was selected, the patient would now be required to specify the anatomical location, e.g. leg, arm, hand, etc., or if blood test was selected, the patient would now have to specify what is to be tested for, e.g. glucose, TC/DC, blood cholesterol, HIV, etc. Once the required test has been precisely defined, one of a plurality of cubicles (corresponding to the specific test required to be performed) is identified to the patient, and a remote control (again, specific to the test required) is dispensed. This may considered to be analogous to a vending machine configuration, whereby a particular remote control is dispensed according to a selection made by the user.

Referring to Figure 2 of the drawings, the patient then proceeds to the allocated cubicle 100 and enables the cubicle 100 by transmission of a signal 102 from the remote control unit 104. Each cubicle 100 contains robotic test equipment for automatically performing a respective test, and in an exemplary embodiment, the robotic test equipment and the respective remote control unit are tuned to the same frequency, a different frequency being allocated to the equipment and remote control unit corresponding to each test available.

Once the patient has entered the selected cubicle 100, an interactive instruction set is provided, whereby the patient is given oral and/or visual, step-by-step instructions and, and once each instruction has been performed, the patient can confirm by transmitting a signal via the remote control (which may be in the form of a touch pad or the like), following which the test is performed. Several options may be provided by which the patient can communicate with the system, for example, there may be options indicating ready', wait', stop', painful', repeat instructions', repeat instructions slowly', etc. The test equipment is controlled by line-of-sight communication and/or frequency tuning.

The functionality of the robotic test equipment is controlled by a microcontroller, which imparts the desired movement thereto by regulating the motors associated therewith. Referring to Figure 4 of the drawings, the robot architecture is typically comprised of first and second processors 201, 202, a first primary memory 203 associated with the first processor 201, and a first secondary memory 205 (which may be of ROM type) associated with the second processor 202. A microcontroller 207 is provided for controlling movement of the motors (not shown) to control operation of the test equipment. A second primary memory 204 and a second secondary memory 206 are associated with the microcontroller 207. An antenna 208 is provided for receiving signals from the remote control (not shown). The robotic test equipment is arranged and configured to have ongoing learning capability in respect of a specific respective test. Thus, it captures data (e.g. image data) specific to a respective test and "learns" types of abnormalities/normalities.

Data collected during performance of the test is then transmitted, via a hard wired connection 106 in this case, to an interpretation and decision support system 108. For example, if the selected test was a mammogram or the like, image data collected during performance of the mammogram would be transmitted to the interpretation and decision support system 108. Means may be provided, either in the test equipment or the interpretation and decision support system, for determining whether or not a test has been performed correctly. Thus, for example, where the selected test involves collecting image data, image recognition means may be provided for determining if the test has been performed correctly.

Referring to Figure 3 of the drawings, a dedicated interpretation and decision support system 108 is provided in respect of each cubicle (i.e. each different test). Thus, each interpretation and decision support system 108 comprises a test specific database 110 for receiving data collected during performance of the corresponding test, and this data is then passed to a processor 112 for software (SIW) based interpretation and a pre-trained neural network or artificial intelligence structure provides an interpretation result, which is passed to a central database 114 and stored there in association with the respective patient ID provided at the beginning of the process. The interpretation result may also be printed out in the form of a report for the patient to read. In addition, a symptoms database 116 is provided, from which a symptoms of a subject under investigation can be retrieved and fed, along with the interpretation result, to a clinical decision support module which correlates the interpretation result and the respective symptoms, and the output is stored in a primary database 118 which is connected to a wireless transmission system, such that the results can be transmitted wirelessly to a remote communications device, such as the GP's PDA, according to the GP ID provided at the beginning of the process. In addition, the GP can also retrieve the original test data from the central database 114 via the remote telecommunications device. Once a diagnosis has been made, by the GP and/or the clinical decision support system, a message may be generated within the GP's PDA and transmitted directly to a pharmacy for dispensing of the required drugs to the patient.

As will be well known to a person skilled in the art, in general, neural networks are parallel information processing tools in which individual processing elements called neurons are arrayed in layers and furnished with a large number of interconnections between elements in successive layers. The functioning of the processing elements is modelled to approximate biological neurons where the output of the processing element is determined by a typically nonlinear transfer function. In a typical model for neural networks, the processing elements are arranged into an input layer for elements which receive inputs, an output layer containing one or more elements which generate an output, and one or more hidden layers of elements therebetween.

The hidden layers provide the means by which nonlinear problems may be solved.

