Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
2. The action is responsive to the communications filed on 8/5/2025. Claims 1, 3-5, 7-8, 10-21, 23, and 32-39 are pending in the case. Claims 1, 7, 8, 10, 11, 32, 36 and 39 are amended. Claim 2, 6, 9, 22, 24-31 are cancelled. Claims 1, 24, 32, 39 are independent claims. Claims 1, 3-5, 7-8, 10-21, 23, and 32-39 are rejected.
Summary of claims
3. Claims 1, 3-5, 7-8, 10-21, 23, and 32-39 are pending,
Claims 1, 7, 8, 10, 11, 32, 36 and 39 are amended,
Claims 2, 6, 9, 22, 24-31 are cancelled,
Claims 1, 24, 32, 39 are independent claims,
Claims 1, 3-5, 7-8, 10-21, 23, and 32-39 are rejected.
Remarks
4. Applicant’s arguments, see Remarks, filed on 8/5/2025, with respect to the rejection(s) of claim(s) 1, 3-5, 7-8, 10-21, 23, and 32-39 under 103 have been fully considered and are not persuasive.
Applicant argued on pages 12-17 that the cited references including Xing, Yuan, Stumpe and Davies did not teach the amended features such as “extract a partial graph including, among the nodes included in the second graph, nodes belonging to a category of a display target selected by a user and an edge connecting the nodes, display a visualization graph that visualizes the partial graph, and display the nodes included in the visualization graph in a display mode according to the probability of relevance allocated to the nodes”, as recited in claim 1. Specifically, Applicant argued Xing, Yuan, Stumpe and Davies did not teach only a partial graph corresponding to a category that the user is focused on, and in particular, Davies discloses displaying a graph showing the time change of certain values. Examiner respectfully disagrees and submits that at least Davies discloses that user indicates record on first view (Fig. 8, step 214), choose how to display record’s context in newly generated views (Fig. 8, step 220), and updates newly generated views to display context of the original record (Fig. 8, step 222), specifically, Davies discloses providing the message 180 as a tooltip may provide the user with a convenient format for viewing the linked text, providing the message 180 as a tooltip may allow the user to see the relevant part of the clinical note without having to look at the rest of the clinical note, which may save time ([0127], the highlighting circuitry 28 generates a respective new presentation panel 180, 182, 184 for each of the identified keywords. The display circuitry 24 displays each of the new presentation panels 180, 182, 184 on display screen 16 ([0135]), that is, in Davies, user may select a particular content, and only the data related to the selected content is displayed to user. Accordingly, Xing, Yuan, Stumpe and Davies still read the amended features in claim 1.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
5. Claims 1, 3-5, 7-8, 10-21, 23, 32-39 are rejected under 35 U.S.C. 103 as being unpatentable over Xiaohan Xing et al (US Publication 20230028046 A1, hereinafter Xing), and in view of Quan Yuan et al (US Publication 20210375479 A1, hereinafter Yuan), and Martin Stumpe et al (US Publication 20220261668 A1, hereinafter Stumpe), and Michelle Louise Davies et al (US Publication 20180292978 A1, hereinafter Davies).
