Application of machine learning models on predicting the length of hospital stay in fragility fracture patients

Table 5 Example of a leaderboard of various algorithms using Auto-Sklearn 2.0

Name	model_type	metric_type	metric_value	train_time
[Ensemble]	Ensemble	logloss	0.610714	33.05
[1_DecisionTree]	Decision Tree	logloss	0.647846	38.1
[52_ExtraTrees]	Extra Trees	logloss	0.647803	119.35
[63_NeuralNetwork]	Neural Network	logloss	0.647378	129.13
[2_DecisionTree]	Decision Tree	logloss	0.647368	54.02
[3_DecisionTree]	Decision Tree	logloss	0.647368	60.36
[50_ExtraTrees]	Extra Trees	logloss	0.646168	92.43
[57_NeuralNetwork]	Neural Network	logloss	0.643688	58.06
[60_NeuralNetwork]	Neural Network	logloss	0.643677	94.05
[4_Linear]	Linear	logloss	0.641538	41.21
[65_NeuralNetwork]	Neural Network	logloss	0.640687	150.32
[10_Default_ExtraTrees]	Extra Trees	logloss	0.640079	59.92
[43_RandomForest]	Random Forest	logloss	0.639776	113.87
[41_RandomForest]	Random Forest	logloss	0.63973	93.73
[48_ExtraTrees]	Extra Trees	logloss	0.639579	71.18
[55_ExtraTrees]	Extra Trees	logloss	0.639313	150.11
[59_NeuralNetwork]	Neural Network	logloss	0.63795	82.64
[8_Default_NeuralNetwork]	Neural Network	logloss	0.634294	41.6
[56_ExtraTrees]	Extra Trees	logloss	0.634238	162.46
[54_ExtraTrees]	Extra Trees	logloss	0.634177	143.41
[9_Default_RandomForest]	Random Forest	logloss	0.633282	58.03
[39_RandomForest]	Random Forest	logloss	0.632654	72.66
[58_NeuralNetwork]	Neural Network	logloss	0.632352	71.92
[46_RandomForest]	Random Forest	logloss	0.631393	154.04
[62_NeuralNetwork]	Neural Network	logloss	0.631382	116.89
[61_NeuralNetwork_SelectedFeatures]	Neural Network	logloss	0.630168	170.41
[61_NeuralNetwork]	Neural Network	logloss	0.629733	106.93
[51_ExtraTrees]	Extra Trees	logloss	0.629025	108.55

ISSN: 1472-6947