Ambient artificial intelligence scribe implementation in inpatient setting

{"BACKGROUND:":[0],"Ambient":[1,64,145,214],"artificial":[2],"intelligence":[3],"(AI)":[4],"scribes":[5,36],"have":[6],"shown":[7,21],"promise":[8],"to":[9,149,193,204,232,237,243],"aid":[10],"ambulatory":[11],"clinicians":[12],"with":[13,75,169],"the":[14,23,99],"documentation":[15],"burden,":[16],"but":[17],"little":[18],"has":[19],"been":[20],"about":[22],"inpatient":[24,28,90,178,221,233],"experience.":[25,105],"OBJECTIVE:":[26],"Understand":[27],"physician":[29],"experiences":[30],"before":[31,81],"and":[32,48,61,82,103,109,128,133,155,163],"after":[33,83],"ambient":[34,87,143,245],"AI":[35,65,88,146,215,246],"implementation.":[37,84],"METHODS:":[38],"Quality":[39],"improvement":[40],"pilot":[41],"evaluation":[42],"using":[43],"utilization":[44,136,171,226],"data,":[45],"pre-post":[46],"surveys,":[47],"electronic":[49],"health":[50],"record":[51],"(EHR)":[52],"metrics":[53],"at":[54],"a":[55],"large":[56],"healthcare":[57],"organization":[58],"in":[59,68,72,92,183,247],"northern":[60],"central":[62],"California.":[63],"was":[66,147,188,216,227],"implemented":[67],"acute":[69],"care":[70],"facilities":[71],"March":[73],"2025,":[74],"EHR":[76],"data":[77],"collected":[78],"2":[79],"months":[80],"We":[85],"examined":[86],"usage,":[89],"Time":[91],"Notes":[93],"per":[94,186],"day,":[95],"NASA-TLX":[96],"cognitive":[97],"load,":[98],"mini-Z":[100],"burnout":[101],"question,":[102],"overall":[104,170,225],"McNemar,":[106],"paired":[107,110],"t-test,":[108],"Wilcoxon":[111],"signed-rank":[112],"tests":[113],"were":[114,119],"used.":[115],"RESULTS:":[116],"Fifty-nine":[117],"physicians":[118],"included:":[120],"36":[121],"(61%)":[122],"male,":[123],"28":[124],"(48%)":[125],"adult":[126],"hospitalists,":[127],"20":[129],"completed":[130],"both":[131],"pre-":[132],"post-surveys.":[134],"Monthly":[135],"remained":[137],"relatively":[138],"stable":[139],"(4.2%-3.5%":[140],"notes":[141,184],"by":[142],"AI).":[144],"used":[148,217],"generate":[150],"12%":[151],"(647/5350)":[152],"of":[153,160,166,173],"history":[154],"physical":[156],"notes,":[157,162,168,223],"2%":[158],"(518/245,921)":[159],"progress":[161],"6%":[164],"(33/511)":[165],"consult":[167,222],"rate":[172],"3%":[174],"(1198/46,161)":[175],"across":[176],"all":[177],"note":[179],"types.":[180],"Mean":[181],"time":[182],"(SD)":[185],"day":[187],"unchanged,":[189],"from":[190],"41.9":[191],"(25.59)":[192],"41.6":[194],"(27.3)":[195],"min":[196],"(p":[197],"=":[198],".77).":[199],"Physicians":[200],"requested":[201],"additional":[202],"functionality":[203],"\\"pull":[205],"forward\\"":[206],"or":[207],"add":[208],"onto":[209],"previously":[210],"generated":[211],"notes.":[212],"CONCLUSION:":[213],"most":[218],"consistently":[219],"for":[220],"although":[224],"low.":[228],"Future":[229],"development":[230],"tailored":[231],"workflows":[234],"is":[235],"needed":[236],"increase":[238],"adoption":[239],"as":[240],"organizations":[241],"begin":[242],"expand":[244],"this":[248],"new":[249],"clinical":[250],"setting.":[251]}

Authors

Institutions

Publication Details

Journal
Journal of Hospital Medicine
Published
2026-09-14
DOI
https://doi.org/10.1002/jhm.70451
Primary Topic
Electronic Health Records Systems
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Ambient artificial intelligence scribe implementation in inpatient setting

Joseph Wilcox, Richard C. Liu, Cheryl D. Stults, Sien Deng et al.
Journal of Hospital Medicine
Electronic Health Records Systems
article

Ambient artificial intelligence scribe implementation in inpatient setting

Joseph Wilcox, Richard C. Liu, Cheryl D. Stults, Sien Deng, Stephanie Driscoll, Naveed Rabbani, Nina Szwerinski, Meghan C. Martinez, Jackson Wilde, Veena G. Jones
article en

Abstract

BACKGROUND: Ambient artificial intelligence (AI) scribes have shown promise to aid ambulatory clinicians with the documentation burden, but little has been shown about the inpatient experience. OBJECTIVE: Understand inpatient physician experiences before and after ambient AI scribes implementation. METHODS: Quality improvement pilot evaluation using utilization data, pre-post surveys, and electronic health record (EHR) metrics at a large healthcare organization in northern and central California. Ambient AI was implemented in acute care facilities in March 2025, with EHR data collected 2 months before and after implementation. We examined ambient AI usage, inpatient Time in Notes per day, NASA-TLX cognitive load, the mini-Z burnout question, and overall experience. McNemar, paired t-test, and paired Wilcoxon signed-rank tests were used. RESULTS: Fifty-nine physicians were included: 36 (61%) male, 28 (48%) adult hospitalists, and 20 completed both pre- and post-surveys. Monthly utilization remained relatively stable (4.2%-3.5% notes by ambient AI). Ambient AI was used to generate 12% (647/5350) of history and physical notes, 2% (518/245,921) of progress notes, and 6% (33/511) of consult notes, with overall utilization rate of 3% (1198/46,161) across all inpatient note types. Mean time in notes (SD) per day was unchanged, from 41.9 (25.59) to 41.6 (27.3) min (p = .77). Physicians requested additional functionality to "pull forward" or add onto previously generated notes. CONCLUSION: Ambient AI was used most consistently for inpatient consult notes, although overall utilization was low. Future development tailored to inpatient workflows is needed to increase adoption as organizations begin to expand ambient AI in this new clinical setting.

Journal of Hospital Medicine
Sutter Health (US), Mills Peninsula Health Services (US)
Sutter Health
Partnerships for the goals
Openalex Percentile: Top 4%
Electronic Health Records Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.