Effects of a Differential Diagnosis List of Artificial Intelligence on Differential Diagnoses by Physicians: An Exploratory Analysis of Data from a Randomized Controlled Study

A diagnostic decision support system (DDSS) is expected to reduce diagnostic errors. However, its effect on physicians’ diagnostic decisions remains unclear. Our study aimed to assess the prevalence of diagnoses from artificial intelligence (AI) in physicians’ differential diagnoses when using AI-driven DDSS that generates a differential diagnosis from the information entered by the patient before the clinical encounter on physicians’ differential diagnoses. In this randomized controlled study, an exploratory analysis was performed. Twenty-two physicians were required to generate up to three differential diagnoses per case by reading 16 clinical vignettes. The participants were divided into two groups, an intervention group, and a control group, with and without a differential diagnosis list of AI, respectively. The prevalence of physician diagnosis identical with the differential diagnosis of AI (primary outcome) was significantly higher in the intervention group than in the control group (70.2% vs. 55.1%, p < 0.001). The primary outcome was significantly >10% higher in the intervention group than in the control group, except for attending physicians, and physicians who did not trust AI. This study suggests that at least 15% of physicians’ differential diagnoses were affected by the differential diagnosis list in the AI-driven DDSS.

Download Full-text

Differential Diagnosis Assessment in Ambulatory Care With an Automated Medical History–Taking Device: Pilot Randomized Controlled Trial

JMIR Medical Informatics ◽

10.2196/14044 ◽

2019 ◽

Vol 7 (4) ◽

pp. e14044 ◽

Cited By ~ 2

Author(s):

Adrien Jean-Pierre Schwitzguebel ◽

Clarisse Jeckelmann ◽

Roberto Gavinio ◽

Cécile Levallois ◽

Charles Benaïm ◽

...

Keyword(s):

Randomized Controlled Trial ◽

Differential Diagnosis ◽

Controlled Trial ◽

Intervention Group ◽

Differential Diagnoses ◽

Control Group ◽

History Taking ◽

Randomized Controlled ◽

Diagnosis Accuracy ◽

Pilot Randomized Controlled Trial

Background Automated medical history–taking devices (AMHTDs) are emerging tools with the potential to increase the quality of medical consultations by providing physicians with an exhaustive, high-quality, standardized anamnesis and differential diagnosis. Objective This study aimed to assess the effectiveness of an AMHTD to obtain an accurate differential diagnosis in an outpatient service. Methods We conducted a pilot randomized controlled trial involving 59 patients presenting to an emergency outpatient unit and suffering from various conditions affecting the limbs, the back, and the chest wall. Resident physicians were randomized into 2 groups, one assisted by the AMHTD and one without access to the device. For each patient, physicians were asked to establish an exhaustive differential diagnosis based on the anamnesis and clinical examination. In the intervention group, residents read the AMHTD report before performing the anamnesis. In both the groups, a senior physician had to establish a differential diagnosis, considered as the gold standard, independent of the resident’s opinion and AMHTD report. Results A total of 29 patients were included in the intervention group and 30 in the control group. Differential diagnosis accuracy was higher in the intervention group (mean 75%, SD 26%) than in the control group (mean 59%, SD 31%; P=.01). Subgroup analysis showed a between-group difference of 3% (83% [17/21]-80% [14/17]) for low complexity cases (1-2 differential diagnoses possible) in favor of the AMHTD (P=.76), 31% (87% [13/15]-56% [18/33]) for intermediate complexity (3 differential diagnoses; P=.02), and 24% (63% [34/54]-39% [14/35]) for high complexity (4-5 differential diagnoses; P=.08). Physicians in the intervention group (mean 4.3, SD 2) had more years of clinical practice compared with the control group (mean 5.5, SD 2; P=.03). Differential diagnosis accuracy was negatively correlated to case complexity (r=0.41; P=.001) and the residents’ years of practice (r=0.04; P=.72). The AMHTD was able to determine 73% (SD 30%) of correct differential diagnoses. Patient satisfaction was good (4.3/5), and 26 of 29 patients (90%) considered that they were able to accurately describe their symptomatology. In 8 of 29 cases (28%), residents considered that the AMHTD helped to establish the differential diagnosis. Conclusions The AMHTD allowed physicians to make more accurate differential diagnoses, particularly in complex cases. This could be explained not only by the ability of the AMHTD to make the right diagnoses, but also by the exhaustive anamnesis provided.

