SwePub
Tyck till om SwePub Sök här!
Sök i SwePub databas

  Utökad sökning

Träfflista för sökning "WFRF:(Soares J. C.) ;lar1:(liu)"

Sökning: WFRF:(Soares J. C.) > Linköpings universitet

  • Resultat 1-3 av 3
Sortera/gruppera träfflistan
   
NumreringReferensOmslagsbildHitta
1.
  •  
2.
  • Belov, Vladimir, et al. (författare)
  • Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures
  • 2024
  • Ingår i: Scientific Reports. - : NATURE PORTFOLIO. - 2045-2322. ; 14:1
  • Tidskriftsartikel (refereegranskat)abstract
    • Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (N = 5365) to provide a generalizable ML classification benchmark of major depressive disorder (MDD) using shallow linear and non-linear models. Leveraging brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD versus healthy controls (HC) with a balanced accuracy of around 62%. But after harmonizing the data, e.g., using ComBat, the balanced accuracy dropped to approximately 52%. Accuracy results close to random chance levels were also observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may yield more encouraging prospects.
  •  
3.
  • Brown, Dylan R., et al. (författare)
  • Hypersaline tidal flats as important "blue carbon" systems : a case study from three ecosystems
  • 2021
  • Ingår i: Biogeosciences. - : COPERNICUS GESELLSCHAFT MBH. - 1726-4170 .- 1726-4189. ; 18:8, s. 2527-2538
  • Tidskriftsartikel (refereegranskat)abstract
    • Hypersaline tidal flats (HTFs) are coastal ecosystems with freshwater deficits often occurring in arid or semiarid regions near mangrove supratidal zones with no major fluvial contributions. Here, we estimate that organic carbon (OC), total nitrogen (TN) and total phosphorus (TP) were buried at rates averaging 21 (+/- 6), 1.7 (+/- 0.3) and 1.4 (+/- 0.3) gm(-2) yr(-1), respectively, during the previous century in three contrasting HTF systems, one in Brazil (eutrophic) and two in Australia (oligotrophic). Although these rates are lower than those from nearby mangrove, saltmarsh and seagrass systems, the importance of HTFs as sinks for OC, TN and TP may be significant given their extensive coverage. Despite the measured short-term variability between net air-saltpan CO2 influx and emission estimates found during the dry and wet season in the Brazilian HTF, the only site with seasonal CO2 flux measurements, the OC sedimentary profiles over several decades suggest efficient OC burial at all sites. Indeed, the stable isotopes of OC and TN (delta C-13 and delta N-1(5)) along with C : N ratios show that microphytobenthos are the major source of the buried OC in these HTFs. Our findings highlight a previously unquantified carbon as well as a nutrient sink and suggest that coastal HTF ecosystems could be included in the emerging blue carbon framework.
  •  
Skapa referenser, mejla, bekava och länka
  • Resultat 1-3 av 3

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy