Objective To build a prostate cancer(PCa) risk prediction model based on common clinical indicators to provide a theoretical basis for the diagnosis and treatment of PCa and to evaluate the value of artificial intelli...Objective To build a prostate cancer(PCa) risk prediction model based on common clinical indicators to provide a theoretical basis for the diagnosis and treatment of PCa and to evaluate the value of artificial intelligence(AI) technology under healthcare data platforms.Methods After preprocessing of the data from Population Health Data Archive,smuothly clipped absolute deviation(SCAD) was used to select features.Random forest(RF),support vector machine(SVM),back propagation neural network(BP),and convolutional neural network(CNN) were used to predict the risk of PCa,among which BP and CNN were used on the enhanced data by SMOTE.The performances of models were compared using area under the curve(AUC) of the receiving operating characteristic curve.After the optimal model was selected,we used the Shiny to develop an online calculator for PCa risk prediction based on predictive indicators.Results Inorganic phosphorus,triglycerides,and calcium were closely related to PCa in addition to the volume of fragmented tissue and free prostate-specific antigen(PSA).Among the four models,RF had the best performance in predicting PCa(accuracy:96.80%;AUC:0.975,95% CI:0.964-0.986).Followed by BP(accuracy:85.36%;AUC:0.892,95% CI:0.849-0.934) and SVM(accuracy:82.67%;AUC:0.824,95% CI:0.805-0.844).CNN performed worse(accuracy:72.37%;AUC:0.724,95% CI:0.670-0.779).An online platform for PCa risk prediction was developed based on the RF model and the predictive indicators.Conclusions This study revealed the application value of traditional machine learning and deep learning models in disease risk prediction under healthcare data platform,proposed new ideas for PCa risk prediction in patients suspected for PCa and had undergone core needle biopsy.Besides,the online calculation may enhance the practicability of AI prediction technology and facilitate medical diagnosis.展开更多
Sericostaehys seandens is a monocarpic and heliophilous liana, native in tropical African forests. In the montane forests of the Kahuzi-Biega National Park （KBNP） （East of DR Congo）, it has been expanding very str...Sericostaehys seandens is a monocarpic and heliophilous liana, native in tropical African forests. In the montane forests of the Kahuzi-Biega National Park （KBNP） （East of DR Congo）, it has been expanding very strongly for a decade, and is currently considered as having negative impacts on biodiversity conservation. In this paper, we test if S. scandens differs from three co-occurring, native, non spreading lianas （Gouania longispicata, Tacazzea apiculata and Adenia bequaertii） for functional traits which might influence plant expansion. For leaf traits （SLA, dry matter content, nitrogen concentration）, S. scandens did not show extreme values compared to those of the three other lianas. In contrast, S. scandens had much higher biomass allocation to sexual reproduction. It also differs from the three other lianas for its reproductive strategy that combines both vegetative propagation and sexual reproduct/on, and propagule dispersal by wind. Moreover, S. scandens has larger leaves and a greater number of lateral branches per unit stem length. It is argued that the particular combination of functional traits exhibited by S.scandens may in part explain its propensity to behave as an opportunistic weed in the disturbed areas in the montane forests of Kahuzi-Biega.展开更多
Aims Seed dispersal by endozoochory is an important process in plant regeneration and the establishment of new populations.Seeds with dormancy may especially benefit after disperser gut passage.However,the ways in whi...Aims Seed dispersal by endozoochory is an important process in plant regeneration and the establishment of new populations.Seeds with dormancy may especially benefit after disperser gut passage.However,the ways in which gut passage affect the germination of plant species with physiological dormancy remain unclear.Here,we experimentally assessed the mutualistic interaction between the Austral parakeet(Enicognathus ferrugineus)as a disperser of calafate(Berberis microphylla),a thorny bush inhabiting the understory of the Austral temperate forests of South America with seeds that are characterized by deep physiological dormancy.Methods Germination success and viability of calafate seeds obtained from faeces and from intact fruits were tested under four treatments:(i)digested seeds,(ii)digested seeds with faecal extract,(iii)intact seeds from fruit and(iv)intact seeds from fruit with pulp.Important Findings About 65%of the Austral parakeet droppings contained calafate seeds.Viability of seeds did not differ between treatments.However,germination was significantly higher in digested seeds than in intact seeds from fruits,while no difference was found between faecal and pulp extracts.Neither faecal matter nor fruit pulp provided seeds with any ecological advantages derived from enhancing germinability,but did confer some disadvantage in germination time.Faecal matter is expected to be completely lacking around seeds after several months under snow before germinating in the following spring,given intense washing due to persistent rain and the spring thaw in the Patagonian Andes.The higher germinability along with faster germination of digested seeds supports the hypothesis of a legitimate mutualistic interaction between Austral parakeets and calafate.We hypothesized that the passage through the disperser digestive tract might break physiological dormancy as differences in germinability between ingested and non-ingested seeds.Our results highlight the relevant role of endozoochory in plant species with physiological dormancy living in highly seasonal environments.展开更多