As for independent claim 1, Xing discloses: A medical information processing apparatus comprising a processor configured to (Xing: Abstract, provide omics data processing method and apparatus based on a graph neural network, a device and a medium, and relate to medical, artificial intelligence, cloud data and other technical fields): obtain medical care information relating to medical care events of a target patient (Xing: Fig. 1a, S101, acquire first omics data of a target object; [0141], omics data of patients may be obtained, and the omics data of each patient includes K different omics features (i.e., K groups of omics features in the graph). In this case, the omics data of patients may be used as training data (i.e., the training data X.sup.N?K in the figure) to train the initial graph neural network, to obtain an analysis result prediction model. Furthermore, medical analysis may be performed on the patient's omics data based on the analysis result prediction model; [0142], the medical analysis result corresponding to the omics data of the patient), wherein the medical care events include an event belonging to at least one category among a symptom, a physical finding, an examination finding, a treatment, a treatment reaction, and a side effect (Xing: [0034], using corresponding sample category tags as supervision signals to train a model, and screening optimal parameters of the model according to the performance of the validation set to obtain a final model, and then performing disease prediction on the omics data based on the final model), and the medical care information includes a combination of kinds of the medical care events and corresponding values indicative of degrees of relevance of the target patient to the kinds of the medical care events (Xing: [0147], an output y of the analysis result prediction model is R.sup.c (i.e., y∈R.sup.c), where R.sup.c represents a probability that the patient's omics data corresponds to each disease, or a probability that the patient's omics data corresponds to each category of diseases. In a case that survival prediction is performed based on the feature R.sup.d1 to determine a survival probability of the patient, the survival probability R.sup.1 corresponding to the omics data of the patient (i.e., the medical analysis result in the previous text) may be obtained based on the feature R.sup.d1); map the medical care information on a first graph to generate a second graph relating to the target patient (Xing: [0078], in response to fusing the first feature and the at least one second feature of each node, the first feature and the at least one second feature may be mapped to a same node dimension through respective fully connected layers, to obtain each mapped feature, and then the mapped features are fused by stitching, and the fused feature is used as the node feature of each node; [0106], constructing, based on the at least two second omics features and each second correlation, a second graph structure corresponding to the second omics data), the first graph and the second graph including nodes corresponding to the medical care events and edges indicative of a relationship between the nodes (Xing: [0076], for each node in the first graph structure, each target node having a connecting edge relationship with the node may be determined); and estimate medical judgment information relating to the target patient, based on the second graph relating to the target patient (Xing: [0066], by constructing the graph structure of the omics data, the omics features that execute similar functions may be connected in the graph, in this case, not only the individual omics features may be reflected, but also the action relationship between different omics features may be reflected, and the pathogenic mechanism may be better revealed, and the simulation of biological processes may be realized, so that more accurate disease prediction effects may be obtained).
Xing discloses acquiring the patient’s data and performing medical analysis on the patient’s omics data (Xing: [0141], [0142]), it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to recognize the patient’s omics data relates to medical care event, in addition, in an analogous art of processing medical data, performing analysis and obtaining medical prediction, Yuan clearly discloses: obtain medical care information relating to medical care events of a target patient, wherein the medical care events include an event belonging to at least one category among a symptom, a physical finding, an examination finding, a treatment, a treatment reaction, and a side effect (Yuan: Abstract, acquiring symptom entity data in electronic medical record data; obtaining symptom entity representation data based on the symptom entity data and a symptom entity representation model; [0037], the electronic medical record of a target patient is retrieved from an electronic medical record system, and symptom entity data are acquired from the electronic medical record; [0093], patient’s symptom data may include examination and inspection results);
Xing and Yuan are analogous arts because they are in the same field of endeavor, processing medical data, performing analysis and obtaining medical prediction. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Yuan to expressly include obtaining medical record information of a target patient. It would provide Xing’s apparatus with enhanced capabilities of perform more accurate data classification and to enabling the patient to obtain more accurate medical treatment measures and achieve the purpose of accurate treatment.
Further, Xing discloses predicting medical judgement information ([0066]) including a probability that the patient's omics data corresponds to each disease ([0147]), but Xing does not expressly disclose a probability of relevance to each disease, Stumpe discloses: wherein the medical judgement information includes a probability of relevance to each disease (Stumpe: [0099], hypotheses are ranked using evidence scoring based on embedding likelihoods, and a final confidence score is derived by merging independent ranks for different sources of evidence; [0134], A confidence score could be added to the ranking/classification based on the number and quality/source of the found existing relations);
Xing and Stumpe are analogous arts because they are in the same field of endeavor, processing medical data, performing analysis and obtaining medical prediction. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Stumpe to include scoring based on embedding likelihoods. It would provide Xing’s apparatus with enhanced capabilities of perform more accurate data classification and to enabling the patient to obtain more accurate medical treatment measures and achieve the purpose of accurate treatment.
