Study on Integrated Visualization of Traditional Chinese Medicine Diagnosis and Treatment Decision-Making Information

Author(s):  
Qingyu Xie ◽  
Qinggang Meng
2021 ◽  
Author(s):  
Hong Zhang

BACKGROUND Clinical diagnosis and treatment decision making support is at the core of medical artificial intelligent research, in which Traditional Chinese Medicine (TCM) decision making is an important part. Traditional Chinese Medicine is a traditional medical system originated from China, of which the main clinical model is to conduct individualized diagnosis and treatment by relying on the four-diagnosis information. One of the key tasks of the TCM artificial intelligence research is to develop techniques and methods of clinical prescription decision making which takes all the relevant information of a patient as input, and produces a diagnosis and treatment scheme as output. Given the complexity of TCM clinical diagnosis and treatment schemes, decision making support of clinical diagnosis and treatment schemes remains as a research challenge for lacking of an effective solution. Fortunately, as the volume of the massive clinical data in the form of electronic medical records increases rapidly, it becomes possible for the computer to produce personalized diagnosis and treatment scheme recommendation through machine learning on the basis of the clinical big data. OBJECTIVE The objective of this research is to develop a real-time diagnosis and treatment scheme recommendation model for TCM inpatients. This is accomplished by using historical clinical medical records as training data to train a Transformer network. Furthermore, to alleviate the issue of overfitting, a Generative Adversarial Network is used to generate noise-added samples from the original training data. These noise-added samples along with the original samples form the complete train data set. METHODS valid information, such as the patient’s current sickness situation, medicines taken, nursing care given, vital signs, examinations and test results, is extracted from the patient’s electronic medical records, then the obtained information is sorted chronically, to produce a sequence of data of each patient. These time-sequence data is then used as input to the Transformer network. The output of the network would be the prescription information a physician would give. Overfitting is a common problem in machine learning, and becomes especially server when the network is complex with insufficient training data. In this research, a Generative Adversarial Network, is used to double the number of training samples by producing noise-added samples from the original samples. This, to a great extent, lessens the overfitting problem. RESULTS A total of 21,295 copies of inpatient electronic medical records from Guang’anmen traditional Chinese medicine hospital was used in this research. These records were created between January 2017 and December 2018, covering a total of 6352 kinds of medicines. These medicines were sorted into 829 types of first category medicines based on the class relationships among medicines. As shown by the test results, the performance of a fully trained Transformer model can have an average precision rate of 80.58%,and an average recall rate of 68.49%. CONCLUSIONS As shown by the preliminary test results, the Transformer-based TCM prescription recommendation model outperforms the existing conventional methods. The extra training samples generated by the GAN network helps to overcome the overfitting issue, leading a further improved recall rate and precision rate.


2016 ◽  
Vol 34 (7_suppl) ◽  
pp. 186-186 ◽  
Author(s):  
Nina A. Bickell ◽  
Sarah Abramson ◽  
Daniel Walker ◽  
Lindsey Sova ◽  
Jenny J Lin ◽  
...  

186 Background: Prostate cancer is the most common cancer for men in the US, yet the burden of this disease falls disproportionately on African Americans (AAs). The disparity’s etiology is complex. Surgery and radiotherapy offer similar survival but historically have different rates of performance with younger and white men more likely to undergo surgery and AAs more likely to experience underuse. This study aims to examine treatment decision-making (TDM) processes for AA men from patient and physician perspectives. Methods: At 1 academic and 1 municipal urban hospital, pathology records and a tumor registry from 2007-2012 were used to identify 359 AA and 282 white men with locally advanced prostate cancer, a Gleason score of 7-10, and receipt of definitive treatment. 15/17 treating physicians of participating patients were interviewed. Underuse overall was 4%, AA had higher rate of underuse compared to whites (6% vs. 1% respectively, p = 0.0002). 14 patients with longer times between diagnosis and treatment were recruited for 4 focus groups & 2 interviews lasting 60-90 minutes eliciting perspectives on themes related to TDM. Transcripts were coded and analyzed using a grounded theory approach. Results: Preliminary analysis of patient interviews suggests that patients primarily base their treatment decisions on physician recommendations. Patients were often unaware of treatment side effects. However, some patients felt this deficit helped them decide to receive treatment, whereas if they had known about possible impotence and incontinence, they would have refused treatment. Physicians recognized that patient concerns about side effects were a critical TDM factor. Physicians attributed prolonged delays between diagnosis and treatment to waiting times for tests of possible tumor spread and medical comorbidities. Conclusions: Understanding decision making and care processes for AA men with local advanced prostate cancer is critical to reducing the treatment and outcome disparities in this population. This study identifies several patient and physician/system factors that contribute to this process. These data can help inform interventions to improve prostate cancer care for AA men.