Download Full-text

The Use of a Game-Based Decision Aid to Educate Pregnant Women about Prenatal Screening: A Randomized Controlled Study

American Journal of Perinatology ◽

10.1055/s-0038-1667371 ◽

2018 ◽

Vol 36 (03) ◽

pp. 322-328 ◽

Cited By ~ 2

Author(s):

Erin Johnson ◽

Bob Wong ◽

Nancy Rose ◽

Gwen Latendresse ◽

Roger Altizer ◽

...

Keyword(s):

Pregnant Women ◽

Decision Aid ◽

Prenatal Screening ◽

Clinical Care ◽

Intervention Group ◽

Randomized Controlled Study ◽

Constructive Method ◽

Controlled Study ◽

Control Group ◽

Randomized Controlled

Purpose This project developed and evaluated the efficacy of a game decision aid among pregnant women about prenatal screening in a randomized controlled study. Study Design Participants were recruited from an obstetric clinic of an academic urban medical center and randomized (n = 73) to one of two study groups: the control group (n = 39) that used a brochure or the intervention group (n = 34) that also used a game decision aid. Result Participants who played the game had higher knowledge scores (m = 21.41, standard deviation [SD] = 1.74) than participants in the control group (m = 19.59; SD = 3.31), p = 0.004. The median time of game playing was 6:43 minutes (range: 2:17–16:44). The groups were similar in frequency of completing screening after the study, control = 6 (15%) versus intervention = 11 (32%), p = 0.087. However, the more interaction with the game resulted in more positive attitudes toward screening. Conclusion The addition of a game decision aid was effective in educating pregnant women about prenatal screening. As other genetic testing decisions continue to increase within clinical care, game-based decision tools may be a constructive method of informed decision-making.

Download Full-text

Effect of intensive handwashing in the prevention of diarrhoeal illness among patients with AIDS: a randomized controlled study

Journal of Medical Microbiology ◽

10.1099/jmm.0.46867-0 ◽

2007 ◽

Vol 56 (5) ◽

pp. 659-663 ◽

Cited By ~ 28

Author(s):

David B. Huang ◽

Jing Zhou

Keyword(s):

Highly Active Antiretroviral Therapy ◽

Shigella Flexneri ◽

Intervention Group ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Therapy Regimen ◽

Randomized Controlled ◽

Highly Active ◽

Before And After

Patients with AIDS frequently develop diarrhoeal illness. In this randomized, controlled study, 260 patients were screened for those who had not had diarrhoea in the preceding 3 months and who had received a stable highly active antiretroviral therapy regimen for at least 6 weeks prior to the study enrolment. A total of 148 patients met the inclusion criteria and were enrolled: 75 patients were randomly assigned to an intensive handwashing intervention (i.e. handwashing after defecation, after cleaning infants who had defecated, before preparing food, before eating, and before and after sex) and 73 patients were randomly assigned to the control group. Patients in both groups were called weekly by telephone to determine compliance with handwashing and to determine the number of diarrhoeal episodes for the preceding week. Patients were observed for 1 year. Patients assigned to the intensive handwashing intervention group washed their hands more frequently compared with the control group (seven vs four times a day, respectively; P <0.05) and developed fewer episodes of diarrhoeal illness (1.24±0.9 vs 2.92±0.6 new episodes of diarrhoea, respectively; P <0.001) during the 1 year observation. The most common pathogens identified in both groups in patients who developed diarrhoeal illness were Giardia lamblia, Cryptosporidium, Entamoeba histolytica and Shigella flexneri. These data suggest that intensive handwashing reduces diarrhoeal illness in patients with AIDS.

