| Both sides previous revision
Previous revision
Next revision
|
Previous revision
|
chatehr [2026/08/05 09:20]
nigam [Automations] |
chatehr [2026/08/21 15:05] (current)
nigam |
| ChatEHR is a vendor-agnostic, internally governed platform that places the full longitudinal patient record—up to twenty million tokens—directly into a model's context window in real time. It is accessible both through an interface embedded in the EHR (40% usage) and through APIs (60% usage) that automate high-volume rote tasks. This [[https://arxiv.org/abs/2602.00074|ArXiv submission]] describes the usage in the first 3 months of launch. | ChatEHR is a vendor-agnostic, internally governed platform that places the full longitudinal patient record—up to twenty million tokens—directly into a model's context window in real time. It is accessible both through an interface embedded in the EHR (40% usage) and through APIs (60% usage) that automate high-volume rote tasks. |
| | |
| | * [[https://www.nature.com/articles/s41591-026-04574-5 | Nature Medicine]] has a 3 page, human readable article. |
| | * [[https://arxiv.org/abs/2602.00074|ArXiv]] as a 45 page, agent friendly technical report. |
| |
| ===== Automations ===== | ===== Automations ===== |
| |
| |
| * [[https://pulse.stanfordmedicine.org/articles/ai-tool-will-streamline-patient-screening-at-sequoia | Streamlined patient screening]] turns a 5 to 20 minutes chart review for 150 patient charts to roughly 30 highly probable cases. | - [[https://pulse.stanfordmedicine.org/articles/ai-tool-will-streamline-patient-screening-at-sequoia | Streamlined patient screening]] turns a 5 to 20 minutes chart review for 150 patient charts to roughly 30 highly probable cases. |
| * [[https://pulse.stanfordmedicine.org/articles/chatehr-automation-categorizes-surgical-patients-for-better-care-coordination | Identifying patients for surgical co-management]] so that hospitalists focus on the neurosurgery, orthopedics, and ENT patients most likely to need support. | - [[https://pulse.stanfordmedicine.org/articles/chatehr-automation-categorizes-surgical-patients-for-better-care-coordination | Identifying patients for surgical co-management]] lets hospitalists focus on the right neurosurgery, orthopedics, and ENT patients. |
| * [[https://pulse.stanfordmedicine.org/articles/chatehr-automation-supports-enhanced-surveillance-of-surgical-site-infections | Enhanced surveillance of surgical site infections]] reduces the number of patients charts needing a manual review by 40%, and improves the timeliness and accuracy of infection reporting. | * [[https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2853099 | JAMA Netw Open paper by Wang et al]], of a prospective study of ChatEHR to accurately augmented surgical patient triage. |
| * [[https://pulse.stanfordmedicine.org/articles/enterprise-contact-center-launches-chatehr-automation-referral-triage-indexing | Referral triage at the Enterprise Contact Center]], cuts handling time by 17.7%, increased throughput by 17.8%, and reduced backlog from five to two business days. | - [[https://pulse.stanfordmedicine.org/articles/chatehr-automation-supports-enhanced-surveillance-of-surgical-site-infections | Surveillance of surgical site infections]] reduces chart review by 40%, and improves the timeliness of infection reporting. |
| * [[https://pulse.stanfordmedicine.org/articles/how-ai-can-help-identify-eligibility-for-inpatient-hospice | Identifying eligibility for Inpatient Hospice]], screens roughly 600 patient charts to find 10–40 potentially eligible cases to avoid approximately 18–20 hours of work each day. | - [[https://pulse.stanfordmedicine.org/articles/enterprise-contact-center-launches-chatehr-automation-referral-triage-indexing | Referral triage at the Contact Center]], cuts time by 17.7%, raises throughput by 17.8%, and reduced backlog from five to two days. |
| * [[https://pulse.stanfordmedicine.org/articles/orthopedics-launches-chatehr-automation-referral-summary-tool | Accelerated referral triage in Orthopedics]], processes over 4,700 documents and saves at least 1.7 staff hours each day. | - [[https://pulse.stanfordmedicine.org/articles/how-ai-can-help-identify-eligibility-for-inpatient-hospice | Identifying eligibility for Inpatient Hospice]], screens 600 patient charts to find 10–40 eligible cases to avoid 18–20 hours each day. |
| * [[https://pulse.stanfordmedicine.org/articles/patient-financial-services-launches-chatehr-automation-for-billing-review | Review of accounts with an LoA stop bill]], saves 10–15 min/account review to accelerate account resolution and lower underpayment recovery cost. | - [[https://pulse.stanfordmedicine.org/articles/orthopedics-launches-chatehr-automation-referral-summary-tool | Accelerated referral triage in Orthopedics]], processes over 4,700 documents and saves at least 1.7 staff hours each day. |
| | - [[https://pulse.stanfordmedicine.org/articles/patient-financial-services-launches-chatehr-automation-for-billing-review | Review of accounts with an LoA stop bill]], saves 10–15 min/account per resolution and lowers underpayment recovery cost. |
| |
| \\ | \\ |