Furthermore, Xing discloses different categories of data in the knowledge graph, but Xing does not clearly disclose displaying a partial graph, in another analogous art of medical data presentation, Davies discloses: extract a partial graph including, among the nodes included in the second graph, nodes belonging to a category of a display target selected by a user and an edge connecting the nodes, display a visualization graph that visualizes the partial graph, and display the nodes included in the visualization graph in a display mode according to the probability of relevance allocated to the nodes (Davies: [0069], the highlighting circuitry 28 determines how to display the context of data from the set of lab results 68 in each view in which data from the record is found. Any suitable display method or methods may be used. For example, data may be highlighted by changing a text color, changing a background color, changing a text format (for example, bolding, italicizing or changing typeface), using an indicator (for example, a pointer, box or balloon), using an animation, animating an existing feature, or overlaying an indicator or other feature; [0127], providing the message 180 as a tooltip may provide the user with a convenient format for viewing the linked text, providing the message 180 as a tooltip may allow the user to see the relevant part of the clinical note without having to look at the rest of the clinical note, which may save time; [0135], the highlighting circuitry 28 generates a respective new presentation panel 180, 182, 184 for each of the identified keywords. The display circuitry 24 displays each of the new presentation panels 180, 182, 184 on display screen 16; that is, in Davies, user may select a particular content, and only the data related to the selected content is displayed to user);
Xing and Davies are analogous arts because they are in the same field of endeavor, processing medical data. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Davies to include displaying the analysis result focus on some content. It would provide Xing’s apparatus with enhanced capabilities of allowing user to choose how to display record’s context in newly generated views, see the relevant part of the clinical note without having to look at the rest of the clinical note, which may save time.
claim 2, cancelled
As for claim 3, Xing-Yuan discloses: wherein the processor is further configured to estimate, by utilizing a trained model, the medical judgment information relating to the target patient, based on the second graph relating to the target patient, and the trained model is a machine learning model trained such that the machine learning model inputs therein the second graph and outputs the medical judgment information (Xing: [0043], machine learning and deep leaning generally include technologies such as an artificial neural network, a belief network, reinforcement learning, transfer learning, inductive learning and learning from demonstrations; [0108], since the graph neural network to which each of the omics corresponds is trained based on different categories of sample omics features, in this case, the network parameters of the graph neural network to which each of the omics corresponds are different; [0110]-[0111], the analysis result prediction model is obtained by training an initial neural network model based on each sample omics data, the initial neural network model is trained based on the obtained sample omics data to obtain an analysis result prediction model) .
As for claim 4, Xing-Yuan discloses: wherein the trained model includes: a graph convolution layer configured to apply a convolution process to the second graph, and configured to output a third graph (Xing: [0069], the first graph neural network is a graph neural network corresponding to the omics to which the first omics data belongs, and the specific type of the first graph neural network may be pre-configured, for example, the graph neural network may be a Graph Attention Network, and other graph neural networks, such as a graph convolution network, a graph self-encoder network, etc. [0087], based on the initial feature of the node and the initial feature of each target node corresponding to the node, the weight of each associated feature is determined through a graph convolution network; Xing: a graph convolutional neural network layer); a readout layer configured to convert the third graph to a feature vector (Yuan: [0041], the symptom entity representation data are vectorized representation of the symptom entity data; [0043], a vector coding layer); and a dense layer configured to convert the feature vector to the medical judgment information (Yuan: [0088], by setting the graph convolutional neural network layer in the symptom entity representation model to include the first graph convolutional neural network sublayer and the second graph convolutional neural network sublayer, the first graph convolutional neural network sublayer is used to obtain the disease vectorized representation data fused with graph structure information based on the medical knowledge graph and the disease encoding vector; the second convolutional neural network sublayer is used to obtain the symptom vectorized representation data fused with graph structure information based on the medical knowledge graph, the symptom encoding vector and the disease vectorized representation data, so that the graph convolutional neural network can parse important medical knowledge graph structural features, improving the accuracy of the finally obtained symptom vectorized representation data, and the complexity of calculation and the computational time overhead can be effectively reduced).