Download Full-text

The Effect of 20-Minute Mindful Breathing on the Perception of Suffering and Changes in Bispectral Index Score (BIS) in Palliative Care Informal Caregivers: A Randomized Controlled Study

American Journal of Hospice and Palliative Medicine® ◽

10.1177/1049909119894507 ◽

2019 ◽

Vol 37 (8) ◽

pp. 606-612 ◽

Cited By ~ 1

Author(s):

Seng Beng Tan ◽

Hui Chi Ching ◽

Yuik Ling Chia ◽

Anne Yee ◽

Chong Guan Ng ◽

...

Keyword(s):

Palliative Care ◽

Bispectral Index ◽

Informal Caregivers ◽

Intervention Group ◽

Index Score ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Randomized Controlled ◽

The University

Informal caregivers are at risk of being overwhelmed by various sources of suffering while caring for their significant others. It is, therefore, important for caregivers to take care of themselves. In the self-care context, mindfulness has the potential to reduce caregiver suffering. We studied the effect of a single session of 20-minute mindful breathing on the perceived level of suffering, together with the changes in bispectral index score (BIS) among palliative care informal caregivers. This was a randomized controlled study conducted at the University of Malaya Medical Centre, Malaysia. Forty adult palliative care informal caregivers were recruited and randomly assigned to either 20-minute mindful breathing or 20-minute supportive listening. The changes in perceived suffering and BIS were measured preintervention and postintervention. The reduction in suffering score in the intervention group was significantly more than the control group at minute 20 ( U = 124.0, n1 = n2 = 20, mean rank1 = 24.30, mean rank2 = 16.70, z = −2.095, P = .036). The reduction in BIS in the intervention group was also significantly greater than the control group at minute 20 ( U = 19.5, n1 = n2 = 20, mean rank1 = 29.52, mean rank2 = 11.48, z = −4.900, P < .0001). Twenty minutes of mindful breathing was more efficacious than 20 minutes of supportive listening in the reduction in suffering among palliative care informal caregivers.

Download Full-text

Evaluation of the Quilting Technique for Reduction of Postmastectomy Seroma: A Randomized Controlled Study

International Journal of Breast Cancer ◽

10.1155/2015/287398 ◽

2015 ◽

Vol 2015 ◽

pp. 1-6 ◽

Cited By ~ 12

Author(s):

Ashraf Khater ◽

Waleed Elnahas ◽

Sameh Roshdy ◽

Omar Farouk ◽

Ahmed Senbel ◽

...

Keyword(s):

Intervention Group ◽

Pathological Finding ◽

Late Complications ◽

Demographic Characteristics ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Wound Drainage ◽

Axillary Clearance ◽

Randomized Controlled

Background. Postmastectomy seroma causes patients’ discomfort, delays starting the adjuvant therapy, and may increase the possibility of surgical site infection.Objective. To evaluate quilting of the mastectomy flaps with obliteration of the axillary space in reducing postmastectomy seroma.Methods. A randomized controlled study was carried out among 120 females who were candidates for mastectomy and axillary clearance. The intervention group (N=60) with quilting and the control group without quilting. All patients were followed up routinely for immediate and late complications.Results. There were no significant differences between the two groups as regards the demographic characteristics, postoperative pathological finding, and the immediate postoperative complications. The incidence of seroma was significantly lower in the intervention group compared with the control group (20% versus 78.3%,P<0.001). Additionally, the intervention group had a shorter duration till seroma resolution (9 days versus 11 days,P<0.001) and a smaller volume of drainage (710 mL versus 1160 mL,P<0.001) compared with the control group.Conclusion. The use of mastectomy with quilting of flaps and obliteration of the axillary space is an efficient method to significantly reduce the postoperative seroma in addition to significantly reducing the duration and volume of wound drainage. Therefore we recommend quilting of flaps as a routine step at the end of any mastectomy.