2021 ◽  
Vol 79 ◽  
pp. S661
Author(s):  
J. Chavarriaga Soto ◽  
P. Juan ◽  
O. Peter ◽  
L. Hugo ◽  
M. Maryori ◽  
...  

Blood ◽  
2015 ◽  
Vol 126 (23) ◽  
pp. 2119-2119 ◽  
Author(s):  
Thomas W. LeBlanc ◽  
Laura J Fish ◽  
Catherine T Bloom ◽  
Areej El-Jawahri ◽  
Debra M Davis ◽  
...  

Abstract Background: Many patients with AML lack prognostic understanding, which may limit their ability to participate in shared decision-making about treatments. The underlying drivers of this misunderstanding are not well understood, so we sought to characterize the experience of being diagnosed with AML, receiving information, and making a treatment decision. We expected to discover areas for improvement in clinical practice. Methods: We developed a semi-structured qualitative interview guide to explore patients' experiences at diagnosis, satisfaction with clinical communication, factors related to prognostic understanding, and the treatment decision-making process. We enrolled 33 hospitalized patients with AML within 7 days of starting a new treatment regimen, and interviewed only those with high-risk AML due to either age >59, relapsed/refractory disease, or complex cytogenetics. We audio recorded interviews and transcribed them for qualitative analysis. Using cycles of open and axial coding, we developed a codebook that was sequentially applied to all transcripts. Further refinement of codes and development of themes occurred via group discussion. Results: Four themes emerged from this analysis, relating to: (1) uncertainty, (2) suddenness, (3) difficulty processing information, and (4) need for better communication. Patients frequently described uncertainty related to their prognosis, the number and nature of available treatments, and even the definition of the term "prognosis." In some cases this uncertainty was a source of hope, leaving open the possibility of a positive outcome. In other cases this uncertainty was crippling and frustrating. In terms of suddenness of the AML diagnosis, many patients described it as "overwhelming," "devastating," and "blindsiding," making them unable to process information and make a treatment decision. Many had not anticipated this severe change in health status. Compounding the suddenness for several patients was the need to travel far from home to be treated at a tertiary center. Many patients found processing the complex information about their diagnosis and treatment options too difficult, which negatively impacted their understanding of available treatments. It was common for patients to dichotomize options into either "do or die," when there were actually several available options of varying intensity and risk. Thus, patients perceived a lack of treatment choices and frequently exhibited negative coping behaviors, such as cognitive distancing and denial. In terms of communication, most described their physicians as providing adequate information, yet sometimes described a mismatch between their needs and the type of information physicians provided. In the cases of mismatch, patients were less satisfied. Receiving bad news from a doctor they did not know stood out as a difficult and negative experience for many patients, and several described poor communication around the time of diagnosis. Conclusions: Patients with AML face a unique, difficult situation characterized by sudden changes in health and pressure to make quick treatment decisions. This results in difficulty processing information, and is sometimes complicated by a mismatch between patients' informational preferences and clinicians' communication styles. This scenario appears to compound the difficulty of processing complex information, and probably impairs patients' abilities to make a truly informed decision. The recommended model of shared decision-making may be of limited utility in the AML setting. Targeted interventions are needed to improve AML patients' understanding of their illness and treatment options, and their experiences with diagnosis and treatment decision-making. Disclosures LeBlanc: Helsinn Therapeutics: Honoraria, Research Funding; Epi-Q: Consultancy; Boehringer Ingelheim: Membership on an entity's Board of Directors or advisory committees; Flatiron: Consultancy.


Andrologia ◽  
2021 ◽  
Author(s):  
Julian Chavarriaga ◽  
Juan Prada ◽  
Peter Olejua ◽  
Hugo López‐Ramos ◽  
Maryori Manjarrez ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document