Raghu Mulukutla

Raghu Mulukutla

Auto-generated profile, based on publicly available information

Raghu Mulukutla

College of Computing, Georgia Institute of Technology, Atlanta, GA, United States

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 March 2020 in JMIR Perioperative Medicine
Verified
Journal Article
Open access
CLCarissa A Low
Carissa A Low
MDMichaela Danko
Michaela Danko
KDKrina C Durica
Krina C Durica
AKAbhineeth Reddy Kunta
Abhineeth Reddy Kunta
RMRaghu Mulukutla
Raghu Mulukutla
JJJohn M. M. Jakicic
John M. M. Jakicic
Background: Sedentary behavior (SB) is common after cancer surgery and may negatively affect recovery and quality of life, but postoperative symptoms such as pain can be a significant barrier to patients achieving recommended physical activity levels. We conducted a single-arm pilot trial evaluating the usability and acceptability of a real-time mobile intervention that detects prolonged SB in the perioperative period and delivers prompts to walk that are tailored to daily self-reported symptom burden. Objective: The aim of this study is to develop and test a mobile technology-supported intervention to reduce SB before and after cancer surgery, and to evaluate the usability and feasibility of the intervention. Methods: A total of 15 patients scheduled for abdominal cancer surgery consented to the study, which involved using a Fitbit smartwatch with a companion smartphone app across the perioperative period (from a minimum of 2 weeks before surgery to 30 days postdischarge). Participants received prompts to walk after any SB that exceeded a prespecified threshold, which varied from day to day based on patient-reported symptom severity. Participants also completed weekly semistructured interviews to collect information on usability, acceptability, and experience using the app and smartphone; in addition, smartwatch logs were examined to assess participant study compliance. Results: Of eligible patients approached, 79% (15/19) agreed to participate. Attrition was low (1/15, 7%) and due to poor health and prolonged hospitalization. Participants rated (0-100) the smartphone and smartwatch apps as very easy (mean 92.3 and 93.2, respectively) and pleasant to use (mean 93.0 and 93.2, respectively). Overall satisfaction with the whole system was 89.9, and the mean System Usability Scale score was 83.8 out of 100. Overall compliance with symptom reporting was 51% (469/927 days), decreasing significantly from before surgery (264/364, 73%) to inpatient recovery (32/143, 22%) and postdischarge (173/420, 41%). Overall Fitbit compliance was 70% (653/927 days) but also declined from before surgery (330/364, 91%) to inpatient (51/143, 36%) and postdischarge (272/420, 65%). Conclusions: Perioperative patients with cancer were willing to use a smartwatch- and smartphone-based real-time intervention to reduce SB, and they rated the apps as very easy and pleasant to use. Compliance with the intervention declined significantly after surgery. The effects of the intervention on postoperative activity patterns, recovery, and quality of life will be evaluated in an ongoing randomized trial.

12 January 2023 in JMIR Perioperative Medicine
Verified
Journal Article
Open access
CLCarissa A Low
Carissa A Low
MDMichaela Danko
Michaela Danko
KDKrina C Durica
Krina C Durica
JVJulio Vega
Julio Vega
MLMeng Li
Meng Li
JJJohn M. M. Jakicic
John M. M. Jakicic
Background: Sedentary behavior (SB) is prevalent after abdominal cancer surgery, and interventions targeting perioperative SB could improve postoperative recovery and outcomes. We conducted a pilot study to evaluate the feasibility and preliminary effects of a real-time mobile intervention that detects and disrupts prolonged SB before and after cancer surgery, relative to a monitoring-only control condition. Objective: Our aim was to evaluate the feasibility and preliminary effects of a perioperative SB intervention on objective activity behavior, patient-reported quality of life and symptoms, and 30-day readmissions. Methods: Patients scheduled for surgery for metastatic gastrointestinal cancer (n=26) were enrolled and randomized to receive either the SB intervention or activity monitoring only. Both groups used a Fitbit smartwatch and companion smartphone app to rate daily symptoms and collect continuous objective activity behavior data starting from at least 10 days before surgery through 30 days post discharge. Participants in the intervention group also received prompts to walk after any SB bout that exceeded a prespecified threshold, with less frequent prompts on days that patients reported more severe symptoms. Participants completed end-of-study ratings of acceptability, and we also examined adherence to assessments and to walking prompts. In addition, we examined effects of the intervention on objective SB and step counts, patient-reported quality of life and depressive and physical symptoms, as well as readmissions. Results: Accrual (74%), retention (88%), and acceptability ratings (mean overall satisfaction 88.5/100, SD 9.1) were relatively high. However, adherence to assessments and engagement with the SB intervention decreased significantly after surgery and did not recover to preoperative levels after postoperative discharge. All participants exhibited significant increases in SB and symptoms and decreases in steps and quality of life after surgery, and participants randomized to the SB intervention unexpectedly had longer maximum SB bouts relative to the control group. No significant benefits of the intervention with regard to activity, quality of life, symptoms, or readmission were observed. Conclusions: Perioperative patients with metastatic gastrointestinal cancer were interested in a real-time SB intervention and rated the intervention as highly acceptable, but engagement with the intervention and with daily symptom and activity monitoring decreased significantly after surgery. There were no significant effects of the intervention on step counts, patient-reported quality of life or symptoms, and postoperative readmissions, and there was an apparent adverse effect on maximum SB. Results highlight the need for additional work to modify the intervention to make reducing SB and engaging with mobile health technology after abdominal cancer surgery more feasible and beneficial. Trial Registration: ClinicalTrials.gov NCT03211806; https://tinyurl.com/3napwkkt

31 October 2025 in JMIR Formative Research
Verified
Journal Article
Open access
YRYiyi Ren
Yiyi Ren
RMRaghu Mulukutla
Raghu Mulukutla
JMJennifer Mankoff
Jennifer Mankoff
ADAnind Dey
Anind Dey
Background: Experiences of unfair treatment on college campuses are linked to adverse mental and physical health outcomes, highlighting the need for interventions. However, detecting such experiences relies mainly on self-reports. No prior research has examined the feasibility of using mobile sensing via smartphones and wearables for the passive detection of these experiences. Objective: This pilot study explores the potential of using passive sensing to detect daily experiences of perceived unfair treatment (PUT) after they occur. It aims to develop and evaluate machine learning models against naive baselines and establish a benchmark for future research. Methods: We analyzed data from 201 undergraduate students collected over two 10-week academic terms in 2018. PUT was self-reported at the daily level via ecological momentary assessment (EMA) surveys, with 413 of 9629 (4.3%) total responses indicating unfair treatment. We implemented two modeling approaches with distinct training schemes: (1) supervised classification models trained in a user-independent manner using data from different individuals, and (2) anomaly detection models trained in a user-dependent manner using historical data from the same individuals. Classification performance was assessed using stratified group 5-fold cross-validation for user-independent models and a chronological train-test split for user-dependent models. Results: Of the 201 study participants, 110 reported experiencing unfair treatment at least once. On average, participants reported unfair treatment in 4.66% of their EMA responses (95% CI 3.13% to 6.19%). User-independent classification models showed mixed performance (AUC-ROC [area under the receiver operating characteristic curve]: 0.546-0.640, AUC-PR [area under the precision-recall curve]: 0.047-0.093, F1-score: 0.070-0.121). Tree-based models, particularly light gradient boosting machine (LightGBM) and Random Forest, outperformed all 3 baselines in AUC-ROC and AUC-PR; LightGBM also improved the F1-score. In comparison, user-dependent anomaly detection models performed better, with the multiday long short-term memory-AE model (50 features, 7-day window) achieving the highest recall (0.830, +73.3%, P<.001) and F1-score (0.391, +24.9%, P<.001) without reducing precision (0.256), and improving AUC-PR by 45.9% and AUC-ROC by 21.6% relative to naive baselines (P<.001). Feature importance analysis identified key behavioral patterns for population-level detection, including increased time spent off campus, elevated evening and nighttime activity, reduced indoor mobility on campus, prolonged screen use, delayed sleep onset, and shorter sleep duration. Conclusions: Mobile sensing shows promise for detecting daily experiences of PUT in college students and identifying associated behavioral patterns. Our findings highlight opportunities for timely interventions through mobile technology to mitigate the impact of these experiences on students’ mental health and well-being.

