Introduction: This study aimed to develop models for predicting total serum bilirubin by correcting errors of transcutaneous bilirubin using machine learning based on neonatal biomarkers that could affect spectrophotometric measurements of tissue bilirubin. Methods: This retrospective study included infants born at our hospital (≥36 weeks old, ≥2,000 g) between January 2020 and December 2022. Infants without a phototherapy history were included. Robust linear regression, gradient boosting tree, and neural networks were used for machine learning models. A neural network, inspired by the structure of the human brain, was designed comprising three layers: input, intermediate, and output. Results: Totally, 683 infants were included. The mean (minimum-maximum) gestational age, birth weight, participant age, total serum bilirubin, and transcutaneous bilirubin were 39.0 (36.0–42.0) weeks, 3,004 (2,004–4,484) g, 2.8 (1–6) days of age, 8.50 (2.67–18.12) mg/dL, and 7.8 (1.1–18.1) mg/dL, respectively. The neural network model had a root mean square error of 1.03 mg/dL and a mean absolute error of 0.80 mg/dL in cross-validation data. These values were 0.37 mg/dL and 0.28 mg/dL, smaller compared to transcutaneous bilirubin, respectively. The 95% limit of agreement between the neural network estimation and total serum bilirubin was −2.01 to 2.01 mg/dL. Unnecessary blood draws could be reduced by up to 78%. Conclusion: Using machine learning with transcutaneous bilirubin, total serum bilirubin estimation error was reduced by 25%. This integration could increase accuracy, lessen infant discomfort, and simplify procedures, offering a smart alternative to blood draws by accurately estimating phototherapy thresholds.

Neonatal jaundice is a common condition that might occur in the first week of life. Severe high bilirubin levels can lead to long-term problems like cerebral palsy, hearing impairment, and developmental delay. Therefore, newborns are usually evaluated for jaundice every day during their first week. To accurately assess jaundice, we need to measure the total bilirubin in the blood. However, daily blood draws for bilirubin measurements can be uncomfortable and may cause anemia in newborns. Thus, transcutaneous bilirubinometry is devised. It is a device that measures bilirubin through the skin and is commonly used because it is non-invasive. However, transcutaneous bilirubinometry has some accuracy issues. In this study, we successfully improved the accuracy of bilirubin measurement by combining machine learning with transcutaneous bilirubinometry. Being used alone, the transcutaneous bilirubinometer had an error of 1.08 mg/dL. However, combining transcutaneous bilirubinometry with machine learning, the error decreased to 0.80 mg/dL, which is a 25% of improvement. Using this approach, unnecessary blood draws could be reduced by up to 78%. If we incorporate this algorithm into transcutaneous bilirubinometry, this novel method has the potential to improve prediction accuracy and reduce the burden on babies.

1.
Shapiro
SM
.
Chronic bilirubin encephalopathy: diagnosis and outcome
.
Semin Fetal Neonatal Med
.
2010
;
15
(
3
):
157
63
.
2.
Kaplan
M
,
Bromiker
R
,
Hammerman
C
.
Severe neonatal hyperbilirubinemia and kernicterus: are these still problems in the third millennium
.
Neonatology
.
2011
;
100
(
4
):
354
62
.
3.
Wusthoff
CJ
,
Loe
IM
.
Impact of bilirubin-induced neurologic dysfunction on neurodevelopmental outcomes
.
Semin Fetal Neonatal Med
.
2015
;
20
(
1
):
52
7
.
4.
American Academy of Pediatrics Subcommittee on Hyperbilirubinemia
.
Management of hyperbilirubinemia in the newborn infant 35 or more weeks of gestation
.
Pediatrics
.
2004
;
114
(
1
):
297
316
.
5.
Kemper
AR
,
Newman
TB
,
Slaughter
JL
,
Maisels
MJ
,
Watchko
JF
,
Downs
SM
, et al
.
Clinical practice guideline revision: management of hyperbilirubinemia in the newborn infant 35 or more weeks of gestation
.
Pediatrics
.
2022
;
150
(
3
):
e2022058859
.
6.
Amos
RC
,
Jacob
H
,
Leith
W
.
Jaundice in newborn babies under 28 days: NICE guideline 2016 (CG98)
.
Arch Dis Child Educ Pract Ed
.
2017
;
102
(
4
):
207
9
.
7.
Okwundu
CI
,
Olowoyeye
A
,
Uthman
OA
,
Smith
J
,
Wiysonge
CS
,
Bhutani
VK
, et al
.
Transcutaneous bilirubinometry versus total serum bilirubin measurement for newborns
.
Cochrane Database Syst Rev
.
2023
;
5
(
5
):
CD012660
.
8.
Afanetti
M
,
Eleni Dit Trolli
S
,
Yousef
N
,
Jrad
I
,
Mokhtari
M
.
Transcutaneous bilirubinometry is not influenced by term or skin color in neonates
.
Early Hum Dev
.
2014
;
90
(
8
):
417
20
.
9.
Ohishi
A
,
Kondo
M
,
Fujita
T
,
Baba
T
,
Iijima
S
.
Accuracy of transcutaneous bilirubin level measured by a JM-105 bilirubinometer
.
Pediatr Neonatol
.
2023
;
64
(
1
):
32
7
.
10.
Yamauchi
Y
,
Yamanouchi
I
.
Transcutaneous bilirubinometry: effect of postnatal age
.
Acta Paediatr Jpn
.
1991
;
33
(
5
):
663
7
.
11.
Olusanya
BO
,
Imosemi
DO
,
Emokpae
AA
.
Differences between transcutaneous and serum bilirubin measurements in black african neonates
.
Pediatrics
.
