{"cells":[{"metadata":{},"cell_type":"markdown","source":"#An interpretable mortality prediction model for COVID-19 patients\nYan, L., Zhang, H., Goncalves, J. et al. An interpretable mortality prediction model for COVID-19 patients. Nat Mach Intell 2, 283–288 (2020). https://doi.org/10.1038/s42256-020-0180-7\n\nThis study leverages a database of blood samples from 485 infected patients in the region of Wuhan, China, to identify crucial predictive biomarkers of disease mortality. For this purpose, `machine learning tools` selected three biomarkers that predict the mortality of individual patients more than 10 days in advance with more than 90% accuracy: `lactic dehydrogenase (LDH), lymphocyte and high-sensitivity C-reactive protein (hs-CRP)`. In particular, relatively high levels of LDH alone seem to play a crucial role in distinguishing the vast majority of cases that require immediate medical attention. This finding is consistent with current medical knowledge that high LDH levels are associated with tissue breakdown occurring in various diseases, including pulmonary disorders such as pneumonia. Overall, this Article suggests a simple and operable decision rule to quickly predict patients at the highest risk, allowing them to be prioritized and potentially reducing the mortality rate.https://www.nature.com/articles/s42256-020-0180-7","execution_count":null},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"#codes from Rodrigo Lima  @rodrigolima82\nfrom IPython.display import Image\nImage(url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn%3AANd9GcR80B1-ealrPRrFhoJNri_GfULKGbbSIZHBkltJIqLE4afweR2X&usqp=CAU',width=400,height=400)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"birminghamhealthpartners.co.uk","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.offline as py\nimport plotly.graph_objs as go\nimport plotly.offline as py\nimport plotly.express as px\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"There is no currently available prognostic biomarker to distinguish patients that require immediate medical attention and to estimate their associated mortality rate.  A `mathematical modelling` approach based on state-of-the-art interpretable `machine learning algorithms` was devised to identify the most discriminative `biomarkers of patient mortality`. The problem was formulated as a classification task, where the inputs included basic information, symptoms, blood samples and the results of laboratory tests, including liver function, kidney function, coagulation function, electrolytes and inflammatory factors, taken from originally general, severe and critical patients, as well as their associated outcomes corresponding to either survival or death at the end of the examination period. Through optimization, this classifier aims to reveal the most crucial biomarkers distinguishing patients at imminent risk, thereby relieving clinical burden and potentially reducing the mortality rate.https://www.nature.com/articles/s42256-020-0180-7","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/trec-covid-information-retrieval/CORD-19/CORD-19/metadata.csv')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#Codes from Salman Chen