11 June 2025 in JMIR Preprints
Verified
Preprint
Open access
YRYiyi Ren
Yiyi Ren
RMRaghu Mulukutla
Raghu Mulukutla
JMJennifer Mankoff
Jennifer Mankoff
ADAnind Dey
Anind Dey
BACKGROUND Experiences of unfair treatment on college campuses are linked to adverse mental and physical health outcomes, highlighting the need for interventions. However, detecting such experiences relies mainly on self-reports. No prior research has examined the feasibility of using mobile sensing via smartphones and wearables for the passive detection of these experiences. OBJECTIVE This pilot study explores the potential of using passive sensing to detect daily experiences of perceived unfair treatment (PUT) after they occur. It aims to develop and evaluate machine learning models against naive baselines and establish a benchmark for future research. METHODS We analyzed data from 201 undergraduate students collected over two 10-week academic terms in 2018. PUT was self-reported at the daily level via ecological momentary assessment (EMA) surveys, with 413 of 9629 (4.3%) total responses indicating unfair treatment. We implemented two modeling approaches with distinct training schemes: (1) supervised classification models trained in a user-independent manner using data from different individuals, and (2) anomaly detection models trained in a user-dependent manner using historical data from the same individuals. Classification performance was assessed using stratified group 5-fold cross-validation for user-independent models and a chronological train-test split for user-dependent models. RESULTS Of the 201 study participants, 110 reported experiencing unfair treatment at least once. On average, participants reported unfair treatment in 4.66% of their EMA responses (95% CI 3.13% to 6.19%). User-independent classification models showed mixed performance (AUC-ROC [area under the receiver operating characteristic curve]: 0.546-0.640, AUC-PR [area under the precision-recall curve]: 0.047-0.093, F1-score: 0.070-0.121). Tree-based models, particularly light gradient boosting machine (LightGBM) and Random Forest, outperformed all 3 baselines in AUC-ROC and AUC-PR; LightGBM also improved the F1-score. In comparison, user-dependent anomaly detection models performed better, with the multiday long short-term memory-AE model (50 features, 7-day window) achieving the highest recall (0.830, +73.3%, P<.001) and F1-score (0.391, +24.9%, P<.001) without reducing precision (0.256), and improving AUC-PR by 45.9% and AUC-ROC by 21.6% relative to naive baselines (P<.001). Feature importance analysis identified key behavioral patterns for population-level detection, including increased time spent off campus, elevated evening and nighttime activity, reduced indoor mobility on campus, prolonged screen use, delayed sleep onset, and shorter sleep duration. CONCLUSIONS Mobile sensing shows promise for detecting daily experiences of PUT in college students and identifying associated behavioral patterns. Our findings highlight opportunities for timely interventions through mobile technology to mitigate the impact of these experiences on students’ mental health and well-being.

3 December 2019 in JMIR Preprints
Verified
Preprint
Open access
CLCarissa A Low
Carissa A Low
MDMichaela Danko
Michaela Danko
KDKrina C Durica
Krina C Durica
AKAbhineeth Reddy Kunta
Abhineeth Reddy Kunta
RMRaghu Mulukutla
Raghu Mulukutla
JJJohn M. M. Jakicic
John M. M. Jakicic
BACKGROUND Sedentary behavior (SB) is common after cancer surgery and may negatively affect recovery and quality of life, but postoperative symptoms such as pain can be a significant barrier to patients achieving recommended physical activity levels. We conducted a single-arm pilot trial evaluating the usability and acceptability of a real-time mobile intervention that detects prolonged SB in the perioperative period and delivers prompts to walk that are tailored to daily self-reported symptom burden. OBJECTIVE The aim of this study is to develop and test a mobile technology-supported intervention to reduce SB before and after cancer surgery, and to evaluate the usability and feasibility of the intervention. METHODS A total of 15 patients scheduled for abdominal cancer surgery consented to the study, which involved using a Fitbit smartwatch with a companion smartphone app across the perioperative period (from a minimum of 2 weeks before surgery to 30 days postdischarge). Participants received prompts to walk after any SB that exceeded a prespecified threshold, which varied from day to day based on patient-reported symptom severity. Participants also completed weekly semistructured interviews to collect information on usability, acceptability, and experience using the app and smartphone; in addition, smartwatch logs were examined to assess participant study compliance. RESULTS Of eligible patients approached, 79% (15/19) agreed to participate. Attrition was low (1/15, 7%) and due to poor health and prolonged hospitalization. Participants rated (0-100) the smartphone and smartwatch apps as very easy (mean 92.3 and 93.2, respectively) and pleasant to use (mean 93.0 and 93.2, respectively). Overall satisfaction with the whole system was 89.9, and the mean System Usability Scale score was 83.8 out of 100. Overall compliance with symptom reporting was 51% (469/927 days), decreasing significantly from before surgery (264/364, 73%) to inpatient recovery (32/143, 22%) and postdischarge (173/420, 41%). Overall Fitbit compliance was 70% (653/927 days) but also declined from before surgery (330/364, 91%) to inpatient (51/143, 36%) and postdischarge (272/420, 65%). CONCLUSIONS Perioperative patients with cancer were willing to use a smartwatch- and smartphone-based real-time intervention to reduce SB, and they rated the apps as very easy and pleasant to use. Compliance with the intervention declined significantly after surgery. The effects of the intervention on postoperative activity patterns, recovery, and quality of life will be evaluated in an ongoing randomized trial.