• Title/Summary/Keyword: disease prediction

Search Result 552, Processing Time 0.018 seconds

A prediction study on the number of emergency patients with ASTHMA according to the concentration of air pollutants (대기오염물질 농도에 따른 천식 응급환자 수 예측 연구)

  • Han Joo Lee;Min Kyu Jee;Cheong Won Kim
    • Journal of Service Research and Studies
    • /
    • v.13 no.1
    • /
    • pp.63-75
    • /
    • 2023
  • Due to the development of industry, interest in air pollutants has increased. Air pollutants have affected various fields such as environmental pollution and global warming. Among them, environmental diseases are one of the fields affected by air pollutants. Air pollutants can affect the human body's skin or respiratory tract due to their small molecular size. As a result, various studies on air pollutants and environmental diseases have been conducted. Asthma, part of an environmental disease, can be life-threatening if symptoms worsen and cause asthma attacks, and in the case of adult asthma, it is difficult to cure once it occurs. Factors that worsen asthma include particulate matter and air pollution. Asthma is an increasing prevalence worldwide. In this paper, we study how air pollutants correlate with the number of emergency room admissions in asthma patients and predict the number of future asthma emergency patients using highly correlated air pollutants. Air pollutants used concentrations of five pollutants: sulfur dioxide(SO2), carbon monoxide(CO), ozone(O3), nitrogen dioxide(NO2), and fine dust(PM10), and environmental diseases used data on the number of hospitalizations of asthma patients in the emergency room. Data on the number of emergency patients of air pollutants and asthma were used for a total of 5 years from January 1, 2013 to December 31, 2017. The model made predictions using two models, Informer and LTSF-Linear, and performance indicators of MAE, MAPE, and RMSE were used to measure the performance of the model. The results were compared by making predictions for both cases including and not including the number of emergency patients. This paper presents air pollutants that improve the model's performance in predicting the number of asthma emergency patients using Informer and LTSF-Linear models.

Clinical Application of Serum CEA, SCC, Cyfra21-1, and TPA in Lung Cancer (폐암환자에서 혈청 CEA, SCC, Cyfra21-1, TPA-M 측정의 의의)

  • Lee, Jun-Ho;Kim, Kyung-Chan;Lee, Sang-Jun;Lee, Jong-Kook;Jo, Sung-Jae;Kwon, Kun-Young;Han, Sung-Beom;Jeon, Young-June
    • Tuberculosis and Respiratory Diseases
    • /
    • v.44 no.4
    • /
    • pp.785-795
    • /
    • 1997
  • Background : Tumor markers have been used in diagnosis, predicting the extent of disease, monitoring recurrence after therapy and prediction of prognosis. But the utility of markers in lung cancer has been limited by low sensitivity and specificity. TPA-M is recently developed marker using combined monoclonal antibody of Cytokeratin 8, 18, and 19. This study was conducted to evaluate the efficacy of new tumor marker, TPA-M by comparing the estabilished markers SCC, CEA, Cyfra21-1 in lung cancer. Method : An immunoradiometric assay of serum CEA, sec, Cyfra21-1, and TPA-M was performed in 49 pathologically confirmed lung cancer patients who visited Keimyung University Hospital from April 1996 to August 1996, and 29 benign lung diseases. Commercially available kits, Ab bead CEA (Eiken) to CEA, SCC RIA BEAD (DAINABOT) to SCC, CA2H (TFB) to Cyfra2H. and TPA-M (DAIICHI) to TPA-M were used for this study. Results : The mean serum values of lung cancer group and control group were $10.05{\pm}38.39{\mu}/L$, $1.59{\pm}0.94{\mu}/L$ in CEA, $3.04{\pm}5.79{\mu}/L$, $1.58{\pm}2.85{\mu}/L$ in SCC, $8.27{\pm}11.96{\mu}/L$, $1.77{\pm}2.72{\mu}/L$ in Cyfra21-1, and $132.02{\pm}209.35\;U/L$, $45.86{\pm}75.86\;U/L$ in TPA-M respectively. Serum values of Cyfra21-1 and TPA-M in lung cancer group were higher than control group (p<0.05). Using cutoff value recommended by the manufactures, that is $2.5{\mu}/L$ in CEA, $3.0{\mu}/L$ in Cyfra21-1, 70.0 U/L in TPA-M, and $2.0{\mu}/L$ in SCC, sensitivity and specificity of lung cancer were 33.3%, 78.6% in CEA, 50.0%, 89.7% in Cyfra21-1, 52.3%, 89.7% in TPA-M, 23.8%, 89.3% in SCC. Sensitivity and specificity of nonsmall cell lung cancer were 36.1%, 78.1% in CEA, 50.1%, 89.7% in Cyfra21-1, 53.1%, 89.7% in TPA-M, 33.8%, 89.3% in SCC. Sensitivity and specificity of small cell lung cancer were 25.0%, 78.5% in CEA, 50.0%, 89.6% in Cyfra21-1, 50.0%, 89.6% in TPA-M, 0%, 89.2% in SCC. Cutoff value according to ROC(Receiver operating characteristics) curve was $1.25{\mu}/L$ in CEA, $1.5{\mu}/L$ in Cyfra2-1, 35 U/L in TPA-M, $0.6{\mu}/L$ in SCC. With this cutoff value, sensitivity, specificity, accuracy and kappa index of Cyfra21-1 and TPA-M were better than CEA and SCC. SCC only was related with statistic significance to TNM stages, dividing to operable stages(TNM stage I to IIIA) and inoperable stages (IIIB and IV) (p<0.05). But no tumor markers showed any correlation with significance with tumor size(p>0.05). Conclusion : Serum TPA-M and Cyfra21-1 shows higher sensitivity and specificity than CEA and SCC in overall lung cancer and nonsmall cell lung cancer those were confirmed pathologically. SCC has higher specificity in nonsmall cell lung cancer. And the level of serum sec are signiticantly related with TNM staging.

  • PDF