https://www.kaggle.com/salmanhiro/covids-incubation-transmission-related-articles/comments","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"title = df.copy()\ntitle = title.dropna(subset=['title'])\ntitle['title'] = title['title'].str.replace('[^a-zA-Z]', ' ', regex=True)\ntitle['title'] = title['title'].str.lower()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#Development of a machine learning model\n\nMost patients had multiple blood samples taken throughout their stay in hospital. However, the `model training and testing` uses only the data from the final sample as inputs to the model to assess the crucial biomarkers of disease severity, distinguish patients that require immediate medical assistance and accurately match corresponding features to each label. Nevertheless, the model can be applied to all other blood samples and the predictive potential of the identified biomarkers estimated. Missing data were ‘−1’ padded. The model output corresponds to patient mortality. Patients that survived were assigned to class 0 and those that died to class 1.\n\nThe performance models were evaluated by assessing the classification accuracy (ratio of true predictions over all predictions), the precision, sensitivity/recall and F1 scores.\n\nThis study uses a supervised XGBoost classifier8 as the predictor model. In contrast(to XGBoost), internal model mechanisms of black-box modelling strategies are typically difficult to interpret. The importance of each individual feature in XGBoost is determined by its accumulated use in each decision step in trees. This computes a metric characterizing the relative importance of each feature, which is particularly valuable to estimate features that are the most discriminative of model outcomes, especially when they are related to meaningful clinical parameters.\n\nXGBoost was originally trained with the following default parameter settings: maximum depth equal to 4, learning rate equal to 0.2, number of tree estimators set to 150, value of the regularization parameter α set to 1 and ‘subsample’ and ‘colsample_bytree’ both set to 0.9 to prevent overfitting for cases with many features and small sample size8. https://www.nature.com/articles/s42256-020-0180-7","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"title['keyword_biomarker'] = title['title'].str.find('biomarker')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"If the result prompt -1, then the title doesn't contained the keyword.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"title.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#Feature importance for an operable Decision Tree.\n\nTo evaluate the markers of imminent mortality risk, they assessed the contribution of each patient parameter to decisions of the algorithm. Features were ranked by Multi-tree XGBoost according to their importance. The performances of the model showed no improvement in area under the curve (AUC) scores when the number of top features increased to four. Hence, the number of key features was set to the following three: `lactic dehydrogenase (LDH), lymphocytes and high-sensitivity C-reactive protein (hs-CRP)`.