As for claim 5, Xing-Yuan discloses: wherein the graph convolution layer computes, with respect to each of nodes included in the second graph, a feature after a convolution process, based on a feature before the convolution process in regard to a process-target node and an adjacent node to the process-target node, an adjacency matrix indicative of the edge connecting the process-target node and the adjacent node, and a weight on the edge, and the readout layer converts the feature after the convolution process in regard to each of the nodes to the feature vector (Xing: [0058], a correlation matrix between different omics features may be calculated by Weighted Gene Co-Expression Network Analysis (WGCNA), and then binary processing may be performed on the correlation matrix by setting a threshold, and the correlation matrix subjected to the binary processing is called an edge matrix. For example, in a case that the correlation between two first omics features is not less than the threshold, it is indicated that the functions executed by the two first omics features are similar and interact with each other (i.e., constituting a signal pathway). In this case, values of elements in the correlation matrix representing the correlation between the two first omics features may be set to 1, and in a case that the correlation between the two first omics features is less than the threshold, it is indicated that the correlation between the two first omics features is lower, the values of the elements in the correlation matrix representing the correlation between the two first omics features may be set to 0).
claim 6, canceled
As for claim 7, Xing-Yuan discloses: wherein the processor is further configured to cause the display to display nodes included in the visualization graph in a display mode corresponding to patient features allocated to the nodes included in the second graph (Yuan: [0042], The symptom entity representation model is provided with a graph convolutional neural network layer, for converting the symptom entity data into symptom entity representation data fused with graph structure information based on a pre-established medical knowledge graph. The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
As for claim 8, Xing-Yuan discloses: wherein the processor is further configured to cause the display to display the nodes included in the visualization graph in a display mode corresponding to disease influence levels that correspond to the nodes and are allocated to the nodes included in the second graph (Yuan: [0042], The symptom entity representation model is provided with a graph convolutional neural network layer, for converting the symptom entity data into symptom entity representation data fused with graph structure information based on a pre-established medical knowledge graph. The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
claim 9, canceled
As for claim 10, Xing-Yuan discloses: wherein the nodes are classified into at least two categories among the symptom, the physical finding, the examination finding, the treatment, the treatment reaction, and the side effect (Yuan: [0075], the first graph convolutional neural network sub-layer 20 is used to obtain disease vectorized representation data fused with graph structure information, based on the medical knowledge graph and a disease encoding vector of a target disease entity node, the target disease entity node having a connection relationship with a target symptom entity node corresponding to the symptom entity data).
As for claim 11, Xing-Yuan discloses: wherein the processor is further configured to add, to the nodes included in the visualization graph, names or symbols of the medical care events corresponding to the nodes (Yuan: [0142], provide interaction with the user, for example, provide feedback to user and receive input from the user, please note receiving input from the user may include adding names or symbols to the node in the graphic interface).
As for claim 12, Xing-Yuan discloses: wherein the graph convolution layer switches parameters of the convolution process in accordance with an edge relation type of process-target edges connected to process-target nodes, and the edge relation type is a cause-and-effect direction, a cause-and-effect strength and/or a strength of correlation between medical care events relating to the process-target edges (Yuan: [0088], by setting the graph convolutional neural network layer in the symptom entity representation model to include the first graph convolutional neural network sublayer and the second graph convolutional neural network sublayer, the first graph convolutional neural network sublayer is used to obtain the disease vectorized representation data fused with graph structure information based on the medical knowledge graph and the disease encoding vector; the second convolutional neural network sublayer is used to obtain the symptom vectorized representation data fused with graph structure information based on the medical knowledge graph, the symptom encoding vector and the disease vectorized representation data, so that the graph convolutional neural network can parse important medical knowledge graph structural features, improving the accuracy of the finally obtained symptom vectorized representation data, and the complexity of calculation and the computational time overhead can be effectively reduced).