Download Full-text

Efficacy of Artificial-Intelligence-Driven Differential-Diagnosis List on the Diagnostic Accuracy of Physicians: An Open-Label Randomized Controlled Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18042086 ◽

2021 ◽

Vol 18 (4) ◽

pp. 2086

Author(s):

Yukinori Harada ◽

Shinichi Katsukura ◽

Ren Kawamura ◽

Taro Shimizu

Keyword(s):

Artificial Intelligence ◽

Differential Diagnosis ◽

Diagnostic Accuracy ◽

Medical History ◽

Correct Diagnosis ◽

Medical History Taking ◽

Randomized Controlled Study ◽

Controlled Study ◽

History Taking ◽

Randomized Controlled

Background: The efficacy of artificial intelligence (AI)-driven automated medical-history-taking systems with AI-driven differential-diagnosis lists on physicians’ diagnostic accuracy was shown. However, considering the negative effects of AI-driven differential-diagnosis lists such as omission (physicians reject a correct diagnosis suggested by AI) and commission (physicians accept an incorrect diagnosis suggested by AI) errors, the efficacy of AI-driven automated medical-history-taking systems without AI-driven differential-diagnosis lists on physicians’ diagnostic accuracy should be evaluated. Objective: The present study was conducted to evaluate the efficacy of AI-driven automated medical-history-taking systems with or without AI-driven differential-diagnosis lists on physicians’ diagnostic accuracy. Methods: This randomized controlled study was conducted in January 2021 and included 22 physicians working at a university hospital. Participants were required to read 16 clinical vignettes in which the AI-driven medical history of real patients generated up to three differential diagnoses per case. Participants were divided into two groups: with and without an AI-driven differential-diagnosis list. Results: There was no significant difference in diagnostic accuracy between the two groups (57.4% vs. 56.3%, respectively; p = 0.91). Vignettes that included a correct diagnosis in the AI-generated list showed the greatest positive effect on physicians’ diagnostic accuracy (adjusted odds ratio 7.68; 95% CI 4.68–12.58; p < 0.001). In the group with AI-driven differential-diagnosis lists, 15.9% of diagnoses were omission errors and 14.8% were commission errors. Conclusions: Physicians’ diagnostic accuracy using AI-driven automated medical history did not differ between the groups with and without AI-driven differential-diagnosis lists.

Download Full-text

Differential Diagnosis Assessment in Ambulatory Care With an Automated Medical History–Taking Device: Pilot Randomized Controlled Trial (Preprint)

10.2196/preprints.14044 ◽

2019 ◽

Author(s):

Adrien Jean-Pierre Schwitzguebel ◽

Clarisse Jeckelmann ◽

Roberto Gavinio ◽

Cécile Levallois ◽

Charles Benaïm ◽

...

Keyword(s):