\n\nThe results show that the model is able to accurately identify the outcome of patients, regardless of their original diagnosis upon hospital admission. Notably, the performance of the external test set is similar to that of the training and validation sets, which suggests that the model captures the key biomarkers of patient mortality. Demonstrating a clear separability.The importance of LDH as a crucial biomarker for patient mortality rate was emphasized. https://www.nature.com/articles/s42256-020-0180-7","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#codes from Rodrigo Lima  @rodrigolima82\nfrom IPython.display import Image\nImage(url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn%3AANd9GcRrwtPS-Yst8VfH_BazvJYgaRWfp_tctzl4pTCoMpPH6S-Dzj5s&usqp=CAU',width=400,height=400)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"nature.com","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"included_biomarker = title.loc[title['keyword_biomarker'] != -1]\nincluded_biomarker","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#codes from Rodrigo Lima  @rodrigolima82\nfrom IPython.display import Image\nImage(url = 'https://media.springernature.com/lw685/springer-static/image/art%3A10.1038%2Fs42256-020-0180-7/MediaObjects/42256_2020_180_Fig3_HTML.png?as=webp',width=400,height=400)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"nature.com - Figure above: An interpretable mortality prediction model for COVID-19 patients Yan, L., Zhang, H., Goncalves, J. et al. An interpretable mortality prediction model for COVID-19 patients. Nat Mach Intell 2, 283–288 (2020). https://doi.org/10.1038/s42256-020-0180-7\nhttps://www.nature.com/articles/s42256-020-0180-7","execution_count":null},{"metadata":{"trusted":true,"collapsed":true,"_kg_hide-output":true},"cell_type":"code","source":"import json\nfile_path = '/kaggle/input/trec-covid-information-retrieval/CORD-19/CORD-19/document_parses/pdf_json/b54932936d9dd6f8a399f23e19d0a1d0aeabd954.json'\nwith open(file_path) as json_file:\n     json_file = json.load(json_file)\njson_file","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"'Endothelial Biomarkers. Biomarkers can be used, and ideally should be used, for quantitative evaluation of the body\\'s response to external effects. Quantitative characteristics include the diagnostic sensitivity, specificity, predictive value, likelihood ratio, and so forth. An ideal biomarker is characterized by a high sensitivity, specificity, and predictive value; it is reproduced in humans of different sexes and ethnic groups, and the procedure for its determination is cost-effective. However, rarely does such a marker stand alone as a single parameter; rather, it is a derivative of several original indicators. At the same time, a complex of physiological and biochemical methods combined with an appropriate analytical platform should be relatively simple (low-invasive and noninvasive methods), universal (modular), and flexible (algorithmic). Ambiguous expression pattern and complexity of determining many biomarkers decrease their predictive value, leading to an overdue diagnosis and bad prognosis. Parallel measurement of multiple \"early\" biomarkers would certainly increase the diagnostic accuracy. Together with identification studies, validation studies of multimarker assays are urgently needed.' ('section': 'Endothelium and Toxicology of Organophosphates.'