CN114334145A - Dynamic identification method for atypical critical patients - Google Patents
Dynamic identification method for atypical critical patients Download PDFInfo
- Publication number
- CN114334145A CN114334145A CN202111481837.9A CN202111481837A CN114334145A CN 114334145 A CN114334145 A CN 114334145A CN 202111481837 A CN202111481837 A CN 202111481837A CN 114334145 A CN114334145 A CN 114334145A
- Authority
- CN
- China
- Prior art keywords
- data sequence
- sign data
- dynamic
- patient
- dynamic sign
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to a dynamic identification method of atypical critical patients, which comprises the steps of calculating the proximity distance between a first dynamic sign sequence set of a patient to be detected and a second dynamic sign data sequence set of a historical patient to obtain first K second dynamic sign data sequence sets with the minimum proximity distance to form a candidate set, calculating the risk score of the patient to be detected according to the proximity distance between the first dynamic sign sequence set of the patient to be detected and each second dynamic sign sequence set of the candidate set, and finally comparing the risk score with a set threshold value to judge whether the patient to be detected is a critical patient. Because the first dynamic sign sequence set corresponds to at least two signs of the patient to be tested one by one, and is a dynamic data sequence of the sign data of the patient to be tested in a time domain, compared with the original method for manually judging whether the patient to be tested is a critical patient through static data, the method is more accurate and has higher efficiency.
Description
Technical Field
The invention relates to identification, in particular to a dynamic identification method for atypical critical patients.
Background
Aiming at the contradiction between the increase of the emergency treatment amount and the limited medical resource distribution, the medical resource can be reasonably distributed by adopting an emergency treatment triage system and arranging the treatment priority according to the degree of illness of a patient. The triage system has the characteristic of timeliness, and the triage error of the triage system can cause emergency treatment congestion and diagnosis delay problems of different degrees, and correspondingly causes the problems of medical resource waste or increase of the death rate of patients.
In China, a 4-level diagnosis system determined in the 'emergency patient condition grading guiding principle' issued by the Wei Ji Commission in 2011 is currently used, endangered and critically ill patients with the diagnosis grading of 1-2 are directly diagnosed to enter a rescue room or monitor vital signs, and emergency and non-emergency patients with the diagnosis grading of 3-4 need to wait for the diagnosis room to receive a call. The present triage system is accurate and effective in most cases, but still some potentially critical patients are triaged to 3-4 levels by the electronic triage system, but are sent to the rescue room in a short time. The procedure of waiting for a visit may be dangerous for such patients. The error of the diagnosis system is ubiquitous in various diagnosis systems, potential critical patients are identified through a reasonable means, and the diagnosis delay problem under an emergency scene is improved. If the dynamic evaluation can be carried out on the patient during the waiting period of the patient, the state change of the atypical critical patient can be found in time, the identification of the atypical critical patient is more favorable to the single evaluation compared with the single evaluation in the room, the international colleagues also adopt a mode of intermittently measuring key signs in an emergency room, data are collected for a plurality of hours and then re-graded, but the mode is still static evaluation and does not fully mine the dynamic development data of the patient.
In summary, the existing triage system mainly has the following two problems:
1. the existing emergency classification is usually classified once according to data of patients when the patients are admitted to a hospital for treatment, the data used for classification is generally vital signs and important chief complaints of the patients when the patients are treated, and the data is a static evaluation mode, can only reflect disease states of the patients when the patients are treated, cannot find disease changes of the patients when the patients wait for treatment, and does not consider other factors related to critical illness.
2. For patients initially classified as urgent and non-urgent, during their waiting period, physicians may take intermittent measurements to collect key signs of patients at different times and then re-grade the signs. But the grading system under the rule system can only evaluate the current state of the patient and still belongs to a static evaluation mode.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a dynamic identification method for atypical critical patients based on multivariate time series data mining, which makes full use of dynamic physical sign data of the patients during waiting period.