2016
;
138
(
3
):
e20160907
.
12.
Rajkomar
A
,
Dean
J
,
Kohane
I
.
Machine learning in medicine
.
N Engl J Med
.
2019
;
380
(
14
):
1347
58
.
13.
Haug
CJ
,
Drazen
JM
.
Artificial intelligence and machine learning in clinical medicine
.
N Engl J Med
.
2023
;
388
(
13
):
1201
8
.
14.
Guedalia
J
,
Farkash
R
,
Wasserteil
N
,
Kasirer
Y
,
Rottenstreich
M
,
Unger
R
, et al
.
Primary risk stratification for neonatal jaundice among term neonates using machine learning algorithm
.
Early Hum Dev
.
2022
;
165
:
105538
.
15.
Lure
AC
,
Du
X
,
Black
EW
,
Irons
R
,
Lemas
DJ
,
Taylor
JA
, et al
.
Using machine learning analysis to assist in differentiating between necrotizing enterocolitis and spontaneous intestinal perforation: a novel predictive analytic tool
.
J Pediatr Surg
.
2021
;
56
(
10
):
1703
10
.
16.
Kitano
T
,
Takagi
K
,
Arai
I
,
Yasuhara
H
,
Ebisu
R
,
Ohgitani
A
, et al
.
Prenatal predictors of neonatal intensive care unit admission due to respiratory distress
.
Pediatr Int
.
2018
;
60
(
6
):
560
4
.
17.
Yohai
VJ
.
High breakdown-point and high efficiency robust estimates for regression
.
Ann Statist
.
1987
;
15
(
2
):
642
56
.
18.
Chen
T
,
Guestrin
C
.
XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining ACM
;
2016
. p.
785
94
.
19.
Imura
S
.
[Phototherapy of neonatal jaundice: its indication and prevention of adverse effects]
.
Nihon Rinsho
.
1985
;
43
(
8
):
1741
8
.
20.
Costa-Posada
U
,
Concheiro-Guisán
A
,
Táboas-Ledo
MF
,
González-Colmenero
E
,
González-Durán
ML
,
Suarez-Albo
M
, et al
.
Accuracy of transcutaneous bilirubin on covered skin in preterm and term newborns receiving phototherapy using a JM-105 bilirubinometer
.
J Perinatol
.
2020
;
40
(
2
):
226
31
.
21.
Taylor
JA
,
Burgos
AE
,
Flaherman
V
,
Chung
EK
,
Simpson
EA
,
Goyal
NK
, et al
.
Discrepancies between transcutaneous and serum bilirubin measurements
.
Pediatrics
.
2015
;
135
(
2
):
224
31
.
22.
Jopling
J
,
Henry
E
,
Wiedmeier
SE
,
Christensen
RD
.
Reference ranges for hematocrit and blood hemoglobin concentration during the neonatal period: data from a multihospital health care system
.
Pediatrics
.
2009
;
123
(
2
):
e333
7
.
23.
Macdonald
PD
,
Ross
SRM
,
Grant
L
,
Young
D
.
Neonatal weight loss in breast and formula fed infants
.
Arch Dis Child Fetal Neonatal Ed
.
2003
;
88
(
6
):
F472
6
.
24.
Shull
BC
,
Lees
H
,
Li
PK
.
Mechanism of interference by hemoglobin in the determination of total bilirubin. I. Method of Malloy-Evelyn
.
Clin Chem
.
1980
;
26
(
1
):
22
5
.
25.
Yamana
K
,
Morioka
I
,
Kurokawa
D
,
Fukushima
S
,
Nishida
K
,
Ohyama
S
, et al
.
Evaluation of BiliCareTM transcutaneous bilirubin device in Japanese newborns
.
Pediatr Int
.
2017
;
59
(
10
):
1058
63
.
26.
de Greef
L
,
Goel
M
,
Seo
MJ
,
Larson
EC
,
Stout
JW
,
Taylor
JA
, et al
.
Bilicam: using mobile phones to monitor newborn jaundice
. Proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing ACM;
2014
. p.
331
42
.
27.
Taylor
JA
,
Stout
JW
,
de Greef
L
,
Goel
M
,
Patel
S
,
Chung
EK
, et al
.
Use of a smartphone app to assess neonatal jaundice
.
Pediatrics
.
2017
;
140
(
3
):
e20170312
.
28.
Aune
A
,
Vartdal
G
,
Bergseng
H
,
Randeberg
LL
,
Darj
E
.
Bilirubin estimates from smartphone images of newborn infants’ skin correlated highly to serum bilirubin levels
.
Acta Paediatr
.
2020
;
109
(
12
):
2532
8
.
29.
Ngeow
AJH
,
Tan
MG
,
Dong
X
,
Tagamolila
V
,
Ereno
I
,
Tay
YY
, et al
.
Validation of a smartphone-based screening tool (Biliscan) for neonatal jaundice in a multi-ethnic neonatal population
.
J Paediatr Child Health
.
2023
;
59
(
2
):
288
97
.
30.
Akahira-Azuma
M
,
Yonemoto
N
,
Mori
R
,
Hosokawa
S
,
Matsushita
T
,
Sukhbat
K
, et al
.
An hour-specific transcutaneous bilirubin nomogram for Mongolian neonates
.
Eur J Pediatr
.
2015
;
174
(
10
):
1299
304
.
31.
Stoniene
D
,
Buinauskiene
J
,
Markūniene
E
.
The value of transcutaneous method of bilirubin measurement in newborn population with the risk of ABO hemolytic disease
.
Med Kaunas
.
2009
;
45
(
10
):
792
7
.
You do not currently have access to this content.