As for claim 13, Xing-Yuan discloses: wherein the graph convolution layer switches parameters of the convolution process in accordance with an edge relation type of process-target edges connected to process-target nodes, and the edge relation type is a combination of a category of a medical care event of the process-target node to which the process-target edge is connected, and a category of a medical care event of an adjacent node that neighbors the process-target node (Yuan: [0088], by setting the graph convolutional neural network layer in the symptom entity representation model to include the first graph convolutional neural network sublayer and the second graph convolutional neural network sublayer, the first graph convolutional neural network sublayer is used to obtain the disease vectorized representation data fused with graph structure information based on the medical knowledge graph and the disease encoding vector; the second convolutional neural network sublayer is used to obtain the symptom vectorized representation data fused with graph structure information based on the medical knowledge graph, the symptom encoding vector and the disease vectorized representation data, so that the graph convolutional neural network can parse important medical knowledge graph structural features, improving the accuracy of the finally obtained symptom vectorized representation data, and the complexity of calculation and the computational time overhead can be effectively reduced).
As for claim 14, Xing-Yuan discloses: wherein the graph convolution layer switches parameters of the convolution process in accordance with a kind of the medical judgment information (Yuan: [0088], by setting the graph convolutional neural network layer in the symptom entity representation model to include the first graph convolutional neural network sublayer and the second graph convolutional neural network sublayer, the first graph convolutional neural network sublayer is used to obtain the disease vectorized representation data fused with graph structure information based on the medical knowledge graph and the disease encoding vector; the second convolutional neural network sublayer is used to obtain the symptom vectorized representation data fused with graph structure information based on the medical knowledge graph, the symptom encoding vector and the disease vectorized representation data, so that the graph convolutional neural network can parse important medical knowledge graph structural features, improving the accuracy of the finally obtained symptom vectorized representation data, and the complexity of calculation and the computational time overhead can be effectively reduced).
As for claim 15, Xing-Yuan discloses: wherein the graph convolution layer switches parameters of the convolution process in accordance with a kind of a disease in the medical judgment information (Yuan: [0088], by setting the graph convolutional neural network layer in the symptom entity representation model to include the first graph convolutional neural network sublayer and the second graph convolutional neural network sublayer, the first graph convolutional neural network sublayer is used to obtain the disease vectorized representation data fused with graph structure information based on the medical knowledge graph and the disease encoding vector; the second convolutional neural network sublayer is used to obtain the symptom vectorized representation data fused with graph structure information based on the medical knowledge graph, the symptom encoding vector and the disease vectorized representation data, so that the graph convolutional neural network can parse important medical knowledge graph structural features, improving the accuracy of the finally obtained symptom vectorized representation data, and the complexity of calculation and the computational time overhead can be effectively reduced).
As for claim 16, Xing-Yuan discloses: wherein the processor is further configured to determine a period of the medical care information to be mapped, in accordance with a kind of a disease of a classification target that is the medical judgment information (Xing: [0078], In response to fusing the first feature and the at least one second feature of each node, the first feature and the at least one second feature may be mapped to a same node dimension through respective fully connected layers, to obtain each mapped feature, and then the mapped features are fused by stitching, and the fused feature is used as the node feature of each node; Yuan: [0086], represents a frequency of the target symptom entity node presenting in medical records with the target disease entity node as the main diagnosis, that is, the number of times of that the target symptom entity node shows up in the medical records which are with the target disease entity node as the main diagnosis per unit time).
As for claim 17, Xing-Yuan discloses: wherein the medical care information includes an order of occurrence of the medical care event, a count of occurrences of the medical care event, and/or a degree of occurrence of the medical care event, and the processor is further configured to map the medical care information on the nodes as a node feature (Xing: [0128], The importance parameter value of the first omics feature represents the degree of importance of the first omics feature in a signal pathway constructed by the first omics feature; Yuan: [0086], represents a frequency of the target symptom entity node presenting in medical records with the target disease entity node as the main diagnosis, that is, the number of times of that the target symptom entity node shows up in the medical records which are with the target disease entity node as the main diagnosis per unit time).
As for claim 18, Xing-Yuan discloses: wherein the medical care information includes local information and/or temporal information relating to the medical care events, the processor is further configured to map the local information and/or the temporal information on the nodes as a node feature, the local information is information relating to a position of occurrence of a particular medical care event, and the temporal information is information relating to a time of occurrence of the particular medical care event (Yuan: [0086], represents a frequency of the target symptom entity node presenting in medical records with the target disease entity node as the main diagnosis, that is, the number of times of that the target symptom entity node shows up in the medical records which are with the target disease entity node as the main diagnosis per unit time).