Randomized Controlled Trial ◽

Differential Diagnosis ◽

Controlled Trial ◽

Intervention Group ◽

Differential Diagnoses ◽

Control Group ◽

History Taking ◽

Randomized Controlled ◽

Diagnosis Accuracy ◽

Pilot Randomized Controlled Trial

BACKGROUND Automated medical history–taking devices (AMHTDs) are emerging tools with the potential to increase the quality of medical consultations by providing physicians with an exhaustive, high-quality, standardized anamnesis and differential diagnosis. OBJECTIVE This study aimed to assess the effectiveness of an AMHTD to obtain an accurate differential diagnosis in an outpatient service. METHODS We conducted a pilot randomized controlled trial involving 59 patients presenting to an emergency outpatient unit and suffering from various conditions affecting the limbs, the back, and the chest wall. Resident physicians were randomized into 2 groups, one assisted by the AMHTD and one without access to the device. For each patient, physicians were asked to establish an exhaustive differential diagnosis based on the anamnesis and clinical examination. In the intervention group, residents read the AMHTD report before performing the anamnesis. In both the groups, a senior physician had to establish a differential diagnosis, considered as the gold standard, independent of the resident’s opinion and AMHTD report. RESULTS A total of 29 patients were included in the intervention group and 30 in the control group. Differential diagnosis accuracy was higher in the intervention group (mean 75%, SD 26%) than in the control group (mean 59%, SD 31%; <italic>P</italic>=.01). Subgroup analysis showed a between-group difference of 3% (83% [17/21]-80% [14/17]) for low complexity cases (1-2 differential diagnoses possible) in favor of the AMHTD (<italic>P</italic>=.76), 31% (87% [13/15]-56% [18/33]) for intermediate complexity (3 differential diagnoses; <italic>P</italic>=.02), and 24% (63% [34/54]-39% [14/35]) for high complexity (4-5 differential diagnoses; <italic>P</italic>=.08). Physicians in the intervention group (mean 4.3, SD 2) had more years of clinical practice compared with the control group (mean 5.5, SD 2; <italic>P</italic>=.03). Differential diagnosis accuracy was negatively correlated to case complexity (<italic>r</italic>=0.41; <italic>P</italic>=.001) and the residents’ years of practice (<italic>r</italic>=0.04; <italic>P</italic>=.72). The AMHTD was able to determine 73% (SD 30%) of correct differential diagnoses. Patient satisfaction was good (4.3/5), and 26 of 29 patients (90%) considered that they were able to accurately describe their symptomatology. In 8 of 29 cases (28%), residents considered that the AMHTD helped to establish the differential diagnosis. CONCLUSIONS The AMHTD allowed physicians to make more accurate differential diagnoses, particularly in complex cases. This could be explained not only by the ability of the AMHTD to make the right diagnoses, but also by the exhaustive anamnesis provided.

Download Full-text

The Effect of Exercise on Sleep and Fatigue in Rheumatoid Arthritis: A Randomized Controlled Study

The Journal of Rheumatology ◽

10.3899/jrheum.131282 ◽

2014 ◽

Vol 41 (10) ◽

pp. 1966-1973 ◽

Cited By ~ 45

Author(s):

Laura Durcan ◽

Fiona Wilson ◽

Gaye Cunnane

Keyword(s):

Rheumatoid Arthritis ◽

Sleep Quality ◽

Exercise Intervention ◽

Intervention Group ◽

Exercise Program ◽

Chronic Fatigue ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Randomized Controlled

Objective.Sleep disturbance and chronic fatigue are common in rheumatoid arthritis (RA) and contribute to disability, symptomatology, and healthcare use. It has long been recognized in other populations that exercise can improve sleep and diminish fatigue. The effect of exercise on sleep quality and fatigue in RA has not been evaluated.Methods.Ours is a randomized controlled study in RA to determine the effect of an exercise program on sleep quality and fatigue. These were measured using the Pittsburgh Sleep Quality Index and the Fatigue Severity Scale. Patients were randomized to either a 12-week, home-based exercise intervention or usual care. The exercise program consisted of specific exercises to target individual deficiencies identified using the Health Assessment Questionnaire (HAQ) with cardiovascular work as per the guidelines. The intervention group was evaluated on a 3-week basis. Full evaluation was carried out at baseline and at 12 weeks.Results.Forty patients were randomized to the intervention with 38 controls. In the exercise intervention group, there was a statistically significant improvement in HAQ (p = 0.00), pain (p = 0.05), stiffness (p = 0.05), sleep quality (p = 0.04), and fatigue (p = 0.04). In our control group, there was a statistically significant improvement demonstrated in their overall perceptions of the benefits of exercise, but none of the other variables.Conclusion.Our study demonstrates that an exercise program resulted in significant improvement in sleep quality and fatigue. This is particularly interesting given the importance of fatigue as an outcome measure in RA and gives us yet another reason to prescribe exercise in this population.

