全程呼吸監測
遞增的風險需要即時的警示
臨床風險日益增加，即時警示與麻醉專業醫師的介入，對病患安全至關重要。
全程呼吸監測
遞增的風險需要即時的警示
臨床風險日益增加，即時警示與麻醉專業醫師的介入，對病患安全至關重要。
適用術式
精準應對臨床風險，提升安全與效率。
牙科舒眠鎮靜
牙科舒眠鎮靜
牙科舒眠鎮靜
醫美舒眠療程
醫美舒眠療程
醫美舒眠療程
無痛腸胃道鏡檢
無痛腸胃道鏡檢
無痛腸胃道鏡檢
輻射下鎮靜術式
輻射下鎮靜術式
輻射下鎮靜術式
ECRP、導管術式
ECRP、導管術式
ECRP、導管術式
創新技術產品
AI RESPIRATORY MONITOR
AIRMOD DISPLAY
愛兒默德顯示器（輔助軟體）
愛兒默德智慧呼吸監測軟體是全球首款AI驅動的連續呼吸音監測系統，專為Android設備設計，需搭配電子聽診器使用。 它將呼吸音轉換為視覺化頻譜，讓臨床人員即時監控並分析患者呼吸狀況。內建深度學習演算法，可自動計算呼吸頻率， 異常時發出警示。專用軟體協助快速判讀報告，準確高效。獨特的舒適穿戴設計減輕壓迫感，實現長時間穩定監測， 為醫療人員提供可靠輔助工具。
ELECTRONIC STETHOSCOPE
AS-101
AS-101
AS101聽診器是一款專為醫事人員設計的高效聽診工具， 配備先進的降噪技術，能在吵雜環境中清晰放大心臟、肺部及其他內部器官的聲音。 它包含主機與四個獨立USB-C接口的聽診貼片，使用LED指示燈顯示連接狀態。醫事人員可將聽診貼片固定於患者身上， 隨時切換通道，精確診斷呼吸異常等病症。操作簡便，不需要額外訓練，適用於診所和醫院中的各類身體檢查。
領導品牌，專注呼吸監測AI
AI RESPIRATORY MONITOR
AIRMOD DISPLAY
ELECTRONIC STETHOSCOPE
AS-101
| Better Data Quality | Big Data | Security | Achievement |
|---|---|---|---|
Active Noise Cancellation |
1.6M Labels DL*Deep Learning |
Patient Data |
GRANTED 
DQC 510k |
| Better Data Quality & Usability | Big Data | Achievement | |
|
Active Noise 
Lightweight 
High-fidelity |
Cybersecurity- |
GRANTED
DQC K221805 |
| Candidate N=255 | Bias | Var | 95% CI | p value++ |
|---|---|---|---|---|
| Hypothesis: Bias(airRR)=Bias(capRR) | ||||
| Bias measure | ||||
| (airRR-capRR) | -0.116 | 0.912 | (-0.229,-0.004) | <0.05 |
| Hypothesis: Var(airRR)=Var(capRR) | ||||
| Precision measure | ||||
| SD(airRR)-SD(capRR) | -0.648 | 4.696 | (-1.227,-0.069) | <0.05 |
| ++: Paired Test | ||||
| Response Latency n=130 | mean (sec) | SD (sec) | p value++ | |
| Hypothesis: Airmod = Capnography | ||||
| (Airmod-Capnography)Latency | -16.32 | 21.83 | <0.001 | |
| ++: Paired t Test | FDA submission trial* |
| Better Data Quality | Big Data |
|---|---|
|
Active Noise Cancellation |
1.6M Labels DL*Deep Learning |
| Better Data Quality & Usability | Big Data |
|
Active Noise
Lightweight
High-fidelity |
| Candidate N=255 | Bias |
|---|---|
| Hypothesis: Bias(airRR)=Bias(capRR) | |
| Bias measure | |
| (airRR-capRR) | -0.116 |
| Hypothesis: Var(airRR)=Var(capRR) | |
| Precision measure | |
| SD(airRR)-SD(capRR) | -0.648 |
| ++: Paired Test | |
| Response Latency n=130 | mean (sec) |
| Hypothesis: Airmod = Capnography | |
| (Airmod-Capnography)Latency | -16.32 |
| ++: Paired t Test |
| Security | Achievement |
|---|---|
|
Patient Data |
GRANTED
DQC 510k |
| Achievement | |
|
Cybersecurity- |
GRANTED
DQC K221805 |
| Candidate N=255 | Var |
|---|---|
| Hypothesis: Bias(airRR)=Bias(capRR) | |
| Bias measure | |
| (airRR-capRR) | 0.912 |
| Hypothesis: Var(airRR)=Var(capRR) | |
| Precision measure | |
| SD(airRR)-SD(capRR) | 4.696 |
| ++: Paired Test | |
| Response Latency n=130 | |
| Hypothesis: Airmod = Capnography | |
| (Airmod-Capnography)Latency | |
| ++: Paired t Test |
| Better Data Quality | Big Data |
|---|---|
|
Active Noise Cancellation |
1.6M Labels DL*Deep Learning |
| Better Data Quality & Usability | Big Data |
|
Active Noise
Lightweight
High-fidelity |
| Candidate N=255 | 95% CI |
|---|---|
| Hypothesis: Bias(airRR)=Bias(capRR) | |
| Bias measure | |
| (airRR-capRR) | (-0.229,-0.004) |
| Hypothesis: Var(airRR)=Var(capRR) | |
| Precision measure | |
| SD(airRR)-SD(capRR) | (-1.227,-0.069) |
| ++: Paired Test | |
| Response Latency n=130 | SD (sec) |
| Hypothesis: Airmod = Capnography | |
| (Airmod-Capnography)Latency | 21.83 |
| ++: Paired t Test |
| Security | Achievement |
|---|---|
|
Patient Data |
GRANTED
DQC 510k |
| Achievement | |
|
Cybersecurity- |
GRANTED
DQC K221805 |
| Candidate N=255 | p value++ |
|---|---|
| Hypothesis: Bias(airRR)=Bias(capRR) | |
| Bias measure | |
| (airRR-capRR) | <0.05 |
| Hypothesis: Var(airRR)=Var(capRR) | |
| Precision measure | |
| SD(airRR)-SD(capRR) | <0.05 |
| ++: Paired Test | |
| Response Latency n=130 | p value++ |
| Hypothesis: Airmod = Capnography | |
| (Airmod-Capnography)Latency | <0.001 |
| ++: Paired t Test | FDA submission trial* |