As for claim 19, Xing-Yuan discloses: wherein a plurality of pieces of medical care information with different time instants of occurrence are allocated to the nodes, and the processor is further configured to estimate, by utilizing a trained model including a graph convolution layer and a recurrent neural network layer, the medical judgment information relating to the target patient from the second graph including the nodes to which the plurality of pieces of medical care information are allocated (Yuan: [0086], represents a frequency of the target symptom entity node presenting in medical records with the target disease entity node as the main diagnosis, that is, the number of times of that the target symptom entity node shows up in the medical records which are with the target disease entity node as the main diagnosis per unit time).
As for claim 20, Xing-Yuan discloses: wherein the medical care information includes medical care information of the target patient, and medical care information of another patient whose spatial information is close to the target patient, the spatial information includes local information and/or biological information of the another patient, and the processor is further configured to map the medical care information of the target patient and the medical care information of the another patient on the nodes as node features (Xing: [0141], omics data of N patients may be obtained, the omics data of N patients may be used as training data to train the initial graph neural network, to obtain an analysis result prediction model).
As for claim 21, Xing-Yuan discloses: wherein the processor is further configured to estimate, as the medical judgment information, at least one among disease classification information, prognosis estimation information and severity level classification information corresponding to the second graph relating to the target patient (Xing: [0145], disease diagnosis, disease typing, or survival prediction may be performed; [0147], In some embodiments, in a case that disease diagnosis or disease typing (i.e., disease classification and typing in the figure) is performed based on the feature R.sup.d1, the feature R.sup.d1 may be mapped to a feature with the dimension the same as the number of disease types or disease categories (c disease types or disease categories are taken as an example in this example), and then a disease prediction result or disease typing prediction result R.sup.c (i.e., the medical analysis result in the foregoing text) is obtained based on the mapped feature; Yuan: [0056], The disease prediction result corresponding to the electronic medical record data is obtained based on the symptom entity representation data and the classification model obtained by pre-training, and the effect of disease prediction for the patient based on the patient's electronic medical record data is realized).
claim 22 cancelled
As for claim 23, Xing-Yuan discloses: wherein the first graph is a graph generated based on medical care information of a plurality of patients, or medical ontology (Xing: [0141], omics data of N patients may be obtained, the omics data of N patients may be used as training data to train the initial graph neural network, to obtain an analysis result prediction model).
claims 24-31 cancelled
As for independent claim 32, Xing discloses: A medical information display apparatus comprising (Xing: Abstract, provide omics data processing method and apparatus based on a graph neural network, a device and a medium, and relate to medical, artificial intelligence, cloud data and other technical fields): a memory to store a graph including nodes corresponding to medical care events and edges indicative of a relationship between the nodes, a patient feature and/or a disease influence level being allocated to the nodes (Xing: [0076], for each node in the first graph structure, each target node having a connecting edge relationship with the node may be determined; [0147], In a case that survival prediction is performed based on the feature R.sup.d1 to determine a survival probability of the patient, the survival probability R.sup.1 corresponding to the omics data of the patient (i.e., the medical analysis result in the previous text) may be obtained based on the feature R.sup.d1. In this case, the output y of the analysis result prediction model is R.sup.1 (i.e., y∈R.sup.1));
Xing discloses acquiring the patient’s data and performing medical analysis on the patient’s omics data (Xing: [0141], [0142]), it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to recognize the patient’s omics data relates to medical care event, in addition, in an analogous art of processing medical data, performing analysis and obtaining medical prediction, Yuan clearly discloses: based on medical care information, wherein the medical care events include events belonging to categories that include a symptom, a physical finding, an examination finding, a treatment, a treatment reaction, and a side effect, and the medical care information includes a combination of kinds of the medical care events and corresponding values indicative of degrees of relevance of the target patient to the kinds of the medical care events (Yuan: Abstract, acquiring symptom entity data in electronic medical record data; obtaining symptom entity representation data based on the symptom entity data and a symptom entity representation model; [0037], the electronic medical record of a target patient is retrieved from an electronic medical record system, and symptom entity data are acquired from the electronic medical record; [0065], The connection relationships among the disease entity node, the symptom entity node, the disease entity node, and the connection relationships between the disease entity nodes and the symptom entity nodes in the medical knowledge graph of the present embodiment are mined from a large number of real desensitization medical records based on a statistical method. In the medical knowledge graph, the connection relationship between disease entity nodes has no weight, while the connection relationship between disease