ABSTRACT
Introduction: Visual assessment and imaging of the donor liver are inaccurate in predicting fibrosis and remain surrogates for histopathology. We demonstrate that 3-s scans using a handheld near-infrared-spectroscopy (NIRS) instrument can identify and quantify fibrosis in fresh human liver samples. Methods: We undertook NIRS scans on 107 samples from 27 patients, 88 from 23 patients with liver disease, and 19 from four organ donors. Results: Liver disease patients had a median immature fibrosis of 40% (interquartile range [IQR] 20-60) and mature fibrosis of 30% (10%-50%) on histopathology. The organ donor livers had a median fibrosis (both mature and immature) of 10% (IQR 5%-15%). Using machine learning, this study detected presence of cirrhosis and METAVIR grade of fibrosis with a classification accuracy of 96.3% and 97.2%, precision of 96.3% and 97.0%, recall of 96.3% and 97.2%, specificity of 95.4% and 98.0% and area under receiver operator curve of 0.977 and 0.999, respectively. Using partial-least square regression machine learning, this study predicted the percentage of both immature (R 2 = 0.842) and mature (R 2 = 0.837) with a low margin of error (root mean square of error of 9.76% and 7.96%, respectively). Conclusion: This study demonstrates that a point-of-care NIRS instrument can accurately detect, quantify and classify liver fibrosis using machine learning.
ABSTRACT
The complex terrain and poor climatic conditions in Bashang area of Hebei Province result in water and soil loss and geological disasters, which pose a serious threat to ecological safety in North China. In order to improve local environmental quality, barren-resistant and fast-growing tree species such as Pinus sylvestris var. mongolica and Larix gmelinii are planted with large areas. However, unreasonable plantation density will lead to inefficient utilization of rainfall and intensify the conflict between forest and water. In this study, we analyzed the effects of five thinning intensities (0, 20%, 40%, 60%, 80%) of P. sylvestris var. mongolica plantation on herbs, litter, soil and overall water-holding capacity, with the aim to provide scientific basis for management of P. sylvestris var. mongolica. The results showed that water-holding rate of herb varied from 47.7% to 90.7%, and that the water-holding capacity of herb decreased with increasing thinning intensity. When the thinning intensity was less than 40%, water-holding capacity decreased slowly, and then decreased rapidly. With the increase of thinning intensity, natural water-holding rate and maximum water-holding rate of undecomposed layer and semi-decomposed layer decreased gradually, with the effective water-holding rate being 60%>40%>20%>80%>0, and the water-holding capacity of semi-decomposed layer being better than that of undecomposed layer. The water-holding capacity of soil decreased gradually with the increases of thinning intensity. Thinning intensity less than 40% promoted water holding capacity. Under different thinning intensities, the total water-holding rate of understory was 8.3%-14.3%, with an order of 20%>0>40%>60%>80%. In view of understory all layers and overall changes, the thinning intensity at 20% in the study area could effectively improve the understory water-holding capacity and achieve better ecological benefits.