The invention discloses a dynamic identification method of atypical critical patients, which comprises the following steps:
s1: acquiring a first dynamic sign data sequence set of a patient to be detected, wherein the first dynamic sign data sequence set comprises a plurality of first dynamic sign data sequences which correspond to at least two signs of the patient to be detected one by one;
s2: acquiring N second dynamic sign data sequence sets corresponding to N historical patients, wherein each second dynamic sign data sequence set comprises a plurality of second dynamic sign data sequences corresponding to the corresponding historical patients and the signs one to one;
s3: respectively calculating the proximity distance D between the first dynamic sign data sequence set in the step S1 and each second dynamic sign data sequence set in the N second dynamic sign data sequence sets in the step S2;
s4: acquiring first K second dynamic sign data sequence sets with the minimum approximation distance in the step S3, and forming a candidate set by the K second dynamic sign data sequence sets with the minimum approximation distance, wherein K is smaller than N;
s5: acquiring the risk score of the patient to be tested by the following formula:
wherein D isiThe approximation distance between the first dynamic sign data sequence set and the ith second dynamic sign data sequence set in the candidate set is obtained;
wherein, ciThe values of (A) are as follows:
c when the ith second dynamic sign data sequence set in the candidate set is a positive samplei＝1；
C when the ith second dynamic sign data sequence set in the candidate set is a negative samplei＝-1；
If the historical patient corresponding to the second dynamic sign data sequence set is a critical patient, the second dynamic sign data sequence set is a positive sample;
if the historical patient corresponding to the second dynamic sign data sequence set is not a critical patient, the second dynamic sign data sequence set is a negative sample;
s6: judging whether the patient to be detected is a critical patient or not according to the risk score acquired in the step S5 and the set threshold value:
if the risk score is larger than a set threshold value, the patient to be detected is a critical patient;
and if the risk score is less than or equal to the set threshold value, the patient to be detected is not a critical patient.
The dynamic identification method of atypical critical patients comprises the steps of calculating the proximity distance between a first dynamic sign sequence set of a patient to be detected and a second dynamic sign data sequence set of historical patients to obtain first K second dynamic sign data sequence sets with the minimum proximity distance to form a candidate set, calculating the risk score of the patient to be detected according to the proximity distance between the first dynamic sign sequence set of the patient to be detected and each second dynamic sign sequence set of the candidate set, and finally comparing the risk score with a set threshold value to judge whether the patient to be detected is a critical patient. Because the first dynamic sign sequence set corresponds to at least two signs of the patient to be tested one by one, and is a dynamic data sequence of the sign data of the patient to be tested in a time domain, compared with the original method for manually judging whether the patient to be tested is a critical patient through static data, the method is more accurate and has higher efficiency.
Further, in the dynamic identification method of atypical critical patients according to the present invention, the approximation distance calculation method in step S3 is as follows:
s31: calculating the proximity distance d between each first dynamic sign data sequence in the first dynamic sign data sequence set and a second dynamic sign data sequence corresponding to the first dynamic sign data sequence in the second dynamic sign data sequence set;
the first dynamic sign data sequence and the second dynamic sign data sequence correspond to each other, and the sign data recorded by the first dynamic sign data sequence are the same in type as the sign data recorded by the second dynamic sign data sequence; here, the approximation distance d may be a euclidean distance;
s32: obtaining the approximate distance between the first dynamic sign data sequence set and the second dynamic sign data sequence set by the following formula:
wherein n is the number of physical sign types, diThe approximation distance between a first dynamic sign data sequence corresponding to the feature in the ith and a second dynamic sign data sequence set is obtained;
wherein wiAttribute weight of the approximation distance corresponding to the ith sign data;
the method calculates the proximity distance between each first dynamic sign data sequence in the first dynamic sign data sequence set and the corresponding second dynamic sign data sequence in the second dynamic sign data sequence set, and obtains the proximity value between the first dynamic sign data sequence set and the second dynamic sign data sequence set by combining the attribute weight of the proximity distance, thereby realizing the calculation of the proximity distance between the multiple sequence sets. Here, the multiple sequence set value is a set formed by data sequences corresponding to various physical signs. The attribute weight is set by an operator according to historical data experience, or set after autonomous learning by a deep learning system.
Further, in the method for dynamically identifying atypical critical patients according to the present invention, before calculating the proximity distance d between the first dynamic sign data sequence and the corresponding second dynamic sign data sequence in step S31, the two data sequences are dynamically time-warped by the DTW algorithm.
And the DTW algorithm is adopted to carry out dynamic time warping on the data sequence, so that the approximation distance obtained by calculation after warping is more accurate.
Further, the dynamic identification method for atypical critical patients of the present invention further comprises the steps of performing data segmentation and feature extraction on the data sequence before performing dynamic time warping.
According to the high-dimensional characteristics of the dynamic patient sign data, before the classification identification model is constructed, local feature extraction or global feature decomposition is carried out on a data sequence to reduce dimensionality and capture relevant information between trend change and different dimensionalities, so that effective information of patient condition change is extracted. The strategy and the result of the feature representation are directly related to the performance of the subsequent classification recognition model.
For data segmentation, in order to extract local features, a time sequence data sequence needs to be segmented, and local information is extracted aiming at the segmented sequence.