entity nodes and symptom entity nodes has a weight. This weight is obtained based on the frequency of the occurrence of the disease entity node, the greater the frequency, the greater the weight. Alternatively, since the connection relationship between disease entity nodes and symptom entity nodes has a long tail characteristic, and the connection relationship with a low weight is generally generated due to noise data, an overall effect will be affected if this part of low-weight edges are introduced into the calculation process. So the connection relationship associated with each symptom entity node is truncated, and only the connection relationship corresponding to a score in the Top-k range is retained. Preferably, k is set to 5, that is, each symptom entity node forms connection relationships with at most 5 disease entity nodes; [0093], patient’s symptom data may include examination and inspection results);
Xing and Yuan are analogous arts because they are in the same field of endeavor, processing medical data, performing analysis and obtaining medical prediction. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Yuan to expressly include obtaining medical record information of a target patient. It would provide Xing’s apparatus with enhanced capabilities of perform more accurate data classification and to enabling the patient to obtain more accurate medical treatment measures and achieve the purpose of accurate treatment.
Further, Xing does not clearly disclose a visualization graph, in an analogous art of processing medical data, performing analysis and obtaining medical prediction, Yuan clearly discloses: and processor configured to select a patient and/or a disease which is a display target (Yuan: [0143], a user computer having a graphical user interface or a web browser, through which the user may interact with the implementations of the systems and the technologies).
Xing and Yuan are analogous arts because they are in the same field of endeavor, processing medical data, performing analysis and obtaining medical prediction. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Yuan to expressly include displaying the visualization graph in a graphical user interface or a web browser. It would provide Xing’s apparatus with enhanced capabilities of allowing user to interact with the visualized graph.
Further, Xing discloses predicting medical judgement information ([0066]) including a probability that the patient's omics data corresponds to each disease ([0147]), but Xing does not expressly disclose a probability of relevance to each disease, Stumpe discloses: estimate medical judgement information relating to the target patient based on the second graph relating to the target patient, wherein the medical judgement information includes a probability of relevance to each disease (Stumpe: [0099], hypotheses are ranked using evidence scoring based on embedding likelihoods, and a final confidence score is derived by merging independent ranks for different sources of evidence; [0134], A confidence score could be added to the ranking/classification based on the number and quality/source of the found existing relations);
Xing and Stumpe are analogous arts because they are in the same field of endeavor, processing medical data, performing analysis and obtaining medical prediction. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Stumpe to include scoring based on embedding likelihoods. It would provide Xing’s apparatus with enhanced capabilities of perform more accurate data classification and to enabling the patient to obtain more accurate medical treatment measures and achieve the purpose of accurate treatment.
Furthermore, Xing discloses different categories of data in the knowledge graph, but Xing does not clearly disclose displaying partial graph, in another analogous art of medical data presentation, Davies discloses: extract a partial graph including, among the nodes included in the second graph, nodes belonging to a category of a display target selected by a user and edge connecting the nodes, display a visualization graph that visualizes the partial graph, and display the nodes included in the visualization graph in a display mode according to the probability of relevance allocated to the node (Davies: [0069], the highlighting circuitry 28 determines how to display the context of data from the set of lab results 68 in each view in which data from the record is found. Any suitable display method or methods may be used. For example, data may be highlighted by changing a text color, changing a background color, changing a text format (for example, bolding, italicizing or changing typeface), using an indicator (for example, a pointer, box or balloon), using an animation, animating an existing feature, or overlaying an indicator or other feature; [0127], providing the message 180 as a tooltip may provide the user with a convenient format for viewing the linked text, providing the message 180 as a tooltip may allow the user to see the relevant part of the clinical note without having to look at the rest of the clinical note, which may save time; [0135], the highlighting circuitry 28 generates a respective new presentation panel 180, 182, 184 for each of the identified keywords. The display circuitry 24 displays each of the new presentation panels 180, 182, 184 on display screen 16; that is, in Davies, user may select a particular content, and only the data related to the selected content is displayed to user);
Xing and Davies are analogous arts because they are in the same field of endeavor, processing medical data. Therefore, it would have been obvious to one with ordinary skill, in the art before the effective filing date of the claimed invention, to modify the invention of Xing using the teachings of Davies to include displaying the analysis result focus on some content. It would provide Xing’s apparatus with enhanced capabilities of allowing user to choose how to display record’s context in newly generated views, see the relevant part of the clinical note without having to look at the rest of the clinical note, which may save time.
