A Phase 4 interventional study of StethoMe AI-enabled digital stethoscope system and Standard IMCI assessment in Pneumonia, Tuberculosis, Pulmonary and Respiratory Tract Infections, sponsored by Johns Hopkins University. Not yet recruiting. Open to participants aged 2 Months to 59 Months. Per ClinicalTrials.gov, last updated 2026-11-10.
Sponsored by Johns Hopkins University · Phase 4, Interventional, and Diagnostic
Pneumonia is the leading infectious cause of death in children under five years of age worldwide, and most of these deaths occur in low- and middle-income countries. In these settings, frontline health workers diagnose pneumonia using the World Health Organization's Integrated Management of Childhood Illness (IMCI) guidelines, which rely mainly on counting how fast a child is breathing and checking for chest indrawing. This approach has saved many lives, but it is not very specific. As a result, many children who actually have self-limiting viral illnesses that do not require antibiotics are nonetheless treated with antibiotics, contributing to the global rise of antimicrobial resistance.
New digital stethoscopes paired with artificial intelligence (AI) can record a child's lung sounds and automatically detect abnormal sounds such as crackles and wheezes with accuracy comparable to physicians. The LaLeLa Lung Study will evaluate whether adding an AI-enabled digital stethoscope to standard IMCI assessment improves the accuracy of pneumonia diagnosis among children aged 2 to 59 months who present with cough and/or difficult breathing at a primary care clinic in Cape Town, South Africa.
The main component (Objective 1) is a randomized, triple-blinded diagnostic accuracy study that will enroll 350 children, randomly assigned in a 1:1 ratio to either IMCI care enhanced by the AI-enabled digital stethoscope or standard IMCI care. An independent panel of physicians, blinded to the AI results and to study-arm assignment, will review each case and serve as the reference standard for determining whether pneumonia was truly present. The investigators hypothesize that IMCI enhanced by the AI stethoscope will diagnose pneumonia more accurately, and target antibiotics more appropriately, than standard IMCI alone. Nested sub-studies will additionally evaluate a second AI stethoscope for tuberculosis detection, a wearable lung-sound and respiratory-rate patch, an automated respiratory-rate monitor, and a smartphone-connected pulse oximeter.
A separate component (Objective 2) is a mixed-methods implementation study at a second clinic that will assess how easily health workers can use these devices, how acceptable the devices are to health workers and caregivers, and how well the devices fit into routine clinic workflows.
Throughout the study, all AI-generated results will remain concealed from clinic staff, study clinicians, and caregivers, so the AI-generated results will not influence the care any child receives. All children continue to receive standard IMCI care. Findings will help inform whether AI-enabled digital auscultation should be integrated into childhood pneumonia care in South Africa and similar low-resource settings, with the goal of improving diagnosis, strengthening antibiotic stewardship, and reducing antimicrobial resistance and child mortality.
Background and Rationale The World Health Organization Integrated Management of Childhood Illness (IMCI) algorithm classifies pneumonia in children with cough and/or difficult breathing primarily on the basis of elevated respiratory rate and chest indrawing. Lung auscultation was historically excluded from IMCI because of its poor reproducibility among non-physician health workers. Since IMCI's introduction, the rollout of Haemophilus influenzae type b and pneumococcal conjugate vaccines has shifted the etiology of childhood lower respiratory infection toward viral pathogens, and placebo-controlled trials indicate that most IMCI-defined non-severe pneumonia is self-limiting. Reliance on respiratory rate alone yields low specificity, driving substantial antibiotic overuse and antimicrobial resistance. AI-enabled digital stethoscopes can reintroduce standardized, objective auscultation by automatically classifying crackles and wheezes with accuracy comparable to expert physicians. The StethoMe device, a CE-marked (EU Class IIa) system using a deep convolutional recurrent neural network trained on more than 25,000 labeled lung-sound recordings, has demonstrated 85-90% agreement with physician reference panels in prior validation and pilot work conducted by the study consortium across multiple low- and middle-income settings.