For feature extraction, the time sequence data acquisition interval during waiting period is large, in order to guarantee capture of important information such as time sequence morphological change and key points, the time sequence representation based on statistical features, symbolization representation in two-dimensional space and other methods are adopted to process the features of the required data, and the change trend and morphological characteristics of the time sequence data are described. The time domain value includes the dimensional characteristics of maximum value, minimum value, peak value, mean square error and the like, and also can select the dimensionless characteristics of peak value factor, pulse factor, waveform factor and the like.
The above steps of data segmentation and feature extraction are conventional methods and will not be described in detail here.
The above description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood and to implement the technical means in accordance with the content of the description, the embodiments of the present invention are described in detail below.
Drawings
FIG. 1 is a flow chart illustrating a method for dynamically identifying atypical critically ill patients in accordance with the present invention;
fig. 2 is a schematic diagram of data segmentation of a sequence.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1 and 2, the dynamic identification method for an atypical critical patient of the present embodiment is described with the patient's heart rate sign r and blood pressure sign p (blood pressure) as the tested signs, and so on, and the identification method for multiple signs is not described in detail.
Setting a first dynamic sign data sequence set of a patient to be detected as a, a second dynamic sign data sequence set of a historical patient as b, wherein b is E { b ∈1,b2,...bNAnd the sequence sets a and b respectively contain sequences corresponding to two signs r and p, and the sequences are as follows:
a＝{{Sr(1),Sp(1)},...,{Sr(t),Sp(t)}}
b＝{{Tr(1),Tp(1)},...,{Tr(t),Tp(t)}}
wherein the sequence set a can be split into two first dynamic sign data sequences arAnd ap，ar＝{Sr1,...,Srt1}，ap＝{Sp1, a., Spt2, and similarly, the sequence set b and split into two second dynamic vital signs data sequences brAnd bp，br＝{Tr(1),...,Tr(f)}，bp＝{Tp(1),...,Tp(f) And after a segmentation method D based on data self-adaptation and feature extraction F (including statistical features, symbolic representation, dimensional and dimensionless features based on a sliding window and the like), forming a new dynamic sign data sequence:
new first dynamic vital signs data sequence:
new second dynamic vital signs data sequence:
calculating sequence a'rAnd b'rThe approximation distance of (2) is calculated as follows:
firstly, searching the curved path P with the minimum accumulated distance by a DTW algorithmbest＝p1,p2...pUP represents ar,brA match between the points. The optimal path planning problem is solved, and the model obtains the optimal path through continuous iterative optimization. The constraints are as follows:
(1) borderline of path: p is a radical of1＝(1,1),pU＝(n1,m1)
The recurrence relation is expressed as follows:
DTW(i,j)＝∞if i＝0,j≠0 or i≠0,j＝0
DTW(i,j)＝0 if i＝j＝0
DTW＝γ(ari,brj)+min{DTW(i-1,j),DTW(i-1,j-1),DTW(i,j-1)}
wherein gamma (a)ri,brj) Denotes ariAnd brjWhere i e [1, n1 ]],j∈[1,m1]：
γ(ari,brj)＝||ari-brj||w
w is usually 2, in which case γ (a)ri,brj) Namely the euclidean distance.
Finding out a matching point according to the DTW model to obtain ar,brThe distance between
dr＝DTW(ar,br)
D is obtained in the same manner as described aboveP。
Analyzing the contribution rate of the heart beat r and the blood pressure p to the attributes of the patient according to historical data, or calculating a correlation matrix to obtain attribute weights w corresponding to r and pr,wp
The proximity distance of the first and second sets of dynamic vital signs data sequences a and b can be expressed as,
setting k candidates according to a k-means algorithm, then obtaining
candidate＝k-means(a,B)＝{b1,b2,...,bk}
D (a, b) is calculated separately as described above1),....D(a,bk)；
Calculating the risk score of the first feature data sequence set a according to the following formula:
and then setting a threshold thred according to the actual situation if: score > t hred then proceed with early warning.
The above description is only a preferred embodiment of the present invention, which is used to assist those skilled in the art to implement the corresponding technical solutions, and is not used to limit the protection scope of the present invention, which is defined by the appended claims. It should be noted that, for those skilled in the art, on the basis of the technical solution of the present invention, several modifications and variations can be made equivalent thereto, and these modifications and variations should also be regarded as the protection scope of the present invention. Also, it should be understood that although the present description has been described in terms of the above embodiments, not every embodiment may include only a single embodiment, and such description is for clarity only, and those skilled in the art will recognize that the description is taken as a whole, and that the embodiments may be suitably combined to form other embodiments as will be appreciated by those skilled in the art.