Within a processing element, the input signals to the element are weighted arithmetically according to a weight coefficient associated with each input. The resulting weighted sum is transformed by a selected nonlinear transfer function, such as a sigmoid function, to produce an output, whose values range from 0 to 1, for each processing element. The learning process, called "training", is a trial and error process involving a series of iterative adjustments to the processing element weights so that a particular processing element provides an output which, when combined with the outputs of other processing elements, generates a result which minimises the resulting error between the outputs of the neural network and the desired outputs as represented by the training data. Adjustment of the element weights is triggered by error signals and training data is described as a number of training examples in which each example contains a set of input values to be presented to the neural network and an associated set of desired output values. When a neural network is trained on sufficient training data, it acts as an associative memory that is able to generalise a correct solution for sets of new input data that were not part of the training data.

Thus, in this case, each dedicated neural network based interpretation and decision support system is trained using training data specific to a respective test. In general, automatic interpretation of a set of medical test results is known, and clinical decision support systems which use such interpreted results are also known. For example, International Patent Application No. WO 2004/074982 describes a method of training neural networks for the detection of abnormalities in medical images, International Patent Application No. WO 02/059828 describes a system for computer-aided image analysis, International Patent Application No. WO 97/05553 describes a system for analysing patient data in a trained neural network and producing a diagnostic value, for the purpose of diagnosing disease and treating a patient, US Patent Application Publication No. US 2004/0015372 describes a clinical decision support system, whereby a medical test is performed (in the conventional manner by a skilled practitioner) and the data collected during performance of the test is fed to the decision support system for analysis, and International Patent Application No. WO 0 1/26026 describes a system which employs neural networks for medical diagnosis.

Thus, it will be apparent to a person skilled in the art the maimer in which a neural network can be trained to interpret medical test data and correlate the test results with the patient's symptoms to provide the clinical decision support referred to above.

However, none of the known systems provide for automatic performance of a selected test, or a system which is capable of selectively performing one of a plurality of tests without the need for skilled supervision or intervention.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be capable of designing many alternative embodiments without departing from the scope of the invention as defined by the appended claims. In the claims, any reference signs placed in parentheses shall not be construed as limiting the claims. The word "comprising" and "comprises", and the like, does not exclude the presence of elements or steps other than those listed in any claim or the specification as a whole. The singular reference of an element does not exclude the plural reference of such elements and vice-versa. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a device claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

Claims

CLAIMS: Apparatus for performing an investigative procedure in respect of

a live patient, the apparatus comprising testing equipment, motive means for moving said testing equipment relative to said patient, and a controller for controlling said motive means, said controller comprising means for receiving a signal indicating that a patient is present and prepared to said procedure to be performed, means for causing said motive means to move said testing equipment to a correct location relative to said patient, means for causing said testing equipment to perform said procedure in respect of said patient, and means for collecting data obtained by said test equipment during performance of said procedure.
2. Apparatus according to claim 1, further comprising means for interactively giving instructions to the patient and receiving signals indicating whether or not the patient has followed such instructions.
3. Apparatus according to claim 1 or claim 2, arranged and configured to be operable via a remote control unit.
4. Apparatus according to claim 3, wherein the remote control unit and respective apparatus are tuned to the same unique frequency.
5. A system for selectively performing one of a plurality of investigative procedures in respect of a live patient, apparatus according to any one of claims I to 4 being provided in respect of each respective investigative procedure, the system comprising means for enabling the investigative procedure required to be performed to be selected from a plurality of investigative procedures, means for enabling said patient to control the apparatus corresponding to the selected procedure so as to enable the selected procedure to be performed, and means for collecting data obtained by said apparatus during performance of said procedure.
6. A system according to claim 5, arranged and configured such that when an investigative procedure has been selected, a remote control unit specifically arranged and configured to operate the respective apparatus is dispensed.
7. A system according to claim 5 or claim 6, further comprising interpretation means for receiving data collected during performance of an investigative procedure, and interpreting said data to obtain one or more test results.
8. A system according to claim 7, further comprising a decision support system, wherein said test results and data representative of any symptoms experienced by the patient are used to generate advisory data in respect of said patient.
9. A system according to claim 8, wherein the decision support system comprises a pre-trained neural network.
10. A system according to claim 9, wherein a dedicated pre-trained neural network or artificial intelligence structure is provided in respect of each investigative procedure supported by the system.
11. A system according to any one of claims 7 to 10, further comprising wirelessly transmitting data from said interpretation means and/or said decision support system to a remote communications device.