Overall Study Design The LaLeLa Lung Study comprises two objectives conducted at two primary healthcare facilities in Cape Town, South Africa. Objective 1 is a randomized, triple-blinded, individually allocated diagnostic accuracy study (with nested device-validation sub-studies) evaluating whether IMCI enhanced by an AI-enabled digital stethoscope improves pneumonia diagnostic accuracy and antibiotic targeting relative to standard IMCI. Objective 2 is a mixed-methods, concurrent-triangulation implementation study evaluating usability, acceptability, and fidelity of the digital devices in routine care. The study will enroll a total of approximately 380 participants (350 in Objective 1; up to 30 health workers and caregivers in Objective 2).
Objective 1: Diagnostic Accuracy Study
Objective 1 enrolls 350 children at Site B Clinic, Khayelitsha, randomized 1:1 to IMCI enhanced by the StethoMe AI-enabled digital stethoscope or to standard IMCI care. A computer-generated randomization sequence prepared in advance by the study statistician and implemented through REDCap is used, with stratification by age group (\<1 year and >=1 year) and allocation concealment from enrollment staff. The design is triple-blinded. Caregivers/participants, routine health workers performing IMCI assessments, and study clinicians performing the digital recordings are all blinded to the device's real-time AI classifications, which are permanently disabled on the device interface for field users. The independent physician reference panel is blinded to study arm, AI outputs, and participant identifiers. Only the statistician holds the allocation key. Importantly, AI outputs do not inform clinical care in either arm, and all participants receive identical study procedures and full IMCI-standard care.
After informed consent and screening, each child is first assessed by a routine clinic health worker who documents IMCI findings and management (including antibiotic prescription or referral) on a study case-management form, without access to the digital stethoscope or study-arm allocation. The child then undergoes an independent structured IMCI-based respiratory assessment by a study clinician, who obtains StethoMe lung-sound recordings at four standardized chest positions. The embedded algorithm computes respiratory rate and classifies abnormal sounds in real time, but all outputs remain concealed. Pulse oximetry (Masimo Rad-G or equivalent), lung ultrasound (Butterfly iQ+), and chest radiography are also obtained. Imaging may be shared with the health worker on request but only after the initial treatment decision and is stored in the regional system using study identifiers. Each enrolled child completes a single in-person encounter (anticipated 60 minutes, integrated into routine clinic flow) followed by a telephone outcome assessment at day 7.
Reference diagnoses are established retrospectively by an independent three-physician panel reviewing compiled, de-identified case records (health worker and study-clinician findings, SpO2, imaging, tuberculosis investigations where applicable, treatment, and follow-up status), excluding any AI output. The panel adjudicates in stages. Stage 1 uses clinical information excluding lung sounds and imaging. Stage 2 adds lung sounds. Stage 3 adds imaging. Blinding integrity is maintained through separation of enrollment, assessment, and follow-up personnel and a weekly blinding-compliance checklist verified by the principal investigator. Unblinding occurs only when essential for clinical management and must be authorized by the principal investigator and documented.
Objective 1: Nested Sub-Studies
Two cross-sectional device-validation sub-studies are nested within Objective 1. In the first, a subset of approximately 225 participants has one chest-position recording obtained in parallel with the AI Diagnostics digital stethoscope (a SAHPRA-approved device for tuberculosis detection). Among children with features suggestive of pulmonary tuberculosis, device classifications are recorded but concealed and not used clinically, with additional 28-day telephone follow-up to support a composite microbiological, radiological, and clinical reference standard.
In the second, the first 100 participants enrolled with the study clinician present undergo additional respiratory assessments with the Perin Health Patch multimodal wearable and the ChARM automated respiratory-rate monitor, with paired clinician respiratory-rate counts and conventional auscultation obtained during sequential timed recordings. Study staff remain blinded to all device-generated outputs.
Statistical Considerations and Sample Size Analyses follow a pre-specified Statistical Analysis Plan finalized before unblinding, conducted primarily on a complete-case/per-protocol basis among randomized participants with an available reference diagnosis, with intention-to-treat sensitivity analyses. Diagnostic performance is summarized using sensitivity, specificity, overall accuracy, diagnostic odds ratio, and receiver operating characteristic (ROC) area under the curve, with between-arm comparisons by two-sample tests of proportions and DeLong's test, and adjusted comparisons by multivariable logistic regression (adjusting for age, sex, baseline SpO2, and symptom duration). The primary sample size of 350 (175 per arm) provides 85% power at two-sided alpha = 0.05 to detect a difference in diagnostic accuracy from 0.67 (standard IMCI) to 0.80 (AI-enhanced IMCI), inflated for an anticipated 10% rate of missing or indeterminate reference diagnoses. The nested sub-studies are powered separately for non-inferiority of recording quality (10% margin) and for respiratory-rate agreement (equivalence margin of +/-3 breaths per minute). Enrollment is expected to require approximately 7-13 months depending on seasonal respiratory illness presentation.