As for claim 33, Xing-Yuan discloses: wherein when a specific patient is selected as the display target, the processor is further configured to cause the display to display nodes included in the visualization graph in a display mode corresponding to a patient feature of the specific patient, the patient feature corresponding to the nodes (Yuan: [0037], the electronic medical record of a target patient (a specific patient) is retrieved from an electronic medical record system, and symptom entity data are acquired from the electronic medical record; Yuan: [0042], The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
As for claim 34, Xing-Yuan discloses: wherein when a specific disease is selected as the display target, the processor is further configured to cause the display to display nodes included in the visualization graph in a display mode corresponding to a disease influence level of the specific disease, the disease influence level corresponding to the nodes (Xing: [0090], Perform medical analysis on the target object based on the node feature of each node, and obtain a medical analysis result corresponding to each dimension in the at least one dimension, the medical analysis including performing disease diagnosis, disease typing, and survival prediction on the target object; Yuan: [0042], The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
As for claim 35, Xing-Yuan discloses: wherein when a combination of a specific patient and a specific disease is specified as the display target, the processor is further configured to cause the display to display nodes included in the visualization graph in a display mode corresponding to a patient feature of the combination, which corresponds to the nodes, and in a second display mode corresponding to a disease influence level of the combination (Xing: [0090], Perform medical analysis on the target object based on the node feature of each node, and obtain a medical analysis result corresponding to each dimension in the at least one dimension, the medical analysis including performing disease diagnosis, disease typing, and survival prediction on the target object; Yuan: [0042], The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
As for claim 36, Xing-Yuan discloses: wherein the nodes are classified into at least two categories among a symptom, a physical finding, an examination finding, a treatment, a treatment reaction, and a side effect (Xing: [0128], the medical personnel may learn, according to the importance parameter value of each first omics feature, the omics feature that plays an important role in the medical analysis result, and then propose a biological explanation, which is conductive to enabling the patient to obtain more accurate medical treatment measures and achieve the purpose of accurate treatment; Yuan: Abstract, acquiring symptom entity data in electronic medical record data; obtaining symptom entity representation data based on the symptom entity data and a symptom entity representation model; [0042], The medical knowledge graph includes disease entity nodes and symptom entity nodes, and there are a connection relationships between disease entity nodes and between the disease entity nodes and the symptom entity nodes).
As for claim 37, Xing-Yuan discloses: wherein the processor is further configured to cause the display to display a display screen including a display area of the visualization graph, and a selection area of the category of the display target (Yuan: [0143], a user computer having a graphical user interface or a web browser, through which the user may interact with the implementations of the systems and the technologies; please note the interactive graphical user interface or a web browser may include a display area and a selection area which provide interaction capabilities in GUI).
As for claim 38, Xing-Yuan discloses: wherein the processor is further configured to cause the display to display a display screen including a display area of the visualization graph, and a selection area of the patient and/or the disease of the display target (Yuan: [0143], a user computer having a graphical user interface or a web browser, through which the user may interact with the implementations of the systems and the technologies; please note the interactive graphical user interface or a web browser may include a display area and a selection area which provide interaction capabilities in GUI).
As per claim 39, it recites features that are substantially same as those features claimed by claim 1, thus the rationales for rejecting claim 1 are incorporated herein.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final acti