文摘Objective To build a prostate cancer(PCa) risk prediction model based on common clinical indicators to provide a theoretical basis for the diagnosis and treatment of PCa and to evaluate the value of artificial intelligence(AI) technology under healthcare data platforms.Methods After preprocessing of the data from Population Health Data Archive,smuothly clipped absolute deviation(SCAD) was used to select features.Random forest(RF),support vector machine(SVM),back propagation neural network(BP),and convolutional neural network(CNN) were used to predict the risk of PCa,among which BP and CNN were used on the enhanced data by SMOTE.The performances of models were compared using area under the curve(AUC) of the receiving operating characteristic curve.After the optimal model was selected,we used the Shiny to develop an online calculator for PCa risk prediction based on predictive indicators.Results Inorganic phosphorus,triglycerides,and calcium were closely related to PCa in addition to the volume of fragmented tissue and free prostate-specific antigen(PSA).Among the four models,RF had the best performance in predicting PCa(accuracy:96.80%;AUC:0.975,95% CI:0.964-0.986).Followed by BP(accuracy:85.36%;AUC:0.892,95% CI:0.849-0.934) and SVM(accuracy:82.67%;AUC:0.824,95% CI:0.805-0.844).CNN performed worse(accuracy:72.37%;AUC:0.724,95% CI:0.670-0.779).An online platform for PCa risk prediction was developed based on the RF model and the predictive indicators.Conclusions This study revealed the application value of traditional machine learning and deep learning models in disease risk prediction under healthcare data platform,proposed new ideas for PCa risk prediction in patients suspected for PCa and had undergone core needle biopsy.Besides,the online calculation may enhance the practicability of AI prediction technology and facilitate medical diagnosis.
基金the Belgian Development Cooperation for the financial help
文摘Sericostaehys seandens is a monocarpic and heliophilous liana, native in tropical African forests. In the montane forests of the Kahuzi-Biega National Park （KBNP） （East of DR Congo）, it has been expanding very strongly for a decade, and is currently considered as having negative impacts on biodiversity conservation. In this paper, we test if S. scandens differs from three co-occurring, native, non spreading lianas （Gouania longispicata, Tacazzea apiculata and Adenia bequaertii） for functional traits which might influence plant expansion. For leaf traits （SLA, dry matter content, nitrogen concentration）, S. scandens did not show extreme values compared to those of the three other lianas. In contrast, S. scandens had much higher biomass allocation to sexual reproduction. It also differs from the three other lianas for its reproductive strategy that combines both vegetative propagation and sexual reproduct/on, and propagule dispersal by wind. Moreover, S. scandens has larger leaves and a greater number of lateral branches per unit stem length. It is argued that the particular combination of functional traits exhibited by S.scandens may in part explain its propensity to behave as an opportunistic weed in the disturbed areas in the montane forests of Kahuzi-Biega.
基金K.S.and S.A.L.were funded by the projects PICT 2015-2072 and PICT 2018-1623.
文摘Aims Seed dispersal by endozoochory is an important process in plant regeneration and the establishment of new populations.Seeds with dormancy may especially benefit after disperser gut passage.However,the ways in which gut passage affect the germination of plant species with physiological dormancy remain unclear.Here,we experimentally assessed the mutualistic interaction between the Austral parakeet(Enicognathus ferrugineus)as a disperser of calafate(Berberis microphylla),a thorny bush inhabiting the understory of the Austral temperate forests of South America with seeds that are characterized by deep physiological dormancy.Methods Germination success and viability of calafate seeds obtained from faeces and from intact fruits were tested under four treatments:(i)digested seeds,(ii)digested seeds with faecal extract,(iii)intact seeds from fruit and(iv)intact seeds from fruit with pulp.Important Findings About 65%of the Austral parakeet droppings contained calafate seeds.Viability of seeds did not differ between treatments.However,germination was significantly higher in digested seeds than in intact seeds from fruits,while no difference was found between faecal and pulp extracts.Neither faecal matter nor fruit pulp provided seeds with any ecological advantages derived from enhancing germinability,but did confer some disadvantage in germination time.Faecal matter is expected to be completely lacking around seeds after several months under snow before germinating in the following spring,given intense washing due to persistent rain and the spring thaw in the Patagonian Andes.The higher germinability along with faster germination of digested seeds supports the hypothesis of a legitimate mutualistic interaction between Austral parakeets and calafate.We hypothesized that the passage through the disperser digestive tract might break physiological dormancy as differences in germinability between ingested and non-ingested seeds.Our results highlight the relevant role of endozoochory in plant species with physiological dormancy living in highly seasonal environments.