Objective 2: Implementation Study Objective 2 is conducted at Delft South Clinic, Delft, using a mixed-methods, concurrent-triangulation design over a four- to six-week controlled-implementation period. Participating health workers use the StethoMe device with its AI interface visible, alongside the Perin Health Patch, the ChARM device, and the Phefumla 2.0 smartphone-connected pulse oximeter. Device outputs are visible but do not drive clinical decision-making. Quantitative data collection comprises structured observation of device-use fidelity (correct chest positions, workflow adherence, time per recording), workflow integration, technical performance (proportion of successful recordings), and post-encounter standardized usability and acceptability surveys (System Usability Scale). The qualitative component comprises semi-structured and in-depth interviews with approximately 5-10 health workers and 5-10 caregivers, purposively sampled and conducted in the participant's preferred language (isiXhosa, English, or Afrikaans), audio-recorded, transcribed, and translated for thematic analysis. Coding follows a hybrid inductive-deductive approach informed by the Consolidated Framework for Implementation Research and the Technology Acceptance Model, with mixed-methods integration via joint-display analysis.
Risk, Data Management, and Oversight Overall participant risk is no more than minimal because no clinical decision is based on the investigational device outputs, which remain concealed in Objective 1. The digital stethoscopes, wearable patch, respiratory-rate monitor, pulse oximeter, and ultrasound are non-invasive, and chest radiography uses standard low-dose pediatric protocols only when clinically indicated. Electronic data, including de-identified lung-sound recordings, are encrypted and stored on secure, password-protected servers hosted by Stellenbosch University, with clinical and acoustic data captured in REDCap. The study is reviewed and approved by the Johns Hopkins University School of Medicine IRB and the Stellenbosch University Health Research Ethics Committee. All study staff complete a multi-day training program with a competency evaluation before enrollment and quarterly refreshers thereafter.
1,564 studies on the registry are indexed under Pneumonia; 265 are open to participants now.
This study's planned enrollment of 350 is above the median of 129 across 975 interventional studies indexed under Pneumonia.
Browse Pneumonia studies →Johns Hopkins University is the lead sponsor of 1,815 studies on the registry; 315 are open to participants now.
Of its 208 completed or terminated interventional studies of FDA-regulated products, 144 (69%) have results posted.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Participants randomized to this arm undergo Integrated Management of Childhood Illness (IMCI) assessment enhanced by the StethoMe AI-enabled digital stethoscope. After the routine health worker IMCI evaluation, a study clinician performs a structured IMCI-based respiratory assessment and obtains digital lung-sound recordings at four standardized chest positions with the StethoMe device. The embedded algorithm computes respiratory rate and classifies abnormal lung sounds (crackles, wheezes) in real time. AI outputs remain concealed from health workers, study staff, and caregivers and do not influence clinical management. The intervention is the StethoMe AI-enabled digital stethoscope, which is applied during a single clinic encounter.
Device: StethoMe AI-enabled digital stethoscope system
Participants randomized to this arm receive standard IMCI assessment per WHO guidelines, in which pneumonia is classified using respiratory rate and chest indrawing without AI-enabled digital auscultation. Routine clinic health workers perform the IMCI evaluation and make all management decisions, including antibiotic prescription or referral. The intervention is the standard IMCI assessment, which is delivered during a single clinic encounter.
Diagnostic Test: Standard IMCI assessment
A CE-marked (EU Class IIa) wireless electronic stethoscope paired with a mobile application and an on-device deep convolutional recurrent neural network trained on more than 25,000 labeled lung-sound recordings. The device captures high-fidelity respiratory sounds, automatically computes respiratory rate, and classifies sounds in real time as normal or abnormal (fine/coarse crackles, high-/low-pitched wheezes), with ambient-noise detection to flag low-quality signals. Recordings are obtained at four standardized chest positions; the algorithm's classifications are generated automatically but the output display is permanently disabled for field users so results stay concealed and do not inform care.