Claims (4)
1. A dynamic identification method for atypical critical patients is characterized by comprising the following steps:
s1: acquiring a first dynamic sign data sequence set of a patient to be detected, wherein the first dynamic sign data sequence set comprises a plurality of first dynamic sign data sequences which correspond to at least two signs of the patient to be detected one by one;
s2: acquiring N second dynamic sign data sequence sets corresponding to N historical patients, wherein each second dynamic sign data sequence set comprises a plurality of second dynamic sign data sequences corresponding to the corresponding historical patients and the signs one to one;
s3: respectively calculating the proximity distance D between the first dynamic sign data sequence set in the step S1 and each second dynamic sign data sequence set in the N second dynamic sign data sequence sets in the step S2;
s4: acquiring first K second dynamic sign data sequence sets with the minimum approximation distance in the step S3, and forming a candidate set by the K second dynamic sign data sequence sets with the minimum approximation distance, wherein K is smaller than N;
s5: acquiring the risk score of the patient to be tested by the following formula:
wherein D isiThe approximation distance between the first dynamic sign data sequence set and the ith second dynamic sign data sequence set in the candidate set is obtained;
wherein, ciThe values of (A) are as follows:
c when the ith second dynamic sign data sequence set in the candidate set is a positive samplei＝1；
C when the ith second dynamic sign data sequence set in the candidate set is a negative samplei＝-1；
If the historical patient corresponding to the second dynamic sign data sequence set is a critical patient, the second dynamic sign data sequence set is a positive sample;
if the historical patient corresponding to the second dynamic sign data sequence set is not a critical patient, the second dynamic sign data sequence set is a negative sample;
s6: judging whether the patient to be detected is a critical patient or not according to the risk score acquired in the step S5 and the set threshold value:
if the risk score is larger than a set threshold value, the patient to be detected is a critical patient;
and if the risk score is less than or equal to the set threshold value, the patient to be detected is not a critical patient.
2. The method of claim 1 for dynamic identification of atypical critically ill patients, wherein: the approximation degree distance calculation method in step S3 is as follows:
s31: calculating the proximity distance d between each first dynamic sign data sequence in the first dynamic sign data sequence set and a second dynamic sign data sequence corresponding to the first dynamic sign data sequence in the second dynamic sign data sequence set;
s32: obtaining the approximate distance between the first dynamic sign data sequence set and the second dynamic sign data sequence set by the following formula:
wherein n is the number of physical sign types, diThe approximation distance between a first dynamic sign data sequence corresponding to the feature in the ith and a second dynamic sign data sequence set is obtained;
wherein wiAttribute weight of the approximation distance corresponding to the ith sign data;
3. the dynamic identification method of atypical critical patients as claimed in claim 2, wherein the two data sequences are dynamically time-warped by the DTW algorithm before the approximation distance d between the first dynamic vital sign data sequence and the corresponding second dynamic vital sign data sequence is calculated in step S31.
4. The method of claim 3, wherein the method comprises: the method also comprises the steps of carrying out data segmentation and feature extraction on the data sequence before carrying out dynamic time warping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111481837.9A CN114334145B (en) | 2021-12-06 | 2021-12-06 | Dynamic identification method for atypical critical patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111481837.9A CN114334145B (en) | 2021-12-06 | 2021-12-06 | Dynamic identification method for atypical critical patients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114334145A true CN114334145A (en) | 2022-04-12 |
| CN114334145B CN114334145B (en) | 2023-06-30 |
Family
ID=81049582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111481837.9A Active CN114334145B (en) | 2021-12-06 | 2021-12-06 | Dynamic identification method for atypical critical patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114334145B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
| CN107408144A (en) * | 2014-11-14 | 2017-11-28 | Zoll医疗公司 | Medical precursor event estimation |
| CN108962389A (en) * | 2018-06-21 | 2018-12-07 | 上海掌门科技有限公司 | Method and system for indicating risk |
| US20190311809A1 (en) * | 2016-11-24 | 2019-10-10 | Oxford University Innovation Limited | Patient status monitor and method of monitoring patient status |