}","execution_count":null},{"metadata":{"trusted":true},"cell_type":"markdown","source":"'Section': 'CD47'},\n  {'text': 'CD54/ICAM-1 ICAM-1 (intercellular adhesion molecule-1) is a transmembrane protein that is upregulated on endothelial and epithelial cells at sites of inflammation. It mediates the vascular adhesion and paracellular migration of leukocytes with activated LFA-1 (CD11a/CD18) and Mac-1 (CD11b/CD18). Soluble ICAM-1 participates in angiogenesis being an indicator of EC activation or damage. Elevated levels of soluble ICAM-1 are linked to oxidative stress, `hypertension, cardiovascular disease, type 2 diabetes,` organ transplant dysfunction, increased abdominal fat mass, liver disease, certain malignancies, and sepsis.","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"import json\nfile_path = '/kaggle/input/trec-covid-information-retrieval/CORD-19/CORD-19/document_parses/pdf_json/0cea2b0d9b7187e2c5a596ed433be46208186d32.json'\nwith open(file_path) as json_file:\n     json_file = json.load(json_file)\njson_file","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":" 'Abstract': 'Text': 'Biomarkers enable early diagnosis, guide molecularly targeted therapy and monitor the activity and therapeutic responses across a variety of diseases. Despite intensified interest and research, however, the overall rate of development of novel biomarkers has been falling. Moreover, no solution is yet available that efficiently retrieves and processes biomarker information pertaining to infectious diseases. Infectious Disease Biomarker Database (IDBD) is one of the first efforts to build an easily accessible and comprehensive literature-derived database covering known infectious disease biomarkers. IDBD is a community annotation database, utilizing collaborative Web 2.0 features, providing a convenient user interface to input and revise data online. It allows users to link infectious diseases or pathogens to protein, gene or carbohydrate biomarkers through the use of search tools. It supports various types of data searches and application tools to analyze sequence and structure features of potential and validated biomarkers. Currently, IDBD integrates 611 biomarkers for 66 infectious diseases and 70 pathogens.' \n\nAuthors: In Seok Yang, Chunsun Ryu. Korea National Institute of Health.","execution_count":null},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"biomarker = pd.read_csv('../input/cusersmarildownloadstcellcsv/TCell.csv', sep=';')\nbiomarker","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The CD4+/CD8+ ratio is the ratio of T helper cells (with the surface marker CD4) to cytotoxic T cells (with the surface marker CD8). Both CD4+ and CD8+ T cells contain several subsets.\n\nBoth effector helper T cells (Th1 and Th2) and regulatory T cells (Treg) cells have a CD4 surface marker, such that although total CD4+ T cells decrease with age, the relative percent of CD4+ T cells increases. The increase in Treg with age results in suppressed immune response to infection, vaccination, and cancer, without suppressing the chronic inflammation associated with aging https://en.wikipedia.org/wiki/CD4%2B/CD8%2B_ratio","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"#Code from Firat Gonen