Also known as: StethoMe, AI-enhanced IMCI
The World Health Organization's standardized clinical algorithm for children with cough and/or difficult breathing, in which pneumonia is classified on the basis of age-specific fast breathing and/or chest indrawing in the absence of general danger signs, without digital or AI-assisted auscultation. Conducted by routine clinic health workers using standard equipment, it represents the current WHO-recommended standard of care for outpatient pneumonia assessment.
Also known as: WHO Integrated Management of Childhood Illness, IMCI
Proportion of children correctly classified with Pneumonia (Diagnostic accuracy of pneumonia diagnosis - IMCI enhanced by AI-enabled digital stethoscope vs. standard IMCI)
Accuracy of pneumonia classification (pneumonia: yes/no), defined as the proportion of children correctly classified relative to the blinded independent physician reference-panel diagnosis, summarized by sensitivity, specificity, and overall accuracy. Compares IMCI enhanced by the StethoMe AI-enabled digital stethoscope (elevated respiratory rate plus crackles ± wheeze) with standard IMCI care; between-arm differences assessed by tests of proportions and ROC area under the curve. Index clinic visit (Day 1); reference-standard diagnosis assigned retrospectively, incorporating 7-day follow-up.
Time frame: Index clinic visit (Day 1); 7-day follow-up
Accuracy, sensitivity, specificity, and positive/negative predictive values (Diagnostic accuracy relative to routine health care worker (HCW) diagnosis)
Accuracy, sensitivity, specificity, and positive/negative predictive values of AI-enhanced IMCI compared with the routine HCW pneumonia diagnosis, each evaluated against the physician reference panel. Day 1; reference standard incorporates 7-day follow-up.
Time frame: Day 1, 7-day follow-up
Proportion of correctly indicated antibiotic decisions (Accuracy of antibiotic decision-making)
Proportion of correctly indicated antibiotic decisions (appropriate vs. inappropriate) for AI-enhanced IMCI compared with (a) HCW antibiotic decisions and (b) IMCI guideline-based decisions, using the physician panel's assessment of antibiotic eligibility (yes/no) as reference.Day 1; reference standard incorporates 7-day follow-up.
Time frame: Day 1; 7-day follow-up
Accuracy of pneumonia diagnosis (Expanded lung-sound classification accuracy)
Accuracy of pneumonia diagnosis when any abnormal lung sound detected by the AI algorithm (defined as AI-identified crackle and/or wheeze of any type (coarse or fine crackle, or high or low-pitched wheeze)) is treated as positive, compared with standard IMCI and HCW assessment, against the physician reference panel. Day 1; reference standard incorporates 7-day follow-up
Time frame: Day 1; 7-day follow-up
Agreement between AI lung-sound classification and physician auscultation
Agreement between StethoMe AI classifications (crackle, wheeze, or normal) and expert physician auscultation, reported as raw percentage agreement and Cohen's kappa (including prevalence- and bias-adjusted kappa), at the chest-position and patient levels.
Time frame: Day 1
Proportion of digital recordings successfully obtained and interpretable (Feasibility of digital auscultation)
Proportion of digital recordings successfully obtained and interpretable by the AI algorithm and listening panel,
Time frame: Day 1
Mean time to obtain standardied chest-position recordings (operational metrics of digital auscultation)
Mean time to obtain a complete set of standardized chest-position recordings within routine clinic flow.
Time frame: Day 1
Caregiver-reported chld status
Clinical outcome at 7 day followup: Caregiver-reported child status (improved, unchanged, or worse) at 7 days post-enrollment, summarized by study arm.
Time frame: Day 7
Proportion of routine HCW encounters (HCW fidelity to the IMCI algorithm)
Proportion of routine HCW encounters documenting all clinical variables required to complete a full IMCI pneumonia-algorithm evaluation.
Time frame: Day 1
Proportion of interpretable lung-sound recordings (Recording quality - AI Diagnostics digital stethoscope vs. StethoMe (non-inferiority)
Proportion of interpretable lung-sound recordings (per blinded expert listener) from the AI Diagnostics device compared with the StethoMe device, evaluated for non-inferiority using a 10% margin (nested sub-study, 225 participants).