| US20200194124A1 (en) * | 2018-12-14 | 2020-06-18 | Prescient Healthcare Consulting, LLC | Dynamic Rolling Severity of Illness Score for a Critically Ill Patient |
| CN112703562A (en) * | 2018-09-18 | 2021-04-23 | 皇家飞利浦有限公司 | General and individual patient risk prediction |
| CN112992350A (en) * | 2021-02-23 | 2021-06-18 | 联仁健康医疗大数据科技股份有限公司 | Physical sign data monitoring method and device, electronic terminal and storage medium |
| WO2021151351A1 (en) * | 2020-09-04 | 2021-08-05 | 平安科技（深圳）有限公司 | Data processing method and apparatus, computer device, and storage medium |
| CN113327680A (en) * | 2021-07-15 | 2021-08-31 | 厦门市易联众易惠科技有限公司 | Disease risk early warning method, device, equipment and storage medium |
-
2021
- 2021-12-06 CN CN202111481837.9A patent/CN114334145B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107408144A (en) * | 2014-11-14 | 2017-11-28 | Zoll医疗公司 | Medical precursor event estimation |
| CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
| US20190311809A1 (en) * | 2016-11-24 | 2019-10-10 | Oxford University Innovation Limited | Patient status monitor and method of monitoring patient status |
| CN108962389A (en) * | 2018-06-21 | 2018-12-07 | 上海掌门科技有限公司 | Method and system for indicating risk |
| CN112703562A (en) * | 2018-09-18 | 2021-04-23 | 皇家飞利浦有限公司 | General and individual patient risk prediction |
| US20200194124A1 (en) * | 2018-12-14 | 2020-06-18 | Prescient Healthcare Consulting, LLC | Dynamic Rolling Severity of Illness Score for a Critically Ill Patient |
| WO2021151351A1 (en) * | 2020-09-04 | 2021-08-05 | 平安科技（深圳）有限公司 | Data processing method and apparatus, computer device, and storage medium |
| CN112992350A (en) * | 2021-02-23 | 2021-06-18 | 联仁健康医疗大数据科技股份有限公司 | Physical sign data monitoring method and device, electronic terminal and storage medium |
| CN113327680A (en) * | 2021-07-15 | 2021-08-31 | 厦门市易联众易惠科技有限公司 | Disease risk early warning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114334145B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10929420B2 (en) | Structured report data from a medical text report | |
| Abdar et al. | UncertaintyFuseNet: robust uncertainty-aware hierarchical feature fusion model with ensemble Monte Carlo dropout for COVID-19 detection | |
| JP6941123B2 (en) | Cell annotation method and annotation system using adaptive additional learning | |
| JP5098559B2 (en) | Similar image search device and similar image search program | |
| CN101551855B (en) | Auxiliary diagnostic system for tracing self-adaptive kernel matching and auxiliary diagnostic method thereof | |
| US20220207730A1 (en) | Systems and Methods for Automated Image Analysis | |
| CN102521534B (en) | Intrusion detection method based on crude entropy property reduction | |
| US8977061B2 (en) | Merging face clusters | |
| Saxena et al. | A deep learning approach for the detection of COVID-19 from chest X-Ray images using convolutional neural networks | |
| Tian et al. | Radiomics and its clinical application: artificial intelligence and medical big data | |
| Karnes et al. | Adaptive Few-Shot Learning PoC Ultrasound COVID-19 Diagnostic System | |
| CN118312816A (en) | Cluster weighted clustering integrated medical data processing method and system based on member selection | |
| Ghafoor | COVID-19 pneumonia level detection using deep learning algorithm | |
| US20240054360A1 (en) | Similar patients identification method and system based on patient representation image | |
| Zhang et al. | A deep Bayesian neural network for cardiac arrhythmia classification with rejection from ECG recordings | |
| CN109859813B (en) | Entity modifier recognition method and device | |
| Fournier et al. | Acute hypotension episode prediction using information divergence for feature selection, and non-parametric methods for classification | |
| CN114334145B (en) | Dynamic identification method for atypical critical patients | |
| CN116596836A (en) | Pneumonia CT image attribute reduction method based on multi-view neighborhood evidence entropy | |
| AU2021102593A4 (en) | A Method for Detection of a Disease | |
| Sankaravadivel et al. | Feature based analysis of endometriosis using machine learning | |
| Fonseca et al. | Screening of viral pneumonia and covid-19 in chest x-ray using classical machine learning | |
| Yavuz et al. | Prediction of breast cancer using machine learning algorithms on different datasets | |
| Wang et al. | A COVID-19 Detection Model Based on Convolutional Neural Network and Residual Learning. | |
| Abdulsamad et al. | Cervical Cancer Screening Using Residual Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230714 Address after: 100005 Wangfujing, Beijing Dongcheng District Wangfujing Shuai Fu Garden No. 1 Patentee after: PEKING UNION MEDICAL COLLEGE Hospital Patentee after: TSINGHUA University Address before: 100005 Wangfujing, Beijing Dongcheng District Wangfujing Shuai Fu Garden No. 1 Patentee before: PEKING UNION MEDICAL COLLEGE Hospital |