Table 4 Independent variables or features used in machine learning algorithms as input variables
Author | Main objectives | Features | Outcome variable | Data source |
|---|---|---|---|---|
Troiani.J et al. [29] | Predict the acute disease events after transplantation | Spirometry variables; values of FEV1 and bronchopulmonary symptoms for these 30 subjects | BOS incidence | A database of home monitoring data |
Oztekin.A et al. [30] | Predict survival rate | Events occurring before listing, Recipient angina/cad at registration, Deceased donor-infection pulmonary source, Recipient functional status at registration, Deceased donor-circumstance of death, Recipient age (years), History of cigarette use of the recipient | Survival rate | UNOS |
Delen.D et al. [31] | Predict the risk factors for transplantation | socio-demographic, health-related factors about both the donor and the recipients, procedure-related factors, patient follow-up data | Risk factors and patient status after LTx | UNOS |
Oztekin.A et al. [32] | Predict survival rate | Recipient’s profile, Match level data, Donor’s profile | Survival rate or transplant success | UNOS |
Hosseini-Baharanchi. F et al. [19] | Predict the acute disease events after transplantation | Age at LTX (yr); Type of transplant; Acute rejection episodes; Underlying lung disease; Cytomegalovirus, Death cause | BOS incidence | Post-LTX at the Masih Daneshvari Hospital, |
Barbosa.E et al. [33] | Predict the acute disease events after transplantation | PFT data (FEV1, FVC, FEV1/FVC, FEF25-75), baseline CT | BOS incidence | Radiology RIS/PACS data for the period between 06/01/2004 and 06/01/2013 |
Pande.A et al. [20] | Predict pulmonary functions/ pulmonary symptoms after transplantation | PFT data (FEV1, FVC, FEV1/FVC, FEF25-75) and Age | LTx outcomes | Cleveland Clinic |
Barbosa.E et al. [21] | Predict the acute disease events after transplantation | CT features and patient age | BOS incidence | Cardiothoracic clinic |
Oztekin.A et al. [22] | Predict quality of life | Donor factors, Recipient factors, Surgical factors, laboratory parameters, hospital stay, intensive care unit (ICU) stay and pulmonary function, | quality of life | UNOS |
Mark.E et al. [13] | Predict survival rate | Recipient age, Recipient primary diagnosis, Recipient functional status at transplant, Recipient lung diagnosis grouping, Donor height (cm), Deceased donor history of cigarettes in past | Survival rate | UNOS |
Braccioni.F et al. [23] | Predict pulmonary functions/ pulmonary symptoms after transplantation | pulmonary function testing (PFTs), blood gas analysis (ABGs), six-minute walking test (6MWT), and physical examination, DLCO, KCO | Transplantation outcome | tertiary teaching Hospital located in Northeast Italy |
Dueñas-Jurado.J et al. [24] | Predict recipient-donor matching | lower pre-transplant carbon dioxide (PCO2) pressure, higher pre-transplant and post-transplant functional vital capacity (FVC), lower donor mechanical ventilation, and shorter ischemia time | Survival rate | Reina Sofı´a university Hospital |
Shaish.H et al. [25] | Predict survival rate | HRCT scans | Survival rate | Institutional databases |
Stefanuto.P et al. [26] | Predict primary graft dysfunction after lung transplantation | Donor factors, Recipient factors, Surgical factors, Outcomes (1-year Mortality, Ventilation, ICU LOS after Tx, Hospital LOS after TX), Lung function at 3 months | primary graft dysfunction | Harefield Hospital |
Su.J et al. [27] | Determine the role of infection in rejection | laboratory parameters, hospital stay, intensive care unit (ICU) stay and pulmonary function, | Rejection with infection | Guangzhou Medical University |
Zafar.F et al. [28] | Predict recipient-donor matching | Recipient: Age, Sex, Ethnicity, BMI, Diagnosis, Initial LAS, End LAS, Functional status, eGFR, Albumin, Tobacco use, Infection, Steroid use, ECMO pretransplant, HIV, Recent infection, Ventilation pretransplant, CMV; Donor: Age, Sex, ethnicity, BMI, Tabacco use, Hypertension, Diabetes, Bronchoscopy result, Chest X-Ray result, Pao2/FiO2 ratio, PEEP, Adjusted tidal volume, Arterial blood pH, cause of death, Mechanism of death, CMV, Transplantation characteristics | Matching | UNOS |