Time frame: Day 1
Sensitivity, specificity, positive and negative predictive values (Diagnostic accuracy of AI-enabled digital stethoscope for pulmonary tuberculosis)
Sensitivity, specificity, positive and negative predictive values, and overall accuracy of AI Diagnostics tuberculosis detection (yes/no) against a composite reference standard (microbiological, radiological, clinical, and follow-up findings); agreement with routine TB screening assessed by kappa (nested sub-study). Index visit (Day 1); composite reference standard incorporates follow-up through Day 28
Time frame: Index visit (Day 1); follow-up up to Day 28
Agreement of automated respiratory-rate measurement and breath counts
Agreement between clinician-counted respiratory rate and (a) breath counts derived from Perin Health Patch recordings and (b) automated respiratory-rate outputs of the Perin Health Patch and ChARM devices, assessed by Bland-Altman analysis (mean difference, 95% limits of agreement) against an equivalence margin of ±3 breaths/minute (nested sub-study, \~100 participants).
Time frame: Day 1
Proportion of Perin Health Patch lung-sound recordings meeting pre-defined acousic quality criteria (Interpretability of Perin Health Patch lung-sound recordings)
Proportion of Perin Health Patch lung-sound recordings meeting predefined acoustic quality criteria (≥3 complete respiratory cycles), with descriptive sub-classification of adventitial sounds where feasible.
Time frame: Day 1
Correct chest positions - fidelity of digital devices in routine care (Objective 2)
Device-use fidelity (correct chest positions) from structured observation across the StethoMe, Perin Health Patch, ChARM, and Phefumla 2.0 devices.
Time frame: Up to 6 weeks
Percentage of successful recordings - Technical Performance (Objective 2)
Device-use fidelity (percent successful recordings (workflow adherence) from structured observation across the StethoMe, Perin Health Patch, ChARM, and Phefumla 2.0 devices.
Time frame: Up to 6 weeks
Time per consultation recording -Workflow Integration (Objective 2)
Device-use fidelity (time in minutes per recording) from structured observation) across the StethoMe, Perin Health Patch, ChARM, and Phefumla 2.0 devices.
Time frame: Up to 6 weeks
Usability/acceptability of digital devices in routine care (Objective 2)
HCW-reported usability/acceptability (System Usability Scale. Score range 0-100 higher score better usability/acceptability across the StethoMe, Perin Health Patch, ChARM, and Phefumla 2.0 devices.
Time frame: Up to 6 weeks
No study locations are listed for this record.
Plan to share: Yes — De-identified individual participant data (IPD) underlying the results reported in publications from this study, together with a data dictionary, will be made available to qualified researchers for scientific purposes. Shared data will include the de-identified clinical, demographic, diagnostic, and outcome variables and the de-identified digital lung-sound recordings necessary to reproduce published findings. Directly identifying information will be removed in accordance with the study's data-protection procedures. Data will be shared following review of a methodologically sound request and execution of a data use/access agreement, with appropriate oversight from the Johns Hopkins University and Stellenbosch University investigators.
Supporting information: Study protocol, Statistical analysis plan, Informed consent form, Analytic code
Time frame: Data will become available beginning 12 months after publication of the primary results and will remain available for at least 5 years thereafter (or for the retention period of the hosting repository).
Access criteria: Requests should be directed to the principal investigator. Requesting researchers must submit a written proposal with a scientifically sound objective and analysis plan, which will be reviewed by the study investigators and sponsor. Approved requestors must sign a data use/access agreement governing confidentiality, permitted uses, and prohibition of re-identification before any data are released; data use must be consistent with the participants' informed consent and the approving ethics committees.
Start is estimated for Dec 2026; primary completion for Jan 2028, 13 months later.
Of 42 non-industry phase 4 interventional studies under Pneumonia, half reached primary completion within 33 months of starting (the median), counting those still running; a quarter within 21 and three quarters within 43. This study's planned 13 months is below that.
Counting every sponsor, half of 49 studies reached it within 31 months; a quarter within 21 and three quarters within 40.
Start moved once since we started tracking on Sep 25, 2026: Nov 2026 → Dec 2026, on Nov 10, 2026.
Earlier changes are on the record history on ClinicalTrials.gov ↗
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Nov 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.