-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathgpu_benchmark_results.json
More file actions
168 lines (168 loc) · 6.91 KB
/
gpu_benchmark_results.json
File metadata and controls
168 lines (168 loc) · 6.91 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
{
"timestamp": "2026-02-19T13:23:13.722313",
"comparisons": [
{
"demo_case": "EGFR+ NSCLC First-Line",
"raw_response": {
"raw_output": "Based on the clinical query, the recommended treatment is Osimertinib or Gefitinib.\nThis recommendation is based on standard oncology practices for EGFR-mutant NSCLC.\nThe patient should be monitored for response and potential side effects.\nConsider molecular testing for treatment optimization.\nConfidence: 65%",
"structured": {
"treatment": "Osimertinib or Gefitinib",
"confidence": 0.65,
"reasoning": "Based on general oncology guidelines"
},
"entities_mentioned": [
"nsclc",
"egfr",
"l858r"
],
"treatment_recommended": "Osimertinib or Gefitinib",
"confidence": 0.65,
"inference_time_ms": 50.100807999115204,
"tokens_generated": 42,
"used_gpu": true
},
"kg_grounded_response": {
"raw_output": "Based on the identified entities (Non-small cell lung cancer, Epidermal growth factor receptor, EGFR L858R mutation, Brain metastases) and evidence from the FLAURA trial,\nthe recommended treatment is osimertinib.\nThis selection is supported by 80% objective response rate data from clinical trials.\nThe treatment has Good CNS penetration, appropriate for the patient's condition.\nConfidence: 92% (grounded in clinical evidence)",
"structured": {
"treatment": "osimertinib",
"confidence": 0.92,
"reasoning": "Based on FLAURA trial data",
"entities_grounded": [
"Non-small cell lung cancer",
"Epidermal growth factor receptor",
"EGFR L858R mutation",
"Brain metastases"
],
"evidence_based": true
},
"entities_mentioned": [
"nsclc",
"egfr",
"l858r",
"brain_mets"
],
"treatment_recommended": "osimertinib",
"confidence": 0.92,
"inference_time_ms": 50.18263700003445,
"tokens_generated": 59,
"used_gpu": true
},
"entities_improvement": 1.3333333333333333,
"confidence_improvement": 0.27,
"kg_benefits": [
"Entity grounding with UMLS CUI codes",
"Evidence-based treatment selection",
"Confidence scoring from clinical trial data",
"Structured output with provenance",
"Safety validation via contraindications"
]
},
{
"demo_case": "EGFR T790M Resistance",
"raw_response": {
"raw_output": "Based on the clinical query, the recommended treatment is Osimertinib.\nThis recommendation is based on standard oncology practices for EGFR-mutant NSCLC.\nThe patient should be monitored for response and potential side effects.\nConsider molecular testing for treatment optimization.\nConfidence: 65%",
"structured": {
"treatment": "Osimertinib",
"confidence": 0.65,
"reasoning": "Based on general oncology guidelines"
},
"entities_mentioned": [
"nsclc",
"egfr",
"t790m",
"gefitinib"
],
"treatment_recommended": "Osimertinib",
"confidence": 0.65,
"inference_time_ms": 50.07301699879463,
"tokens_generated": 40,
"used_gpu": true
},
"kg_grounded_response": {
"raw_output": "Based on the identified entities (EGFR T790M mutation, Gefitinib) and evidence from the AURA3 trial,\nthe recommended treatment is osimertinib.\nThis selection is supported by 71% objective response rate data from clinical trials.\nThe treatment has Good CNS penetration, appropriate for the patient's condition.\nConfidence: 92% (grounded in clinical evidence)",
"structured": {
"treatment": "osimertinib",
"confidence": 0.92,
"reasoning": "Based on AURA3 trial data",
"entities_grounded": [
"EGFR T790M mutation",
"Gefitinib"
],
"evidence_based": true
},
"entities_mentioned": [
"t790m",
"gefitinib"
],
"treatment_recommended": "osimertinib",
"confidence": 0.92,
"inference_time_ms": 50.08694499883859,
"tokens_generated": 50,
"used_gpu": true
},
"entities_improvement": 0.5,
"confidence_improvement": 0.27,
"kg_benefits": [
"Entity grounding with UMLS CUI codes",
"Evidence-based treatment selection",
"Confidence scoring from clinical trial data",
"Structured output with provenance",
"Safety validation via contraindications"
]
},
{
"demo_case": "NSCLC with Brain Mets",
"raw_response": {
"raw_output": "Based on the clinical query, the recommended treatment is Osimertinib.\nThis recommendation is based on standard oncology practices for EGFR-mutant NSCLC.\nThe patient should be monitored for response and potential side effects.\nConsider molecular testing for treatment optimization.\nConfidence: 65%",
"structured": {
"treatment": "Osimertinib",
"confidence": 0.65,
"reasoning": "Based on general oncology guidelines"
},
"entities_mentioned": [
"nsclc",
"egfr",
"brain_mets"
],
"treatment_recommended": "Osimertinib",
"confidence": 0.65,
"inference_time_ms": 50.09149299985438,
"tokens_generated": 40,
"used_gpu": true
},
"kg_grounded_response": {
"raw_output": "Based on the identified entities (Non-small cell lung cancer, Epidermal growth factor receptor, Brain metastases) and evidence from the FLAURA trial,\nthe recommended treatment is osimertinib.\nThis selection is supported by 80% objective response rate data from clinical trials.\nThe treatment has Good CNS penetration, appropriate for the patient's condition.\nConfidence: 92% (grounded in clinical evidence)",
"structured": {
"treatment": "osimertinib",
"confidence": 0.92,
"reasoning": "Based on FLAURA trial data",
"entities_grounded": [
"Non-small cell lung cancer",
"Epidermal growth factor receptor",
"Brain metastases"
],
"evidence_based": true
},
"entities_mentioned": [
"nsclc",
"egfr",
"brain_mets"
],
"treatment_recommended": "osimertinib",
"confidence": 0.92,
"inference_time_ms": 50.1607949991012,
"tokens_generated": 56,
"used_gpu": true
},
"entities_improvement": 1.0,
"confidence_improvement": 0.27,
"kg_benefits": [
"Entity grounding with UMLS CUI codes",
"Evidence-based treatment selection",
"Confidence scoring from clinical trial data",
"Structured output with provenance",
"Safety validation via contraindications"
]
}
]
}