Download Full-text

Effect of Tourniquet Use in Ankle Arthroscopic Surgery on Postoperative Recovery: A Prospective Non- Randomized Controlled Study

10.21203/rs.3.rs-89991/v1 ◽

2020 ◽

Author(s):

Tingting Huang ◽

Haixiao Liu ◽

Yuezheng Hu ◽

Xinxian Xu

Keyword(s):

Functional Outcome ◽

Ischemia Reperfusion Injury ◽

Ischemia Reperfusion ◽

Arthroscopic Surgery ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Complication Rates ◽

Randomized Controlled ◽

The Mean

Abstract The aim of this prospective non- randomized controlled study was to explore the effect of tourniquet use on joint swelling, pain, functional outcome, and tourniquet- related ischemia- reperfusion injury (IRI) during ankle arthroscopic surgery.52 patients who received ankle arthroscopy were allocated to had the procedure done with the tourniquet inflated (the Control group, n= 27) or without the tourniquet inflated (the NT group, n= 25). The main outcome measures were: (1) The amount of swelling of the ankle; (2) Pain as measured by a visual analog scale (VAS); (3) The levels of MDA, IMA,TOS, TAS and OSI at 10 min before incision (T1)，after the completion of surgery (T2), and 30 min after tourniquet deflation (T3); (4) The functional outcome as measured by American Orthopaedic Foot and Ankle Society (AOFAS) ankle hindfoot score; (5) The rate of complication. All patients were reviewed at a mean follow- up of 14.2 months (range, 12- 19 months). The mean circumferences of the ankle in the NT group were significantly lower than those in the Control group on postoperative day 2 and 5 (p<0.05). The mean level of VAS in the Control group was significantly higher on postoperative day 2 (p<0.05). The outcomes of AOFAS ankle hindfoot score were comparable between groups postoperatively (p>0.05). The levels of MDA, IMA, TOS and OSI were all significantly lower in the NT group compared at T2 and T3 (p<0.05), and the level of TAS was significantly lower in the NT group at T3 (p<0.05). The complication rates of two groups were comparable (p>0.05).With the use of tourniquet during ankle arthroscopic surgery, there was increased joint swelling and pain postoperatively, and a trend toward increased levels of MDA, IMA, TOS, TAS and OSI intraoperatively. Thus, we do not recommend using a tourniquet in this type of procedure.

Download Full-text

Effectiveness of ultrasound guided ethanol motor points block in reduction of spasticity and improvement of upper limb function in hemiplegic patients: a randomized controlled study

International Journal of Advances in Medicine ◽

10.18203/2349-3933.ijam20203606 ◽

2020 ◽

Vol 7 (9) ◽

pp. 1409

Author(s):

Sreejith C. ◽

Akoijam Joy Singh ◽

Longjam Nilachandra Singh ◽

Kanti Rajkumari ◽

Margaret Chabungbam ◽

...

Keyword(s):

Upper Limb ◽

Randomized Controlled Study ◽

Controlled Study ◽

Control Group ◽

Ultrasound Guided ◽

Limb Function ◽

Ethanol Injection ◽

Randomized Controlled ◽

Upper Limb Function ◽

Group A

Background: Stroke is the third leading cause of disability in general population commonly causing upper motor neuron syndrome complications like spasticity, which is more common in upper limb. Ethanol injection into spastic muscle is an emerging effective treatment in the spasticity management. Ethanol causes selective destruction of nerve fibers through denaturation of protein.Methods: A randomized controlled study was conducted for a period of 2 years from March 2018 on sixty-eight hemiplegic patients to assess the effectiveness of ethanol muscle block in reduction of spasticity and improvement in functional ability. The patients were allocated into two groups (Group A and B). Group A received ultrasound guided intramuscular ethanol injection along with range of motion (ROM) exercises and wrist hand orthosis (WHO) and Group B received ROM exercises and WHO. The outcomes were measured by modified ashworth scale (MAS) for spasticity and modified version of motor assessment scale for functional improvement.Results: Intervention group showed significant improvement in spasticity shown by reduction of MAS of elbow flexors from 3 at baseline to 1.15±0.3 at 12 weeks as compared to control group with 3 at baseline to 1.76±0.5 at 12 weeks (p<0.05). Upper limb function scale of study group improved from 1.5±0.8 to 3.0±0.6 at 12 weeks compared to control group 1.3±0.8 to 2.8±0.6 (p<0.05).Conclusions: It can thus be concluded that intramuscular injection of ethanol accompanied by wrist hand orthosis have beneficial effect on improvement of spasticity and upper limb function.

Download Full-text