https://www.kaggle.com/frtgnn/world-population-visuals","execution_count":null},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"fig = go.Figure();\nfig.add_trace(go.Scatter(x = biomarker['age_at_enrollment'].head(10),y = biomarker['study_id'],\n                    mode='lines+markers',\n                    name='study_id'));\nfig.add_trace(go.Scatter(x = biomarker['age_at_enrollment'].head(10),y = biomarker['sex'],\n                    mode='lines+markers',\n                    name='sex'));\nfig.add_trace(go.Scatter(x = biomarker['age_at_enrollment'].head(10),y = biomarker['dm'],\n                    mode='lines+markers',\n                    name='dm'));\nfig.add_trace(go.Scatter(x = biomarker['age_at_enrollment'].head(10),y = biomarker['htn'],\n                    mode='lines+markers',\n                    name='htn'));\nfig.add_trace(go.Scatter(x = biomarker['age_at_enrollment'].head(10),y = biomarker['anemia'],\n                    mode='lines+markers',\n                    name='anemia'));\n\nfig.update_traces(mode='lines+markers', marker_line_width=2, marker_size=10);\n\nfig.update_layout(autosize=False, width=1000,height=700, legend_orientation=\"h\");\n\nfig.show();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The researchers identified a CD4 and CD8 lymphocyte response in individuals not exposed to Sars-Cov-2, which indicates cross-reactions with other respiratory coronaviruses. And cellular responses in convalescent patients have a good correlation with neutralizing antibodies. This will be instrumental in the development of an effective vaccine.\n\nThe cross reaction with other coronaviruses is the possible explanation for the non-illness in most of the population. The most interesting thing is that it is perhaps more important than neutralizing antibodies. https://translate.google.com.br/translate?hl=en&sl=pt&u=https://oglobo.globo.com/sociedade/memoria-imunologica-peca-chave-na-protecao-contra-covid-19-indicam-estudos-24444812&prev=search","execution_count":null},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"!pip install chart_studio","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"pip install bubbly","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"from bubbly.bubbly import bubbleplot \nfrom plotly.offline import iplot\nimport chart_studio.plotly as py\n\nfigure = bubbleplot(dataset=biomarker, x_column='cd4', y_column='study_id', \n    bubble_column='age_at_enrollment',size_column='htn', color_column='age_at_enrollment', \n    x_title=\"CD4 Lymphocyte\", y_title=\"Study ID\", title='CD4 Lymphocyte Study ID',\n     scale_bubble=3, height=650)\n\niplot(figure, config={'scrollzoom': True})","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"ax = biomarker.plot(figsize=(15,8), title='CD4 Lymphocyte Study')\nax.set_xlabel('age_at_enrollment, sex, dm, htn')\nax.set_ylabel('study_id')","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"biomarker.iloc[0]","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"biomarker.plot.hist()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"biomarker.plot.scatter(x = 'study_id', y = 'cd4', c = 'htn', s = 190)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"#plt.style.use('dark_background')\nfrom pandas.plotting import scatter_matrix\nscatter_matrix(biomarker, figsize= (8,8), diagonal='kde', color = 'b')\nplt.xticks(rotation=45)\nplt.yticks(rotation=45)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"corr = biomarker.corr(method='pearson')\nsns.heatmap(corr)","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"biomarker_grp = biomarker.groupby([\"study_id\",\"age_at_enrollment\"])[[\"dm\",\"htn\",\"pcp\", \"chronic_heart_disease\", \"ART_use\", \"tb\", \"cd4\"]].sum().reset_index()\nbiomarker_grp.