Objectives: In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is... Show moreObjectives: In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is clinically relevant for surgeon and patient to anticipate unplanned secondary procedures, other than operations that can be readily expected such as reconstructive procedures for soft tissue defects. Therefore, the objective of this study was to develop a machine learning (ML) prediction model using the SPRINT data that can give individual patients and their care team an estimate of their particular probability of an unplanned second surgery. Methods: Patients from the SPRINT trial with unilateral TSFs were randomly divided into a training set (80%) and test set (20%). Five ML algorithms were trained in recognizing patterns associated with subsequent surgery in the training set based on a subset of variables identified by random forest algorithms. Performance of each ML algorithm was evaluated and compared based on (1) area under the ROC curve, (2) calibration slope and intercept, and (3) the Brier score. Results: Total data set comprised 1198 patients, of whom 214 patients (18%) underwent subsequent surgery. Seven variables were used to train ML algorithms: (1) Gustilo-Anderson classification, (2) Tscherne classification, (3) fracture location, (4) fracture gap, (5) polytrauma, (6) injury mechanism, and (7) OTA/AO classification. The best-performing ML algorithm had an area under the ROC curve, calibration slope, calibration intercept, and the Brier score of 0.766, 0.954, -0.002, and 0.120 in the training set and 0.773, 0.922, 0, and 0.119 in the test set, respectively. Conclusions: An ML algorithm was developed to predict the probability of subsequent surgery after IMN for TSFs. This ML algorithm may assist surgeons to inform patients about the probability of subsequent surgery and might help to identify patients who need a different perioperative plan or a more intensive approach. Show less
Zavala, J.A.; Casey, C.M.; Manning, S.M.; Aravena, M.; Bethermin, M.; Caputi, K.I.; ... ; Yun, M.S. 2021
We present the first results of a survey of the [C II]157.7 {$μ$}m emission line in 241 luminous infrared galaxies (LIRGs) comprising the Great Observatories All-sky LIRG Survey (GOALS) sample,... Show moreWe present the first results of a survey of the [C II]157.7 {$μ$}m emission line in 241 luminous infrared galaxies (LIRGs) comprising the Great Observatories All-sky LIRG Survey (GOALS) sample, obtained with the PACS instrument on board the Herschel Space Observatory. The [C II] luminosities, L $_{[C II]}$, of the LIRGs in GOALS range from ~{}10$^{7}$ to 2 { imes} 10$^{9}$ L $_{⊙}$. We find that LIRGs show a tight correlation of [C II]/FIR with far-IR (FIR) flux density ratios, with a strong negative trend spanning from ~{}10$^{-2}$ to 10$^{-4}$, as the average temperature of dust increases. We find correlations between the [C II]/FIR ratio and the strength of the 9.7 {$μ$}m silicate absorption feature as well as with the luminosity surface density of the mid-IR emitting region ({$Sigma$}$_{MIR}$), suggesting that warmer, more compact starbursts have substantially smaller [C II]/FIR ratios. Pure star-forming LIRGs have a mean [C II]/FIR ~{} 4 { imes} 10$^{-3}$, while galaxies with low polycyclic aromatic hydrocarbon (PAH) equivalent widths (EWs), indicative of the presence of active galactic nuclei (AGNs), span the full range in [C II]/FIR. However, we show that even when only pure star-forming galaxies are considered, the [C II]/FIR ratio still drops by an order of magnitude, from 10$^{-2}$ to 10$^{-3}$, with {$Sigma$}$_{MIR}$ and {$Sigma$}$_{IR}$, implying that the [C II]157.7 {$μ$}m luminosity is not a good indicator of the star formation rate (SFR) for most local LIRGs, for it does not scale linearly with the warm dust emission most likely associated to the youngest stars. Moreover, even in LIRGs in which we detect an AGN in the mid-IR, the majority (2/3) of galaxies show [C II]/FIR {gt}= 10$^{-3}$ typical of high 6.2 {$μ$}m PAH EW sources, suggesting that most AGNs do not contribute significantly to the FIR emission. We provide an empirical relation between the [C II]/FIR and the specific SFR for star-forming LIRGs. Finally, we present predictions for the starburst size based on the observed [C II] and FIR luminosities which should be useful for comparing with results from future surveys of high-redshift galaxies with ALMA and CCAT. Show less