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"biomarker_grp.diff().hist(color = 'b', alpha = 0.1, figsize=(10,10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"#codes from Rodrigo Lima  @rodrigolima82\nfrom IPython.display import Image\nImage(url = 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAPQAAADPCAMAAAD1TAyiAAABCFBMVEX///8tKD1Sv5olHzceFzGcmqL7+/s7NkkzLkNraHXBwsNYwp5MvZeI0bhPwJpvopEpIzlcWWdST18hGzRVyaEnITj29vZjxaR/zrLX7uXn5+fI6dwsIjorGjeb2MGm3MgaEy+SkpK4uLhQtZStra3b29t9fX3Ly8uvr68rGDaZmZkrHjigoKDg4ODU1NSPjZV3d3c8aWMUCivq9vK4trx1cn0OAChMpopEiXc6YF0AAByJh5CIiIhIRFQAAAAAACBJnIRsbGxXU2IwN0UAABA/dGpdXV01SlAqDzNFingwM0Q2TlMoAC5MTEw0NDRBfG84V1gAABdEREQlJSWHrKCbtKwYGBgRACst8955AAAW9ElEQVR4nO2di3+bOpbHhXlrZrNgjGZXY88A5uHYgCkDdhpwHZzGSXNvmrSzu/f//0/2CDupm5DbV5q2tn/9lBghhL4cPc4BjJEq75x0pGvcjklr76F3Qz8FtHb5vFW4heZB5kdbTEjRDOOjNL65cqbJadZmwsZeJr8qHQq3HkHTzlvXoy+u+TdoDS0XeV6om9SmmhdFeyxuUpv5rKneZq4aOuY3Esby3Uc9hw1QlGpoQePeDPrg+qLX7fZGz2TwFbS2oATRzLImFtjMSqGek4hQOlbz1GBWNNIUKmShwhLS1GRmtTQzhXywMCfYPZ6JJp9alslZqaXN0UyADwLHpcdinGoyirEkpqIMuYWmShyeHk37/en1+eEzQnPapKATQctoZuoZjlQeoMev52lRjAuhjSdFxMxkSbnq4khvY8vIFrPAy1PV89Sc0GyWpXmUZboCRRgZigsti8RUC7wsYNDyqyyaY3mGI1HQtHsG1Xpcq9Pq9w86rROuu5E+GtW217of5e5yDYLELtOXQHNGQQ0ri2ZUzFGeEYGbeF4GKFlO3mXBTFLE2GLQY5RjOpH0GdJoMUM8KXRRDvBCRakkFkhV3ZSOF1IhZzglqktVWkNTD+UTNPMyXcqV2UzerEL3/M3F9OD84lB5Oe30T+/q3Ts/u35xeshppy+VjQqf3zRgXL487d4wXd5vK72G0WITeuKJ79wgp+/AMtrEi3DQzpwJaRN9jAKPcDV09C4n8ywTsYXiGKmiFKvzzJ2r0gwZ74Ao8yRxLs0mURQQMRDfrZp33sbxHMlEPY5FkRDxo0be75y+7Bz1OG40uu7070x30gEdvOF6R53zum3Ui8OTg8v1R+4usfuy82LUZ/lbJ5fdjQ1c92Q9Rm62rk3oNMheZTiXJipifVo8TtMsO3YjOs+JrOfmChpW0jYhuoDyWSG3UxFZWQbQHFoISI2zV1E4R/okzpRihvGrrIaevRbJBMm0eB2JkzTdHB0PTzrXvV6/Vdf14rrzpraVdtnvnNyc3px0ji5q6G7v9JQbsewtBT52a5RVYnc0qqH7L87OTqCtaKsNXdY7eq3pBZR8eHl62eveDpQfoInBq4hKeo4oyixuQsEcFjTSGRIFPqKSC6soH8MZQIIVwQggwkhnxZ4Xp7CLiuYZipjlI8mdY+SqEpVmUCCtoQlFxQS1xxIl8sc9Wjs9mI44MPFZjTGaHrBKc72TztlhV+v2Xl7Wlu79Nm21+mA1gL5hH89Yy6gTz476hzX09GI0OnzRgeJ6dZYXb6Zc/XfEvWm1Wicv+zfdj6Bh1oLptKvzVkGFdgrrirJamArMZOlCtuo8CtR53SMtMDOXtmFh8LKmcOHsFVInMwaVKorB6YLGy22BFQM+vmVoMicoi/uTNeBCpbjLVr+u0OhFp26Pl53pBWvvo8MRg+69hIZ7NO1Mu9C8O/03b/rQIsC+ByfX007rYA3N2sjFm85NnZttaHEnrdb0ZbffmV6fHBx0Xt6HrmVyfO6l92xRLz70qrvuUafdbtCMTCLeZsYPW7nVgK3drX/UulvMtD2oa12jy4OTXt1JwfLa2fX19RmDHrVa54e9wzeds4uTgynX62nTzm+H/dZvkHjd2YTu3nSuu/0699FBXztsTX8/PII+0jv8rfUINOO27tfrM2XJs6/YdTRt9Vg9Ts9WPe6iBc2TGRzsDxYCszLol53rQ3bWWv3fTzrnXdayO0fnnSOG2etvQmuQelPn5uCkcN3WtNft91njAfZHob9eD834+dCcplzXY/QKmtkLks/PT/s19PWqHUDm32EgY9lPoY/WHYON5xvQ7HS96LxkGy6mK2ildbvlO0B/laDK9cgFDZqN2zCusebNQXvuQp/RLqY19Mp2mvLB0jd3lh5tWrrLRsKb2yawgoZxncF+2tKa0ZDICelHq7xgrpda/QH+sdjirs9DIm+wNRa88Ks91gXdlTE6W9kL6s46N5ijHsYheXoJ/fJyZWk4B6eHvYt1n+72eqN1n77oXVwf3EL/fnhxCnNcT4E+DRugTzPodZ++OIc+fah0H4fWZmJDqiHGG76UphXiwtBMWAozCFaUnMtlOc9zeRV7CG3VhI0zntNUSM0Zc+HWuIp452OBafujNf0168b1uMYxlwRGYBiqry/q0ftgNXqPoGUc9I+O2OjdvTn4aPRuTafTg86bHseG9TdsQx9aTP/NORu9j04OAHrVTW6hIZAwBAggeBZFWMZER7AEy7IARBC02p8QVElVIPQwWW4g8GiGxmlMMSp0JAsFsRDM8h6VFnWJBaLvYhog3dQCCo6okgoTteChAB5cvvpATDAkH13U1K3+IQziR2tH8vAlELSmN4ejs349T8OYdqTBMD+9mXY6fdYeRnUim6dv+i+7ELL0+yc3dcO+YRtenEyh5bQ6Z73LN+Dcn7zo35z1f9PuoPlMjMZilFt5HKtpNo5VkrriRPQw38ZuJgfemDd1SmIh92I9xWKsgCvDz8fxAinv3GhCinmcTQCaHB/HWappRk4yqoArFoOnY/FoliqBiHNxMvbitiwpehzn62i03zlikQXY9uVlp3/ne49G4EaN6kiCY531svbIYG3UvTzVVh5ZnQjbNRgA6oCjt9r9bgM3UuoZUWFFgbPDbTRvgwZj5IrEwouCHNNIVKHKXE7+wNkCZTnGiqtoMsQPbXC6yB/EEzkjRxPOmIB/Bi7sJAsEpDNLEyvNYqHdnmnKmIKrqjDPTlNQm1cQHovxJJBFj5M4CpHKatzQLiHOOAOv8eZgenF9+gzD6hpaoLmAwABaHkfomOZzHSFl4pKARgvJSnPJKwRwVVm0caywwCEFLwbNgSZHllBQyAE+u8GgwWGPVYQ8SwCXdYwQMbkVNLTpuRgcj2PKoFmksra0xh1BQwZ1wK1+jqnkA3QXLWSio67KoC2dBN5EjAxd1SVTW0Bbzk2w6Bx87BlSCLRMU4e2m9EZar/GnmURkqUraJ5mk/k85QAahgSkGnfQszQMcvJajDhJXlgitJS1Di/PTqbTkzNF+byA+GmgDVJoaDEDG0YRmpNc0JERYYVGEoxRGsQWAQQKAJ2aHiXZMWLdUcgQkWAAYEse/qg8zwYyIkWrmAL2Ss0oY7MchBxtE6AtN55JHo0UpASR521MgKMe6OKo9dszWppbe9Qmr1u3/rKgmJau1P3OklUWKLANqT67rWsq6xYPS9Vi87N2d4Vt03dX7l8e4jndYgVZi0V6bxMEH63z54W+TeCa1j4QceZGAG/e2/ZZWmdvclq73HMw/3g39EdoD70rAuiFwe+YjDYq1J1Tgfbaa69tlBRBoB9JCEUQGMG/nRBx3hPfIWjo2oPSc350dZ5JoU2qkCAf+Y7t74qlieNSL0QJ/LNL+0dX53lES5uWJXWC0vEiJ0RY+tE1+gHaQ++K9tC7oj30nZz3/5aq9x58GNAlsbdtOn/E0uWQ+lGC6KsQV37wzHX67mqGJsEVLmmFSmxjXCXxc9fqO6sZOqyu6HIZVMHyipbecttM/UjzJhKSWBDG/m5fLLYfvbdVkWuTYYhQbAfxQMJN0FKjfkBdn04OHkQDD1UoCe0haYL+218eqvUfP6CqTyfHtwmO2UUEYvuNoeVf/nrwQH/9paEdXDqhT4MS+9S1y0bo1kP92tAoJsijiKKATUl0R6DvaQ+90h56D70t2kOvtIfeQ2+L9tAr7aG3AzqOUQCkkkOIh3bE947cIbYpQknkh6UT7AY0QlVUlvVN+dhO4t2AlpZeFDkBYTflh/ZwN6AjO6ShSzC1vYgEzm5A39ceeqU99B56W7SHXmkP/etDk4c3Xbce2gnLB2lbDx0PHj71u+3Q4H7iB4nbDo3iqoQ42kMQUSLiUhogb/uhsWsjJ/YdPIxQQv3QHmx/aEljdwBhVhmu7097tr/9FxEkTAmKrqgTDD2akEQa2vbWQyPshwisLQ2wFJCQUuJtv6WDqCFx66Ftdwfn6aYn/7YdWqIN2NsOTXC4e80bOQ3fw9p6aM8JH6RtPXQcDR6kbT00ON0P0rYdmsbl7oWWEh3sHjQaeHT1gYGup+yth8YJjN70iiYhQeEwHPh0sPXQUcB8by+Mq4GEEuQ7pS9tPTS1Sxf+uDGN3fpL40N/++NpaUDYQIbj0vawM3S92N3+m/LYQxtu6Bp226FJOdzBgKNJ2w6N7cB7mLjl0JIT0AeJ2w6N8GD3Ag6Ewx2EbtK2QxMS7GCUNfR373JRZA93z9IESyyIJqur/tHq+//bDr2S8zYe+hSVTun68a48EEvs2/vTuPR3xdKodOnAW8XT5fbH02s5K1uX2KPYfQpox3UQdV3q0Oihm/tT6gmgqbMEv/499YcPH1P7OfUUzbsMwNzL2Lnyf5H3/TwBtPQWuQPbdwbY/0Ve1PgE0CRCMcHsobSG0PWn1POO3l4C/99e0WVc/sgXIj0rtPR2SZEdh8Oqenj/9Bn1rNBxGfvIDobYq5If+Ubeb4P+5z8a9M9HD0bYO86iqyupJNXD2Of59G3Qf/trg/7rc477Q18A9Y3QTVk/C/qHag+90neBlv7ZpL8/Wi+SLB1YJLSMnabHO79YpU1Q4ONgKH1rPP0F0E29/8/mBO8tVLL0B2X18BLuPdUPBVL2FqrH3xVHfA+hCvnu0P7WePoLoBtytv76j0dBJA/CF5wkgbf0PzWnh29D5L1fDioneRw6cBzko0Syk+aXsP0M0PT9cljhJbhuXvIpjz56FYONr4Jk+fDC512eMsSB7ZTUGX7rRYTvB70xqX1qdpMG9C0lbwfg+/zJq+mh+RPkPcVL2L4n9OcrTGIX+2U8ABf3s3bYBugv1k8ILf29Sf/6Fsp7+gmh/9U4uz3u0X+5fkropqyN0NJ/N+mTjeLXhm5uFJ8cKX5x6MZSP9kT9tB76D30HvpXhKZ+KSHsO9gmzxhP/2DokDoxe947ZDFJw0XJvzx8vfdj7/f+W0PWg+bLRU05H4NuytoM3VhqIzS7Kc/uT4cQqQb4gf6zSf/TkPGxrE05v7nU//38UiHrg+dBvdKngzC0PYfdW21+Q/8vrwemrlO27sc19trr05LKj66u+fUyfuTS870HLv70ppybfOhREg4evfLl3m3BtzuQR37cR/LdjTVSfroSj4hWQeiXcVgNlsOKRFdRYtuhbftNV59JGeHKr5wl/LOTwRCmA9e1/WaeikbId0sbV0PYY+jjYNl4E8+XArxcVrZfhUvHH7qJj4dLtyr9h1mjKhj6Q+zC8cMK4StahW54NUgevyj6iAiu3ieDZQjHSqooXJZDzy9x/D5pyut7Pn1FS6fyquGVPRxWyLbdR+63VzQu36OlH1ZvKYXKsZo2QhN0VTrDBHCjK7esyLCiAz8pG57iIXh5VWEwjh8vK5IsS4yHdkmvmur659C2i0M0JGUQxzZyiRs6bknDhi/ZI/ZzqLR0aVAGkTsMccR2HDp2s6UHcDJc5A4c2yml4YC6Uvnw2xWI/ToKTeIADxI7gJnVCex4iGwMxTbUtXSckAxoGXjBUIK62kE4jJ3wR94G/mrVtzTuznL8rE+yfMlUTh58eLKin6XA0HeJRAhlL7KiUkKoVN8daDpSNYgR5AwpsglBuEI0csjjz9CQiL2Bww0IcbynMV/pOxRRqKtNoGQ4PhxA+poTEA6TJKkGiW/7jl1WbplUttt460D6v6SMqrL02bhnI9unlT3wq0cPWvqlXyWhs6wGV0ljh/5SlcNyaS/x0vdLpyyXA99PfPdrSh6Gw6XtLks78aOlbw+cK5e+bcxJyit7sLSd5RVkd9Dbq4HthuXjP/BcukmQVDh477tL/CSjjR+GV2CksqzsaFmW7mDpxFdfU5AnxUEUxEkQxRKOacwedG2+MSZ5EXW8IIgwjeMYGm+EvSh4/MfWSvbmN1ZoHAX0Sdp3LHmYYq+KY09yoFiH0uiLZ+kNbTYS8jQ98EkeKfhUwY1vK/oM3U4Sv8JTj/Ga8VvrGlUhtFKHDErsOcRhTfab6/a9FPhhFGG8qisd4Kjh+6SfJcke2r4dLgelb7sw4JbV8qeNvkkZ2n5pgzNql2EZJuXV8usKivwKg1cJPn4IHv/ABaf+p/2xw7hMXHc4gOHbCZNhAO7/145jFDkRkSQKDge4JYR81XT/TKIorOvJ/oNLRRpe/fu5+mkt26AnqCuxPxoJbr+L4n3yaa5nFv64Gd+GJ2EAzlVMHfRFrdyO3RDiRN8ph0HpRnZYutjxJWf4c43gxA+CBFcDP6gCCDAdO7RjGMGJs0SVUyUJe/bu81WSeBguPQze3aCyk0ESlXASCK2+W/2/SqSUbLx0wK3Ffuj7wwTi6NIGA2P0/r2TXA2/6IHyGGYquyRV6Lp2FfuxTe3KWRL/6ru5U1+nsgqW0AYrJygTG2M7JBD52OTfJfulcA/Owc/WH/faa6+99tprr70QEndQSLGEHZOloJnG7ZrkXYSefR30J/d5kEHjzHWaqT2Wj/+mQ362tBlqr0vTJgqffnqHiWKmGievdlKUuw0KZ07SycRcr8ofdkk1ZQJ78Pnq9Jp5+0P9NZkVCWJH1nL5XqlsC/+wxG/UB2hNjiSEDc4UoN4GnHVN402T4w1YNQ1+faY1mUJozeXI4gxBE8RoDlk5w9CsSGwjSaK6yTbwuiRoLJntEyMUKbmURrlg8gaXxgWv1QUaBicg3dDZHEKONcOEveF4hhilmsDKtaBEkhtQCU2TkbGuzRNCCy75ox3pqSqqllxwZiEvVFWd5OLCECBNUGo7pTjiZTpWiWUV4iwV41zUNG4syqkH0DMZ01SDNVmUxjMBcpicIBK5S7FKhFzWVchu5DNrIeYCPxMLy0K6qcwK1J7ls0IuFCEX9XTszWWxEBh0rohIg4L0VETjhQVbjaeE5nOU6WlaSJk0XiCOR6qIiOiSDOU5KUheINYCJ1Sc6G1ZJfOAZmgmIky94yjL6IRBdwUVpXGWETlAuJ0FoiRrKQ5SczbLyURSXYSJ95qOdZSRTCZjD88BmoO9hAmRKNRF9MaoPY4tIgaZANCqIK8TMcIq+6B/e98G6MW6lDQPEJE98ZXotZFmADSd/0HyY7UdxEUcK6pZQ4dzD2GddJH+OhLH9HUbyXKRIY5Bc7yKLLamLEhqKIWIVJNBc9YEoInqeq9VNKFFFr+e5SnA0WMGDXvxKRnPU7TgcxEV49ggOE+ZpVVDRjpLzBVkGVouSsW3m/oDtJmrrydE9MTXDFpIATqa8CSft5XYc92xVR8s9bLjV3GmEg7p7zxxHL2GAoiYI41BW/MCyWxN1klqUlcHaCvz5nMR9mDQ8URFfzDod3I7J7m7CZ0bFprF0A8KaN6KSL3a0sc6kmM4ybmMhDlspeMngG7fQhsicjOki9CUQw5hjNSQpmlGxygfk8IrcmKxXAXKMFqoaO7F0NRgHy9qozFGXCQuUICRO2NrsoziHIkZQJvQljNU1M07W0GPVTSmGEqlG9BgQoAmGbO0J0dFRhl0jEk8rxN54uXsw9NA33YSQc0yXRCKrDB4PcvHM73gOWOcqYaRZwW/EPl1LrctzMaGAtYT9FzMZCvP1DFX6DI4tarB57Cvwutiuy5E4/gFlGvNxsJ4phbGTDQKHfYYazwUXVgim7NmosmP2xovyrOsKNp6YcFRYFbkocScN9ss0WiL6iwbF4sn6NMfoDneqmcr1o5Ni80SjNKweLbFgAlmlcu0YDJiK4JlciYvwBoPuTmezVWsgHoNZj6tLoQdg+WEPQzN5NlfXqsLhOyQsS5Vg5GaZRU4zTLqA9dHgQRBYHMbS4RMJkxkxhP4KJvQOyOAVvfQuyCAzp/Cs/ulxKDBwd8xLf4fa3jCSK+5c2oAAAAASUVORK5CYII=',width=400,height=400)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"globaldata.com - According to GlobalData’s Biomarkers database, the top two biomarkers being utilized for COVID-19 trials are diagnostic markers – the first being Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), which is currently being used in approximately 30% of COVID-19 trials; and the second being Coronavirus Nucleic Acid, which is being included in just over 5% of trials. \n\nOther biomarkers used in COVID-19 trials included C-reactive protein, lymphocytes, and SARS-CoV-2 RNA. https://www.globaldata.com/biomarkers-heavily-used-as-diagnostic-tools-in-covid-19-trials/","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"Kaggle Notebook Runner: Marília Prata  @mpwolke","execution_count":null}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}